• MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
• Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
• Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology

Support the show

• RWKV: Reinventing RNNs for the Transformer Era
• DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales
• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
• Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
• The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

Support the show

• Predicting masked tokens in stochastic locations improves masked image modeling
• Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
• Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
• WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings

Support the show

• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• Discovering Adaptable Symbolic Algorithms from Scratch
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• Guiding Image Captioning Models Toward More Specific Captions
• LLM-Rec: Personalized Recommendation via Prompting Large Language Models
• The Hydra Effect: Emergent Self-repair in Language Model Computations

Support the show

• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
• Med-Flamingo: a Multimodal Medical Few-shot Learner
• PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization

Support the show

• Scaling TransNormer to 175 Billion Parameters
• PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
• Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
• To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
• How to Scale Your EMA

Support the show

• Tracking Anything in High Quality
• Towards Generalist Biomedical AI
• Foundation Models and Fair Use
• Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation

Support the show

• The case for 4-bit precision: k-bit Inference Scaling Laws
• No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
• PUMA: Secure Inference of LLaMA-7B in Five Minutes
• Optimized Network Architectures for Large Language Model Training with Billions of Parameters
• A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Support the show

• How will Language Modelers like ChatGPT Affect Occupations and Industries?
• CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
• STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
• StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
• Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

Support the show

• Meta-Transformer: A Unified Framework for Multimodal Learning
• Divide & Bind Your Attention for Improved Generative Semantic Nursing
• Brain2Music: Reconstructing Music from Human Brain Activity
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
• Instruction-following Evaluation through Verbalizer Manipulation

Support the show