Sign up to save your podcasts
Or
Share AI Post Transformers
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
AI Post Transformers
By mcgrofTechnology
AI Post Transformers episodes
- node2vec and Learning Graph EmbeddingsThis episode explores how node2vec adapts the word2vec idea to graphs by learning node embeddings from random walks instead of hand-engineered network features. It explains the core technical move in detail: second-order walks controlled by the `p` and `q` parameters, which bias the sampling process toward more local, BFS-like neighborhoods or more exploratory, DFS-like paths. The discussion highlights the paper’s main claim that this tunable notion of context can capture both homophily and structural roles, while also questioning how strongly the experiments actually prove that flexibility versus simply showing better benchmark performance. Listeners would find it interesting for its clear breakdown of why node2vec became influential: it made graph representation learning feel practical, scalable, and easy to use before modern graph neural methods took over.Sources:1. node2vec: Scalable Feature Learning for Networks — Aditya Grover, Jure Leskovec, 2016http://arxiv.org/abs/1607.006532. DeepWalk: Online Learning of Social Representations — Bryan Perozzi, Rami Al-Rfou, Steven Skiena, 2014https://scholar.google.com/scholar?q=DeepWalk%3A+Online+Learning+of+Social+Representations3. LINE: Large-scale Information Network Embedding — Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Mei, 2015https://scholar.google.com/scholar?q=LINE%3A+Large-scale+Information+Network+Embedding4. node2vec: Scalable Feature Learning for Networks — Aditya Grover, Jure Leskovec, 2016https://scholar.google.com/scholar?q=node2vec%3A+Scalable+Feature+Learning+for+Networks5. Inductive Representation Learning on Large Graphs — William L. Hamilton, Rex Ying, Jure Leskovec, 2017https://scholar.google.com/scholar?q=Inductive+Representation+Learning+on+Large+Graphs6. The PageRank Citation Ranking: Bringing Order to the Web — Lawrence Page, Sergey Brin, Rajeev Motwani, Terry Winograd, 1999https://scholar.google.com/scholar?q=The+PageRank+Citation+Ranking%3A+Bringing+Order+to+the+Web7. Supervised Random Walks: Predicting and Recommending Links in Social Networks — Lars Backstrom, Jure Leskovec, 2011https://scholar.google.com/scholar?q=Supervised+Random+Walks%3A+Predicting+and+Recommending+Links+in+Social+Networks8. Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time — Chantat Eksombatchai, Pranav Jindal, Jerry Zitao Liu, Anand Sharma, Charles Sugnet, Mark Ulrich, Jure Leskovec, 2018https://scholar.google.com/scholar?q=Pixie%3A+A+System+for+Recommending+3%2B+Billion+Items+to+200%2B+Million+Users+in+Real-Time9. The Link-Prediction Problem for Social Networks — David Liben-Nowell, Jon Kleinberg, 2007https://scholar.google.com/scholar?q=The+Link-Prediction+Problem+for+Social+Networks10. Link Prediction Based on Graph Neural Networks — Muhan Zhang, Zhicheng Cui, Marion Neumann, Yixin Chen, 2018https://scholar.google.com/scholar?q=Link+Prediction+Based+on+Graph+Neural+Networks11. Revisiting Semi-Supervised Learning with Graph Embeddings — Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov, 2016https://scholar.google.com/scholar?q=Revisiting+Semi-Supervised+Learning+with+Graph+Embeddings12. Semi-Supervised Classification with Graph Convolutional Networks — Thomas N. Kipf, Max Welling, 2017https://scholar.google.com/scholar?q=Semi-Supervised+Classification+with+Graph+Convolutional+Networks13. word2vec Explained: Deriving Mikolov et al.'s Negative-Sampling Word-Embedding Method — Yoav Goldberg, Omer Levy, 2014https://scholar.google.com/scholar?q=word2vec+Explained%3A+Deriving+Mikolov+et+al.%27s+Negative-Sampling+Word-Embedding+Method14. RolX: Structural Role Extraction and Mining in Large Graphs — Keith Henderson, Brian Gallagher, Tina Eliassi-Rad, Hanghang Tong, S. H. Akoglu, Danai Koutra, Christos Faloutsos, Lei Li, 2012https://scholar.google.com/scholar?q=RolX%3A+Structural+Role+Extraction+and+Mining+in+Large+Graphs15. Role-aware random walk for network embedding — Hegui Zhang, Gang Kou, Yi Peng, Boyu Zhang, 2024https://scholar.google.com/scholar?q=Role-aware+random+walk+for+network+embedding16. WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding — Yanchao Tan, Zihao Zhou, Hang Lv, Weiming Liu, Carl Yang, 2023https://scholar.google.com/scholar?q=WalkLM%3A+A+Uniform+Language+Model+Fine-tuning+Framework+for+Attributed+Graph+Embedding17. INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging — Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, Jianzhong Qi, Chaochao Chen, Longbiao Chen, 2023https://scholar.google.com/scholar?q=INCREASE%3A+Inductive+Graph+Representation+Learning+for+Spatio-Temporal+Kriging18. Graph Condensation for Inductive Node Representation Learning — Xinyi Gao, Tong Chen, Yilong Zang, Wentao Zhang, et al., 2023https://scholar.google.com/scholar?q=Graph+Condensation+for+Inductive+Node+Representation+Learning19. Distributed Graph Embedding with Information-Oriented Random Walks — Peng Fang, Arijit Khan, Siqiang Luo, Fang Wang, et al., 2023https://scholar.google.com/scholar?q=Distributed+Graph+Embedding+with+Information-Oriented+Random+Walks20. AI Post Transformers: GraphSAGE: Inductive Representation Learning on Large Graphs — Hal Turing & Dr. Ada Shannon, Mon,https://podcast.do-not-panic.com/episodes/graphsage-inductive-representation-learning-on-large-graphs/Interactive Visualization: node2vec and Learning Graph Embeddings12 min
- Self-Improving Pretraining With Post-Trained ModelsThis episode explores the idea of “self-improving pretraining,” where already post-trained models are used to shape the pretraining of new models rather than waiting to add safety, reasoning, and factuality later. It explains how the approach rewrites training continuations, uses stronger models as judges, and compares original corpus text, teacher-generated suffixes, and learner rollouts to push model preferences upstream into training. The discussion also situates the paper against earlier work like Constitutional AI, STaR, and Quiet-STaR, while debating whether this is a genuine shift in training philosophy or mainly a more aggressive form of distilling a stronger model’s preferences. Listeners would find it interesting because it gets at a central question in modern AI: whether better behavior can be built into a model’s foundations instead of patched on after the fact.Sources:1. Self-Improving Pretraining: using post-trained models to pretrain better models — Ellen Xiaoqing Tan, Jack Lanchantin, Shehzaad Dhuliawala, Danwei Li, Thao Nguyen, Jing Xu, Ping Yu, Ilia Kulikov, Sainbayar Sukhbaatar, Jason Weston, Xian Li, Olga Golovneva, 2026http://arxiv.org/abs/2601.213432. Constitutional AI: Harmlessness from AI Feedback — Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, et al., 2022https://scholar.google.com/scholar?q=Constitutional+AI%3A+Harmlessness+from+AI+Feedback3. STaR: Self-Taught Reasoner Bootstrapping Reasoning With Reasoning — Eric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. Goodman, and Percy Liang, 2022https://scholar.google.com/scholar?q=STaR%3A+Self-Taught+Reasoner+Bootstrapping+Reasoning+With+Reasoning4. Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking — Eric Zelikman, Yuhuai Wu, Noah D. Goodman, and Jakob Foerster, 2024https://scholar.google.com/scholar?q=Quiet-STaR%3A+Language+Models+Can+Teach+Themselves+to+Think+Before+Speaking5. Self-Rewarding Language Models — Natasha Shumailov, John Adler, Ming-Wei Chang, Sharan Narang, and Yi Tay, 2024https://scholar.google.com/scholar?q=Self-Rewarding+Language+Models6. Confronting Reward Model Overoptimization with Constrained RLHF — Nathan Lambert, Louis Castricato, Leandro von Werra, and Alex Havrilla, 2024https://scholar.google.com/scholar?q=Confronting+Reward+Model+Overoptimization+with+Constrained+RLHF7. On the Diversity of Synthetic Data and its Impact on Training Large Language Models — Hao Chen, Abdul Waheed, Xiang Li, Yidong Wang, Jindong Wang, Bhiksha Raj, Marah I. Abdin, 2024https://scholar.google.com/scholar?q=On+the+Diversity+of+Synthetic+Data+and+its+Impact+on+Training+Large+Language+Models8. In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners — Jaehoon Kim, Kwangwook Seo, Dongha Lee, 2025https://scholar.google.com/scholar?q=In+Their+Own+Words%3A+Reasoning+Traces+Tailored+for+Small+Models+Make+Them+Better+Reasoners9. Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks — William F. Shen, Xinchi Qiu, Chenxi Whitehouse, Lisa Alazraki, Shashwat Goel, Francesco Barbieri, Timon Willi, Akhil Mathur, Ilias Leontiadis, 2026https://scholar.google.com/scholar?q=Rethinking+Rubric+Generation+for+Improving+LLM+Judge+and+Reward+Modeling+for+Open-ended+Tasks10. Ask a Strong LLM Judge when Your Reward Model is Uncertain — Zhenghao Xu, Qin Lu, Qingru Zhang, Liang Qiu, Ilgee Hong, Changlong Yu, Wenlin Yao, Yao Liu, Haoming Jiang, Lihong Li, Hyokun Yun, Tuo Zhao, 2025https://scholar.google.com/scholar?q=Ask+a+Strong+LLM+Judge+when+Your+Reward+Model+is+Uncertain11. FOL-Traces: Verified First-Order Logic Reasoning Traces at Scale — Isabelle Lee, Sarah Liaw, Dani Yogatama, 2025https://scholar.google.com/scholar?q=FOL-Traces%3A+Verified+First-Order+Logic+Reasoning+Traces+at+Scale12. AI Post Transformers: ASI-Evolve for Data, Architectures, and RL — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-05-asi-evolve-for-data-architectures-and-rl-197b2b.mp313. AI Post Transformers: Distilling Multi-Agent Reasoning into a Single LLM — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-22-distilling-multi-agent-reasoning-into-a-143263.mp314. AI Post Transformers: Learning to Reason with 13 Parameters — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-14-learning-to-reason-with-13-parameters-54c87f.mp315. AI Post Transformers: MASA: Meta-Awareness via Self-Alignment Reinforcement Learning — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/masa-meta-awareness-via-self-alignment-reinforcement-learning/16. AI Post Transformers: Kimi K2.5 and Visual Agent Swarms — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-24-kimi-k25-and-visual-agent-swarms-7d04d7.mp3Interactive Visualization: Self-Improving Pretraining With Post-Trained Models16 min
- Selective Classification with Deep Neural NetworksThis episode explores selective classification in deep neural networks: adding a post-hoc reject option so a trained model can abstain when its confidence falls below a calibrated threshold. It explains the key concepts of coverage, selective risk, and the risk-coverage tradeoff, arguing that a model should be judged not just by how often it is right, but by how often it chooses to answer. The discussion centers on the paper’s SGR method, which uses a held-out calibration set to choose a threshold that keeps selective risk below a target with high probability under an i.i.d. assumption, and compares softmax response with MC-dropout as confidence scores. Listeners would find it interesting because it gets at a practical question in AI deployment: not whether a model is always confident, but whether it can reliably know when to defer.Sources:1. Selective Classification for Deep Neural Networks — Yonatan Geifman, Ran El-Yaniv, 2017http://arxiv.org/abs/1705.085002. SelectiveNet: A Deep Neural Network with an Integrated Reject Option — Yonatan Geifman, Ran El-Yaniv, 2019http://arxiv.org/abs/1901.091923. On Optimum Recognition Error and Reject Tradeoff — C. K. Chow, 1970https://scholar.google.com/scholar?q=On+Optimum+Recognition+Error+and+Reject+Tradeoff4. Selective Classification for Deep Neural Networks — Yonatan Geifman and Ran El-Yaniv, 2017https://scholar.google.com/scholar?q=Selective+Classification+for+Deep+Neural+Networks5. SelectiveNet: A Deep Neural Network with an Integrated Reject Option — Yonatan Geifman and Ran El-Yaniv, 2019https://scholar.google.com/scholar?q=SelectiveNet%3A+A+Deep+Neural+Network+with+an+Integrated+Reject+Option6. Selective Classification via One-Sided Prediction — Aditya Gangrade, Anil Kag, and Venkatesh Saligrama, 2021https://scholar.google.com/scholar?q=Selective+Classification+via+One-Sided+Prediction7. Classification with Reject Option — Radu Herbei and Marten H. Wegkamp, 2006https://scholar.google.com/scholar?q=Classification+with+Reject+Option8. Learning with Rejection — Corinna Cortes, Giulia DeSalvo, and Mehryar Mohri, 2016https://scholar.google.com/scholar?q=Learning+with+Rejection9. Boosting with Abstention — Corinna Cortes, Giulia DeSalvo, and Mehryar Mohri, 2016https://scholar.google.com/scholar?q=Boosting+with+Abstention10. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning — Yarin Gal and Zoubin Ghahramani, 2016https://scholar.google.com/scholar?q=Dropout+as+a+Bayesian+Approximation%3A+Representing+Model+Uncertainty+in+Deep+Learning11. On Calibration of Modern Neural Networks — Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger, 2017https://scholar.google.com/scholar?q=On+Calibration+of+Modern+Neural+Networks12. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles — Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell, 2017https://scholar.google.com/scholar?q=Simple+and+Scalable+Predictive+Uncertainty+Estimation+using+Deep+Ensembles13. Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift — Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D. Sculley, Sebastian Nowozin, Joshua Dillon, Balaji Lakshminarayanan, and Jasper Snoek, 2019https://scholar.google.com/scholar?q=Can+You+Trust+Your+Model%27s+Uncertainty%3F+Evaluating+Predictive+Uncertainty+Under+Dataset+Shift14. A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators — Han Zhou, Jordy Van Landeghem, Teodora Popordanoska, and Matthew B. Blaschko, 2025https://scholar.google.com/scholar?q=A+Novel+Characterization+of+the+Population+Area+Under+the+Risk+Coverage+Curve+%28AURC%29+and+Rates+of+Finite+Sample+Estimators15. On the Foundations of Noise-Free Selective Classification — Ran El-Yaniv and Yair Wiener, 2010https://scholar.google.com/scholar?q=On+the+Foundations+of+Noise-Free+Selective+Classification16. Deep Residual Learning for Image Recognition — Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, 2016https://scholar.google.com/scholar?q=Deep+Residual+Learning+for+Image+Recognition17. Support Vector Machines with Embedded Reject Option — Giorgio Fumera and Fabio Roli, 2002https://scholar.google.com/scholar?q=Support+Vector+Machines+with+Embedded+Reject+Option18. A Deep Neural Network with an Integrated Reject Option — Yonatan Geifman and Ran El-Yaniv, 2019https://scholar.google.com/scholar?q=A+Deep+Neural+Network+with+an+Integrated+Reject+Option19. Augmenting the Softmax with Additional Confidence Scores for Improved Selective Classification with Out-of-Distribution Data — Guoxuan Xia, Christos-Savvas Bouganis, 2024https://scholar.google.com/scholar?q=Augmenting+the+Softmax+with+Additional+Confidence+Scores+for+Improved+Selective+Classification+with+Out-of-Distribution+Data20. GPify: Leveraging the Combined Strength of Normalizing Flow and Softmax For an Out-of-Distribution aware Confidence Score — Simon Kristoffersson Lind, Rudolph Triebel, Volker Kruger, 2026https://scholar.google.com/scholar?q=GPify%3A+Leveraging+the+Combined+Strength+of+Normalizing+Flow+and+Softmax+For+an+Out-of-Distribution+aware+Confidence+Score21. LogitAC: Logit Amplitude Constraints for Confidence Calibration and Out-of-Distribution Detection — Zongjing Cao, Yan Li, Byeong Seok Shin, 2024https://scholar.google.com/scholar?q=LogitAC%3A+Logit+Amplitude+Constraints+for+Confidence+Calibration+and+Out-of-Distribution+Detection22. Not all distributional shifts are equal: Fine-grained robust conformal inference — Jiahao Ai, Zhimei Ren, 2024https://scholar.google.com/scholar?q=Not+all+distributional+shifts+are+equal%3A+Fine-grained+robust+conformal+inference23. Wasserstein-regularized Conformal Prediction under General Distribution Shift — Rui Xu, Chao Chen, Yue Sun, Parvathinathan Venkitasubramaniam, Sihong Xie, 2025https://scholar.google.com/scholar?q=Wasserstein-regularized+Conformal+Prediction+under+General+Distribution+ShiftInteractive Visualization: Selective Classification with Deep Neural Networks11 min
- Geometric Memory in Deep Sequence ModelsThis episode explores whether deep sequence models store knowledge as simple associative lookups or as geometric memories that encode broader relational structure. It discusses a recent paper arguing that, after memorizing graph facts in their weights, sequence models can answer multi-hop path queries as if they were making a much shorter move through embedding space, with learned representations resembling graph-embedding methods like node2vec and DeepWalk. The conversation highlights why that matters mechanistically: it suggests some forms of reasoning may be amortized into the model’s parameters during training rather than reconstructed step by step at inference time. Listeners would find it interesting for its sharp debate over what counts as real reasoning versus a clever shortcut, and for its caution about how far results from synthetic graph settings should generalize to large language models in the wild.Sources:1. Deep sequence models tend to memorize geometrically; it is unclear why — Shahriar Noroozizadeh, Vaishnavh Nagarajan, Elan Rosenfeld, Sanjiv Kumar, 2025http://arxiv.org/abs/2510.267452. DeepWalk: Online Learning of Social Representations — Bryan Perozzi, Rami Al-Rfou, Steven Skiena, 2014https://scholar.google.com/scholar?q=DeepWalk%3A+Online+Learning+of+Social+Representations3. node2vec: Scalable Feature Learning for Networks — Aditya Grover, Jure Leskovec, 2016https://scholar.google.com/scholar?q=node2vec%3A+Scalable+Feature+Learning+for+Networks4. Birth of a Transformer: A Memory Viewpoint — Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Herve Jegou, Leon Bottou, 2023https://scholar.google.com/scholar?q=Birth+of+a+Transformer%3A+A+Memory+Viewpoint5. Deep sequence models tend to memorize geometrically; it is unclear why — Shahriar Noroozizadeh, Vaishnavh Nagarajan, Elan Rosenfeld, Sanjiv Kumar, 2025https://scholar.google.com/scholar?q=Deep+sequence+models+tend+to+memorize+geometrically%3B+it+is+unclear+why6. The Pitfalls of Next-Token Prediction — Gregor Bachmann, Vaishnavh Nagarajan, 2024https://scholar.google.com/scholar?q=The+Pitfalls+of+Next-Token+Prediction7. How Transformers Learn to Plan via Multi-Token Prediction — Jianhao Huang, Zhanpeng Zhou, Renqiu Xia, Baharan Mirzasoleiman, Weijie Su, Wei Huang, 2026https://scholar.google.com/scholar?q=How+Transformers+Learn+to+Plan+via+Multi-Token+Prediction8. DeepSeek-V3 Technical Report — DeepSeek-AI and collaborators, 2024https://scholar.google.com/scholar?q=DeepSeek-V3+Technical+Report9. Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More — Arvid Frydenlund, 2025https://scholar.google.com/scholar?q=Language+Models%2C+Graph+Searching%2C+and+Supervision+Adulteration%3A+When+More+Supervision+is+Less+and+How+to+Make+More+More10. Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries — Eden Biran, Daniela Gottesman, Sohee Yang, Mor Geva, and Amir Globerson, 2024https://scholar.google.com/scholar?q=Hopping+Too+Late%3A+Exploring+the+Limitations+of+Large+Language+Models+on+Multi-Hop+Queries11. The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" — Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans, 2024https://scholar.google.com/scholar?q=The+Reversal+Curse%3A+LLMs+trained+on+%22A+is+B%22+fail+to+learn+%22B+is+A%2212. In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval — Matthew Smart, Alberto Bietti, Anirvan M. Sengupta, 2025https://scholar.google.com/scholar?q=In-Context+Denoising+with+One-Layer+Transformers%3A+Connections+between+Attention+and+Associative+Memory+Retrieval13. In-Context Learning as Conditioned Associative Memory Retrieval — Weimin Wu, Teng-Yun Hsiao, Jerry Yao-Chieh Hu, Wenxin Zhang, Han Liu, 2025https://scholar.google.com/scholar?q=In-Context+Learning+as+Conditioned+Associative+Memory+Retrieval14. Position-Aware Relational Transformer for Knowledge Graph Embedding — Guangyao Li, Zequn Sun, Wei Hu, Gong Cheng, et al., 2023https://scholar.google.com/scholar?q=Position-Aware+Relational+Transformer+for+Knowledge+Graph+Embedding15. Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data — Rishabh Ranjan, Valter Hudovernik, Mark Znidar, Charilaos Kanatsoulis, Roshan Upendra, Mahmoud Mohammadi, Joe Meyer, Tom Palczewski, Carlos Guestrin, Jure Leskovec, 2025https://scholar.google.com/scholar?q=Relational+Transformer%3A+Toward+Zero-Shot+Foundation+Models+for+Relational+Data16. AI Post Transformers: In-Place Test-Time Training for Transformers — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-09-in-place-test-time-training-for-transfor-d0b976.mp317. AI Post Transformers: Mamba-3 for Efficient Sequence Modeling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-16-mamba-3-for-efficient-sequence-modeling-97a22a.mp3Interactive Visualization: Geometric Memory in Deep Sequence Models7 min
- Do Language Models Know Their LimitsThis episode explores whether large language models can genuinely recognize the limits of their own knowledge or whether they have simply learned to sound uncertain in socially acceptable ways. It examines the paper’s idea of “self-knowledge” through the lens of confidence calibration, including the dangerous case where a model does not know an answer but responds with unwarranted confidence. The discussion walks through the SelfAware benchmark, explaining how it pairs unanswerable questions with semantically similar answerable ones and why that design is both insightful and methodologically slippery. Listeners would find it interesting because it gets past simple accuracy scores and asks a more consequential question for AI safety and product reliability: when a model says “I don’t know,” is that real judgment or just polished behavior?Sources:1. Do Large Language Models Know What They Don't Know? — Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Xuanjing Huang, 2023http://arxiv.org/abs/2305.181532. Finetuned Language Models Are Zero-Shot Learners — Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew Dai, Quoc V. Le, 2021https://scholar.google.com/scholar?q=Finetuned+Language+Models+Are+Zero-Shot+Learners3. Multitask Prompted Training Enables Zero-Shot Task Generalization — Victor Sanh, Albert Webson, Colin Raffel and many coauthors, 2021https://scholar.google.com/scholar?q=Multitask+Prompted+Training+Enables+Zero-Shot+Task+Generalization4. Training Language Models to Follow Instructions with Human Feedback — Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida and many coauthors, 2022https://scholar.google.com/scholar?q=Training+Language+Models+to+Follow+Instructions+with+Human+Feedback5. Scaling Instruction-Finetuned Language Models — Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, Xuezhi Wang, Denny Zhou, Quoc V. Le, Jason Wei and many coauthors, 2022https://scholar.google.com/scholar?q=Scaling+Instruction-Finetuned+Language+Models6. Self-Instruct: Aligning Language Models with Self-Generated Instructions — Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi, 2023https://scholar.google.com/scholar?q=Self-Instruct%3A+Aligning+Language+Models+with+Self-Generated+Instructions7. Measuring and Improving Factuality in Large Language Models with Calibrated Confidence Scores — Saurav Kadavath, Eric Wallace, Luyu Gao, et al., 2022https://scholar.google.com/scholar?q=Measuring+and+Improving+Factuality+in+Large+Language+Models+with+Calibrated+Confidence+Scores8. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models — Aarohi Srivastava, Jos Rozen, Francesco Tintarev, et al., 2022https://scholar.google.com/scholar?q=Beyond+the+Imitation+Game%3A+Quantifying+and+extrapolating+the+capabilities+of+language+models9. Teaching Small Language Models to Reason — Jason Wei, Xuezhi Wang, Dale Schuurmans, et al., 2022https://scholar.google.com/scholar?q=Teaching+Small+Language+Models+to+Reason10. Self-Consistency Improves Chain of Thought Reasoning in Language Models — Xuezhi Wang, Jason Wei, Dale Schuurmans, et al., 2022https://scholar.google.com/scholar?q=Self-Consistency+Improves+Chain+of+Thought+Reasoning+in+Language+Models11. SimCSE: Simple Contrastive Learning of Sentence Embeddings — Tianyu Gao, Xingcheng Yao, Danqi Chen, 2021https://scholar.google.com/scholar?q=SimCSE%3A+Simple+Contrastive+Learning+of+Sentence+Embeddings12. SQuAD 2.0: The Stanford Question Answering Dataset — Pranav Rajpurkar, Robin Jia, Percy Liang, 2018https://scholar.google.com/scholar?q=SQuAD+2.0%3A+The+Stanford+Question+Answering+Dataset13. Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence — Sophia Hager et al., 2025https://scholar.google.com/scholar?q=Uncertainty+Distillation%3A+Teaching+Language+Models+to+Express+Semantic+Confidence14. Large Language Model Uncertainty Measurement and Calibration for Medical Diagnosis and Treatment — Thomas Savage et al., 2024https://scholar.google.com/scholar?q=Large+Language+Model+Uncertainty+Measurement+and+Calibration+for+Medical+Diagnosis+and+Treatment15. Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey — Xiaoou Liu et al., 2025https://scholar.google.com/scholar?q=Uncertainty+Quantification+and+Confidence+Calibration+in+Large+Language+Models%3A+A+Survey16. Unanswerability Evaluation for Retrieval Augmented Generation — Xiangyu Peng, Prafulla Kumar Choubey, Caiming Xiong, Chien-Sheng Wu, 2025https://scholar.google.com/scholar?q=Unanswerability+Evaluation+for+Retrieval+Augmented+Generation17. Answerability in Retrieval-Augmented Open-Domain Question Answering — Rustam Abdumalikov, Pasquale Minervini, Yova Kementchedjhieva, 2024https://scholar.google.com/scholar?q=Answerability+in+Retrieval-Augmented+Open-Domain+Question+Answering18. The Art of Saying No: Contextual Noncompliance in Language Models — Faeze Brahman et al., 2024https://scholar.google.com/scholar?q=The+Art+of+Saying+No%3A+Contextual+Noncompliance+in+Language+Models19. AI Post Transformers: Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Model — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/hallucination-to-truth-a-review-of-fact-checking-and-factuality-evaluation-in-la/20. AI Post Transformers: Internal Safety Collapse in Frontier LLMs — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-internal-safety-collapse-in-frontier-llm-8be72f.mp321. AI Post Transformers: Self-Search Reinforcement Learning for LLMs — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/self-search-reinforcement-learning-for-llms/22. AI Post Transformers: Real Context Size and Context Rot — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-07-real-context-size-and-context-rot-56cbb4.mp3Interactive Visualization: Do Language Models Know Their Limits12 min
- Fast Speech Recognition by Transcript EditingThis episode explores a speech recognition paper that replaces slow left-to-right transcript generation with a faster draft-and-edit approach, where a speech model produces an initial hypothesis and a bidirectional LLM corrects it in parallel. It explains the tradeoff between CTC-based systems, which are fast but weaker at using linguistic context, and autoregressive decoders, which are more expressive but too slow for low-latency use cases like captioning and meetings. The discussion highlights the paper’s key ideas, including transcript editing with insertion slots, latent alignment inspired by CTC, and the use of LoRA to adapt pretrained language models efficiently. Listeners would find it interesting because it shows a concrete path to pushing ASR onto a better speed-accuracy frontier, with reported gains such as a 27x speedup over an autoregressive baseline while staying competitive on word error rate.Sources:1. NLE: Non-autoregressive LLM-based ASR by Transcript Editing — Avihu Dekel, Samuel Thomas, Takashi Fukada, George Saon, 2026http://arxiv.org/abs/2603.083972. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks — Alex Graves, Santiago Fernandez, Faustino Gomez, Jurgen Schmidhuber, 2006https://scholar.google.com/scholar?q=Connectionist+Temporal+Classification%3A+Labelling+Unsegmented+Sequence+Data+with+Recurrent+Neural+Networks3. Listen, Attend and Spell — William Chan, Navdeep Jaitly, Quoc V. Le, Oriol Vinyals, 2015https://scholar.google.com/scholar?q=Listen%2C+Attend+and+Spell4. Exploring Architectures, Data and Units for Streaming End-to-End Speech Recognition with RNN-Transducer — Hasim Sak, Kanishka Rao, Rohit Prabhavalkar, 2017https://scholar.google.com/scholar?q=Exploring+Architectures%2C+Data+and+Units+for+Streaming+End-to-End+Speech+Recognition+with+RNN-Transducer5. Robust Speech Recognition via Large-Scale Weak Supervision — Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever, 2022https://scholar.google.com/scholar?q=Robust+Speech+Recognition+via+Large-Scale+Weak+Supervision6. Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict — Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi, 2020https://scholar.google.com/scholar?q=Mask+CTC%3A+Non-Autoregressive+End-to-End+ASR+with+CTC+and+Mask+Predict7. Align-Refine: Non-autoregressive Speech Recognition via Iterative Realignment — Ethan A. Chi, Julian Salazar, Katrin Kirchhoff, 2021https://scholar.google.com/scholar?q=Align-Refine%3A+Non-autoregressive+Speech+Recognition+via+Iterative+Realignment8. A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond — Yisheng Xiao, Lijun Wu, Junliang Guo, Juntao Li, Min Zhang, Tao Qin, Tie-Yan Liu, 2022https://scholar.google.com/scholar?q=A+Survey+on+Non-Autoregressive+Generation+for+Neural+Machine+Translation+and+Beyond9. Encode, Tag, Realize: High-Precision Text Editing — Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, Aliaksei Severyn, 2019https://scholar.google.com/scholar?q=Encode%2C+Tag%2C+Realize%3A+High-Precision+Text+Editing10. Levenshtein Transformer — Jiatao Gu, Changhan Wang, Junbo Zhao, 2019https://scholar.google.com/scholar?q=Levenshtein+Transformer11. GECToR - Grammatical Error Correction: Tag, Not Rewrite — Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, Oleksandr Skurzhanskyi, 2020https://scholar.google.com/scholar?q=GECToR+-+Grammatical+Error+Correction%3A+Tag%2C+Not+Rewrite12. FELIX: Flexible Text Editing Through Tagging and Insertion — Jonathan Mallinson, Aliaksei Severyn, Eric Malmi, Guillermo Garrido, 2020https://scholar.google.com/scholar?q=FELIX%3A+Flexible+Text+Editing+Through+Tagging+and+Insertion13. LoRA: Low-Rank Adaptation of Large Language Models — Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, 2021https://scholar.google.com/scholar?q=LoRA%3A+Low-Rank+Adaptation+of+Large+Language+Models14. Token-and-Duration Transducer — Dmitriy Genzel, Yanzhang He, et al., 2023https://scholar.google.com/scholar?q=Token-and-Duration+Transducer15. Mask-Predict: Parallel Decoding of Conditional Masked Language Models — Marjan Ghazvininejad, Omer Levy, Yinhan Liu, Luke Zettlemoyer, 2019https://scholar.google.com/scholar?q=Mask-Predict%3A+Parallel+Decoding+of+Conditional+Masked+Language+Models16. QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache — Rishabh Tiwari, Haocheng Xi, Aditya Tomar, et al., 2025https://scholar.google.com/scholar?q=QuantSpec%3A+Self-Speculative+Decoding+with+Hierarchical+Quantized+KV+Cache17. SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs — Shibo Jie, Yehui Tang, Kai Han, Zhi-Hong Deng, Jing Han, 2025https://scholar.google.com/scholar?q=SpeCache%3A+Speculative+Key-Value+Caching+for+Efficient+Generation+of+LLMs18. SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition — Yichong Leng, Xu Tan, Wenjie Liu, Kaitao Song, Rui Wang, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu, 2022https://scholar.google.com/scholar?q=SoftCorrect%3A+Error+Correction+with+Soft+Detection+for+Automatic+Speech+Recognition19. Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR — W. Ronny Huang, Hao Zhang, Shankar Kumar, Shuo-Yiin Chang, Tara N. Sainath, 2023https://scholar.google.com/scholar?q=Semantic+Segmentation+with+Bidirectional+Language+Models+Improves+Long-form+ASR20. Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR — Yizhou Peng, Hexin Liu, Eng Siong Chng, 2025https://scholar.google.com/scholar?q=Bi-directional+Context-Enhanced+Speech+Large+Language+Models+for+Multilingual+Conversational+ASR21. AI Post Transformers: Qwen3.5-Omni Thinker-Talker for Omnimodal Streaming — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-21-qwen35-omni-thinker-talker-for-omnimodal-36b26c.mp322. AI Post Transformers: Batch-Aware Expert Routing for Faster MoE Decoding — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-batch-aware-expert-routing-for-faster-mo-683ab6.mp3Interactive Visualization: Fast Speech Recognition by Transcript Editing10 min
- CacheFlow and 3D-Parallel KV Cache RestorationThis episode explores CacheFlow, a systems approach to speeding up long-context LLM serving by restoring transformer KV caches more intelligently. It explains the tradeoffs between recomputing prior attention state, loading it from storage, or combining both, and argues that the real user-facing bottleneck is now time-to-first-token rather than raw generation speed. The discussion focuses on CacheFlow’s main idea: a batch-aware scheduler that splits restoration across recomputation and I/O at token, layer, and GPU levels to reduce wasted work under contention. Listeners would find it interesting because it shows how practical transformer serving is increasingly shaped by runtime scheduling, cache movement, and latency engineering rather than new model architectures.Sources:1. CacheFlow and 3D-Parallel KV Cache Restorationhttps://arxiv.org/pdf/2604.250802. Efficient Memory Management for Large Language Model Serving with PagedAttention — Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, Ion Stoica, 2023https://scholar.google.com/scholar?q=Efficient+Memory+Management+for+Large+Language+Model+Serving+with+PagedAttention3. Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention — Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, Pengfei Zuo, 2024https://scholar.google.com/scholar?q=Cost-Efficient+Large+Language+Model+Serving+for+Multi-turn+Conversations+with+CachedAttention4. Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving — Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu, 2024https://scholar.google.com/scholar?q=Mooncake%3A+A+KVCache-centric+Disaggregated+Architecture+for+LLM+Serving5. Fast State Restoration in LLM Serving with HCache — Shiwei Gao, Youmin Chen, Jiwu Shu, 2024https://scholar.google.com/scholar?q=Fast+State+Restoration+in+LLM+Serving+with+HCache6. LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference — Yihua Cheng, Yuhan Liu, Jiayi Yao, Yuwei An, Xiaokun Chen, Shaoting Feng, Yuyang Huang, Samuel Shen, Kuntai Du, Junchen Jiang, 2025https://scholar.google.com/scholar?q=LMCache%3A+An+Efficient+KV+Cache+Layer+for+Enterprise-Scale+LLM+Inference7. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving — Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, Hao Zhang, 2024https://scholar.google.com/scholar?q=DistServe%3A+Disaggregating+Prefill+and+Decoding+for+Goodput-optimized+Large+Language+Model+Serving8. Mooncake: Trading More Storage for Less Computation — A KVCache-centric Architecture for Serving LLM Chatbot — Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu, 2025https://scholar.google.com/scholar?q=Mooncake%3A+Trading+More+Storage+for+Less+Computation+%E2%80%94+A+KVCache-centric+Architecture+for+Serving+LLM+Chatbot9. DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving — Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic, 2024https://scholar.google.com/scholar?q=D%C3%A9j%C3%A0Vu%3A+KV-cache+Streaming+for+Fast%2C+Fault-tolerant+Generative+LLM+Serving10. KV Prediction for Improved Time to First Token — Maxwell Horton, Qingqing Cao, Chenfan Sun, Yanzi Jin, Sachin Mehta, Mohammad Rastegari, Moin Nabi, 2025https://scholar.google.com/scholar?q=KV+Prediction+for+Improved+Time+to+First+Token11. KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing — Yifei Yang et al., 2024https://scholar.google.com/scholar?q=KVSharer%3A+Efficient+Inference+via+Layer-Wise+Dissimilar+KV+Cache+Sharing12. CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing — Yixuan Wang et al., 2025https://scholar.google.com/scholar?q=CommonKV%3A+Compressing+KV+Cache+with+Cross-layer+Parameter+Sharing13. Lossless KV Cache Compression to 2% — Zhen Yang et al., 2024https://scholar.google.com/scholar?q=Lossless+KV+Cache+Compression+to+2%2514. XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference — Weizhuo Li et al., 2024https://scholar.google.com/scholar?q=XKV%3A+Personalized+KV+Cache+Memory+Reduction+for+Long-Context+LLM+Inference15. TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding — Hanshi Sun et al., 2024https://scholar.google.com/scholar?q=TriForce%3A+Lossless+Acceleration+of+Long+Sequence+Generation+with+Hierarchical+Speculative+Decoding16. MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding — Jian Chen, Vashisth Tiwari, Ranajoy Sadhukhan, Zhuoming Chen, Jinyuan Shi, Ian En-Hsu Yen, Beidi Chen, 2024https://scholar.google.com/scholar?q=MagicDec%3A+Breaking+the+Latency-Throughput+Tradeoff+for+Long+Context+Generation+with+Speculative+Decoding17. SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs — Shibo Jie et al., 2025https://scholar.google.com/scholar?q=SpeCache%3A+Speculative+Key-Value+Caching+for+Efficient+Generation+of+LLMs18. Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving — Chao Wang, Pengfei Zuo, Zhangyu Chen, Yunkai Liang, Zhou Yu, Ming-Chang Yang, 2025https://scholar.google.com/scholar?q=Prefill-Decode+Aggregation+or+Disaggregation%3F+Unifying+Both+for+Goodput-Optimized+LLM+Serving19. AI Post Transformers: ContiguousKV for Faster LLM Prefill KV Reuse — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-20-contiguouskv-for-faster-llm-prefill-kv-r-59f545.mp320. AI Post Transformers: ScoutAttention for Efficient KV Cache Offloading — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-24-scoutattention-for-efficient-kv-cache-of-b26699.mp321. AI Post Transformers: Prefill-as-a-Service for Cross-Datacenter KV Cache — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-19-prefill-as-a-service-for-cross-datacente-7560be.mp322. AI Post Transformers: FengHuang for Rack-Scale LLM Inference Memory — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-12-fenghuang-for-rack-scale-llm-inference-m-62708e.mp323. AI Post Transformers: KV Cache TTL for Multi-Turn Agent Scheduling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-09-kv-cache-ttl-for-multi-turn-agent-schedu-996bf1.mp324. AI Post Transformers: Splitwise: Phase-Split LLM Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-03-26-splitwise-phase-split-llm-inference-e8945b.mp325. AI Post Transformers: KVSwap for Disk-Aware Long-Context On-Device Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-16-kvswap-for-disk-aware-long-context-on-de-f3c15e.mp3Interactive Visualization: CacheFlow and 3D-Parallel KV Cache Restoration12 min
- DeltaKV: Compressing KV Caches for Long ContextThis episode explores DeltaKV, a method for reducing the huge GPU memory burden of KV caches in long-context language model inference without simply discarding old tokens. It contrasts three strategies for handling long contexts: token eviction, dynamic sparse attention, and true compression, arguing that the cache contains structured redundancy that can be exploited rather than treated as disposable overhead. The discussion highlights DeltaKV’s core idea of keeping a small uncompressed reference set and storing other cache entries as compressed residuals relative to similar past states, drawing an analogy to delta encoding or version control. Listeners would find it interesting because it connects transformer internals, systems constraints, and practical serving performance, including claims of cutting memory to 29 percent of baseline and reaching up to 2x throughput with supporting infrastructure like Sparse-vLLM.Sources:1. DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity — Jitai Hao, Qiang Huang, Yaowei Wang, Min Zhang, Jun Yu, 2026http://arxiv.org/abs/2602.080052. Generalization through Memorization: Nearest Neighbor Language Models — Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis, 2019https://scholar.google.com/scholar?q=Generalization+through+Memorization%3A+Nearest+Neighbor+Language+Models3. Reformer: The Efficient Transformer — Nikita Kitaev, Lukasz Kaiser, Anselm Levskaya, 2020https://scholar.google.com/scholar?q=Reformer%3A+The+Efficient+Transformer4. Improving Language Models by Retrieving from Trillions of Tokens — Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann and many others, 2021https://scholar.google.com/scholar?q=Improving+Language+Models+by+Retrieving+from+Trillions+of+Tokens5. Memorizing Transformers — Yuhuai Wu, Markus N. Rabe, DeLesley Hutchins, Christian Szegedy, 2022https://scholar.google.com/scholar?q=Memorizing+Transformers6. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving — Yuhan Liu, Hanchen Li, Yihua Cheng and others, 2023https://scholar.google.com/scholar?q=CacheGen%3A+KV+Cache+Compression+and+Streaming+for+Fast+Large+Language+Model+Serving7. Palu: Compressing KV-Cache with Low-Rank Projection — Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin and others, 2024https://scholar.google.com/scholar?q=Palu%3A+Compressing+KV-Cache+with+Low-Rank+Projection8. Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries — Junhyuck Kim, Jongho Park, Jaewoong Cho, Dimitris Papailiopoulos, 2025https://scholar.google.com/scholar?q=Lexico%3A+Extreme+KV+Cache+Compression+via+Sparse+Coding+over+Universal+Dictionaries9. Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models — Alina Shutova, Vladimir Malinovskii, Vage Egiazarian and others, 2025https://scholar.google.com/scholar?q=Cache+Me+If+You+Must%3A+Adaptive+Key-Value+Quantization+for+Large+Language+Models10. OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs — Jitai Hao, Yuke Zhu, Tian Wang, Jun Yu, Xin Xin, Bo Zheng, Zhaochun Ren, Sheng Guo, 2025https://scholar.google.com/scholar?q=OmniKV%3A+Dynamic+Context+Selection+for+Efficient+Long-Context+LLMs11. QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference — Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, Song Han, 2024https://scholar.google.com/scholar?q=QUEST%3A+Query-Aware+Sparsity+for+Efficient+Long-Context+LLM+Inference12. Palu: KV-Cache Compression with Low-Rank Projection — Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin, Chong-Yan Chen, Yu-Fang Hu, Pei-Shuo Wang, Ning-Chi Huang, Luis Ceze, Mohamed S. Abdelfattah, Kai-Chiang Wu, 2025https://scholar.google.com/scholar?q=Palu%3A+KV-Cache+Compression+with+Low-Rank+Projection13. SCBench: A KV Cache-Centric Analysis of Long-Context Methods — Yucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu, 2025https://scholar.google.com/scholar?q=SCBench%3A+A+KV+Cache-Centric+Analysis+of+Long-Context+Methods14. The Pitfalls of KV Cache Compression — Alex Chen, Renato Geh, Aditya Grover, Guy Van den Broeck, Daniel Israel, 2025https://scholar.google.com/scholar?q=The+Pitfalls+of+KV+Cache+Compression15. KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction — Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song, 2025https://scholar.google.com/scholar?q=KVzip%3A+Query-Agnostic+KV+Cache+Compression+with+Context+Reconstruction16. Kvlink: Accelerating Large Language Models via Efficient KV Cache Reuse — approx. recent LLM systems authors, 2025/2026https://scholar.google.com/scholar?q=Kvlink%3A+Accelerating+Large+Language+Models+via+Efficient+KV+Cache+Reuse17. HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse — approx. recent RAG systems authors, 2025/2026https://scholar.google.com/scholar?q=HyperRAG%3A+Enhancing+Quality-Efficiency+Tradeoffs+in+Retrieval-Augmented+Generation+with+Reranker+KV-Cache+Reuse18. ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation — approx. recent RAG/serving authors, 2025/2026https://scholar.google.com/scholar?q=ProphetKV%3A+User-Query-Driven+Selective+Recomputation+for+Efficient+KV+Cache+Reuse+in+Retrieval-Augmented+Generation19. KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs — approx. recent KV quantization authors, 2025/2026https://scholar.google.com/scholar?q=KVSink%3A+Understanding+and+Enhancing+the+Preservation+of+Attention+Sinks+in+KV+Cache+Quantization+for+LLMs20. LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference — approx. recent long-context inference authors, 2025/2026https://scholar.google.com/scholar?q=LLMs+Know+What+to+Drop%3A+Self-Attention+Guided+KV+Cache+Eviction+for+Efficient+Long-Context+Inference21. Task-KV: Task-Aware KV Cache Optimization via Semantic Differentiation of Attention Heads — approx. recent attention/KV optimization authors, 2025/2026https://scholar.google.com/scholar?q=Task-KV%3A+Task-Aware+KV+Cache+Optimization+via+Semantic+Differentiation+of+Attention+Heads22. WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More — approx. recent quantization authors, 2025/2026https://scholar.google.com/scholar?q=WKVQuant%3A+Quantizing+Weight+and+Key%2FValue+Cache+for+Large+Language+Models+Gains+More23. AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization — approx. recent KV systems/quantization authors, 2025/2026https://scholar.google.com/scholar?q=AlignedKV%3A+Reducing+Memory+Access+of+KV-Cache+with+Precision-Aligned+Quantization24. Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off — approx. recent sparse attention authors, 2025/2026https://scholar.google.com/scholar?q=Making+Every+Head+Count%3A+Sparse+Attention+Without+the+Speed-Performance+Trade-off25. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention — approx. recent sparse systems authors, 2025/2026https://scholar.google.com/scholar?q=Native+Sparse+Attention%3A+Hardware-Aligned+and+Natively+Trainable+Sparse+Attention26. AI Post Transformers: Stochastic KV Routing for Cache Sharing — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-29-stochastic-kv-routing-for-cache-sharing-5fef63.mp327. AI Post Transformers: ContiguousKV for Faster LLM Prefill KV Reuse — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-20-contiguouskv-for-faster-llm-prefill-kv-r-59f545.mp328. AI Post Transformers: KVSwap for Disk-Aware Long-Context On-Device Inference — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-16-kvswap-for-disk-aware-long-context-on-de-f3c15e.mp329. AI Post Transformers: Native Sparse Attention: Efficient Long-Context LLMs — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/native-sparse-attention-efficient-long-context-llms/30. AI Post Transformers: Memory Sparse Attention for 100M-Token Scaling — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-07-memory-sparse-attention-for-100m-token-s-377cff.mp331. AI Post Transformers: AWQ: On-Device LLM Compression and Acceleration — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/awq-on-device-llm-compression-and-acceleration/0 min
- A Practical Review of Mechanistic InterpretabilityThis episode explores a review of mechanistic interpretability for transformer language models, focusing on how researchers study internal features, circuits, and claims of universality across models. It explains the core toolkit behind the field, including linear probes, hidden-state analysis, intervention methods, vocabulary projection, and sparse autoencoders, while grounding those ideas in transformer anatomy such as attention heads, MLPs, and the residual stream. The discussion highlights a central tension in the literature: finding information encoded in activations is not the same as proving that information causally drives model behavior, and the episode repeatedly questions where interpretability claims may be overstated. Listeners would find it interesting because it offers a concrete map of a fast-growing area of AI research while also giving a careful critique of the field’s assumptions, evidence, and real-world usefulness.Sources:1. A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models — Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, Ziyu Yao, 2024http://arxiv.org/abs/2407.026462. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning — Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Chris Olah, and collaborators, 2023https://scholar.google.com/scholar?q=Towards+Monosemanticity%3A+Decomposing+Language+Models+With+Dictionary+Learning3. Sparse Autoencoders Find Highly Interpretable Features in Language Models — Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, Lee Sharkey, 2023https://scholar.google.com/scholar?q=Sparse+Autoencoders+Find+Highly+Interpretable+Features+in+Language+Models4. Scaling and Evaluating Sparse Autoencoders — Leo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu, 2024https://scholar.google.com/scholar?q=Scaling+and+Evaluating+Sparse+Autoencoders5. Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders — Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat, Arthur Conmy, Vikrant Varma, Janos Kramar, Neel Nanda, 2024https://scholar.google.com/scholar?q=Jumping+Ahead%3A+Improving+Reconstruction+Fidelity+with+JumpReLU+Sparse+Autoencoders6. A Mathematical Framework for Transformer Circuits — Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, Chris Olah, 2021https://scholar.google.com/scholar?q=A+Mathematical+Framework+for+Transformer+Circuits7. Towards Best Practices of Activation Patching in Language Models: Metrics and Methods — Fred Zhang, Neel Nanda, 2024https://scholar.google.com/scholar?q=Towards+Best+Practices+of+Activation+Patching+in+Language+Models%3A+Metrics+and+Methods8. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet — Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L. Turner, Callum McDougall, Monte MacDiarmid, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, Tom Henighan, 2024https://scholar.google.com/scholar?q=Scaling+Monosemanticity%3A+Extracting+Interpretable+Features+from+Claude+3+Sonnet9. Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models — Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller, 2025https://scholar.google.com/scholar?q=Sparse+Feature+Circuits%3A+Discovering+and+Editing+Interpretable+Causal+Graphs+in+Language+Models10. On the Theoretical Understanding of Identifiable Sparse Autoencoders and Beyond — Jingyi Cui, Qi Zhang, Yifei Wang, Yisen Wang, 2025https://scholar.google.com/scholar?q=On+the+Theoretical+Understanding+of+Identifiable+Sparse+Autoencoders+and+Beyond11. Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words — Gouki Minegishi, Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo, 2025https://scholar.google.com/scholar?q=Rethinking+Evaluation+of+Sparse+Autoencoders+through+the+Representation+of+Polysemous+Words12. Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers — Andrew Nam, Henry Conklin, Yukang Yang, Thomas Griffiths, Jonathan Cohen, Sarah-Jane Leslie, 2025https://scholar.google.com/scholar?q=Causal+Head+Gating%3A+A+Framework+for+Interpreting+Roles+of+Attention+Heads+in+Transformers13. Quantifying LLM Attention-Head Stability: Implications for Circuit Universality — Karan Bali, Jack Stanley, Praneet Suresh, Danilo Bzdok, 2026https://scholar.google.com/scholar?q=Quantifying+LLM+Attention-Head+Stability%3A+Implications+for+Circuit+Universality14. AI Post Transformers: Mechanistic interpretability: Decoding the AI's Inner Logic: Circuits and Sparse Features — Hal Turing & Dr. Ada Shannon, 2025https://podcast.do-not-panic.com/episodes/mechanistic-interpretability-decoding-the-ais-inner-logic-circuits-and-sparse-fe/15. AI Post Transformers: Advancing Mechanistic Interpretability with Sparse Autoencoders — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/advancing-mechanistic-interpretability-with-sparse-autoencoders/16. AI Post Transformers: Neural Chameleons and Evading Activation Monitors — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-14-neural-chameleons-and-evading-activation-bc470e.mp317. AI Post Transformers: Linear Classifier Probes for Intermediate Layers — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-16-linear-classifier-probes-for-intermediat-927ae3.mp318. AI Post Transformers: Internal Safety Collapse in Frontier LLMs — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-04-internal-safety-collapse-in-frontier-llm-8be72f.mp313 min
- Recursive Multi-Agent Systems in Latent SpaceThis episode explores a 2026 paper on recursive multi-agent systems that asks whether AI collaboration can scale better by replacing text-based agent communication with shared latent-state updates. It explains the difference between agent topology, assigned roles, and communication channels, and argues that natural language may be a costly bottleneck compared with the richer internal representations models use during reasoning. The discussion connects this idea to earlier multi-agent chat frameworks, classic transformer architectures, and recent test-time compute work on latent recurrent refinement. Listeners would find it interesting because it frames a sharp debate between today’s practical, inspectable text-first agent workflows and a more trainable, neural-network-like approach that could change how complex AI teams are built.Sources:1. Recursive Multi-Agent Systems — Xiyuan Yang, Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus J. Buehler, Jingrui He, James Zou, 2026http://arxiv.org/abs/2604.259172. CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society — Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem, 2023https://scholar.google.com/scholar?q=CAMEL%3A+Communicative+Agents+for+%22Mind%22+Exploration+of+Large+Scale+Language+Model+Society3. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation — Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, Ahmed Hassan Awadallah, Ryen W. White, Doug Burger, Chi Wang, 2023https://scholar.google.com/scholar?q=AutoGen%3A+Enabling+Next-Gen+LLM+Applications+via+Multi-Agent+Conversation4. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework — Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber, 2023https://scholar.google.com/scholar?q=MetaGPT%3A+Meta+Programming+for+A+Multi-Agent+Collaborative+Framework5. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach — Jonas Geiping, Sean McLeish, Neel Jain, John Kirchenbauer, Siddharth Singh, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Tom Goldstein, 2025https://scholar.google.com/scholar?q=Scaling+up+Test-Time+Compute+with+Latent+Reasoning%3A+A+Recurrent+Depth+Approach6. Learning Multiagent Communication with Backpropagation — Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus, 2016https://scholar.google.com/scholar?q=Learning+Multiagent+Communication+with+Backpropagation7. Learning to Communicate with Deep Multi-Agent Reinforcement Learning — Jakob Foerster, Ioannis Alexandros Assael, Nando de Freitas, Shimon Whiteson, 2016https://scholar.google.com/scholar?q=Learning+to+Communicate+with+Deep+Multi-Agent+Reinforcement+Learning8. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments — Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch, 2017https://scholar.google.com/scholar?q=Multi-Agent+Actor-Critic+for+Mixed+Cooperative-Competitive+Environments9. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning — Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson, 2018https://scholar.google.com/scholar?q=QMIX%3A+Monotonic+Value+Function+Factorisation+for+Deep+Multi-Agent+Reinforcement+Learning10. TextGrad: Automatic "Differentiation" via Text — Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, James Zou, 2024https://scholar.google.com/scholar?q=TextGrad%3A+Automatic+%22Differentiation%22+via+Text11. Mixture-of-Agents Enhances Large Language Model Capabilities — Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, James Zou, 2024https://scholar.google.com/scholar?q=Mixture-of-Agents+Enhances+Large+Language+Model+Capabilities12. ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems — Andrew Zhu, Liam Dugan, Chris Callison-Burch, 2024https://scholar.google.com/scholar?q=ReDel%3A+A+Toolkit+for+LLM-Powered+Recursive+Multi-Agent+Systems13. Why Do Multi-Agent LLM Systems Fail? — Mert Cemri, Melissa Z. Pan, Shuyi Yang, Lakshya A. Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica, 2025https://scholar.google.com/scholar?q=Why+Do+Multi-Agent+LLM+Systems+Fail%3F14. Scaling Latent Reasoning via Looped Language Models — Rui-Jie Zhu, Zixuan Wang, Kai Hua, Tianyu Zhang, Ziniu Li, Haoran Que, Boyi Wei, Zixin Wen, Fan Yin, He Xing, Lu Li, Jiajun Shi, Kaijing Ma, Shanda Li, Taylor Kergan, Andrew Smith, Xingwei Qu, Mude Hui, Bohong Wu, Qiyang Min, Hongzhi Huang, Xun Zhou, Wei Ye, Jiaheng Liu, Jian Yang, Yunfeng Shi, Chenghua Lin, Enduo Zhao, Tianle Cai, Ge Zhang, Wenhao Huang, Yoshua Bengio, Jason Eshraghian, 2025https://scholar.google.com/scholar?q=Scaling+Latent+Reasoning+via+Looped+Language+Models15. Enabling Agents to Communicate Entirely in Latent Space — Zhuoyun Du et al., 2025https://scholar.google.com/scholar?q=Enabling+Agents+to+Communicate+Entirely+in+Latent+Space16. Latent Collaboration in Multi-Agent Systems — Jiaru Zou, Xiyuan Yang et al., 2025https://scholar.google.com/scholar?q=Latent+Collaboration+in+Multi-Agent+Systems17. Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification — Anqi Zhang et al., 2025https://scholar.google.com/scholar?q=Reasoning+Models+Know+When+They%27re+Right%3A+Probing+Hidden+States+for+Self-Verification18. Do Language Models Use Their Depth Efficiently? — Robert Csordas, Christopher D. Manning, Christopher Potts, 2025https://scholar.google.com/scholar?q=Do+Language+Models+Use+Their+Depth+Efficiently%3F19. Exploring Depth Generalization in Large Language Models for Solving Recursive Logic Tasks — Zhiyuan He, 2025https://scholar.google.com/scholar?q=Exploring+Depth+Generalization+in+Large+Language+Models+for+Solving+Recursive+Logic+Tasks20. Minimizing Response Latency in LLM-Based Agent Systems: A Comprehensive Survey — Gyeongmuk Park, Seonghyeon Lee, Yeonsu Park, 2026https://scholar.google.com/scholar?q=Minimizing+Response+Latency+in+LLM-Based+Agent+Systems%3A+A+Comprehensive+Survey21. AI Post Transformers: TUMIX Multi-Agent Test-Time Scaling with Tools — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-22-tumix-multi-agent-test-time-scaling-with-40671c.mp322. AI Post Transformers: Neural Computers as Learned Latent Runtimes — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-11-neural-computers-as-learned-latent-runti-9fa282.mp323. AI Post Transformers: VL-JEPA for Vision-Language Semantic Prediction — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-12-vl-jepa-for-vision-language-semantic-pre-69c9f4.mp324. AI Post Transformers: Neural Chameleons and Evading Activation Monitors — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-14-neural-chameleons-and-evading-activation-bc470e.mp325. AI Post Transformers: Efficient KV Cache Sharing for Multi-LoRA Agents — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-22-efficient-kv-cache-sharing-for-multi-lor-afda05.mp326. AI Post Transformers: TokenDance for Multi-Agent KV Cache Sharing — Hal Turing & Dr. Ada Shannon, 2026https://podcast.do-not-panic.com/episodes/2026-04-22-tokendance-for-multi-agent-kv-cache-shar-aa9b99.mp317 min
About AI Post Transformers
From the publisher's feed
AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis,…
proper citations, and nerdy humor.