• Fast Inference from Transformers via Speculative Decoding
• YaRN: Efficient Context Window Extension of Large Language Models
• VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation
• RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Support the show

• The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
• Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images
• BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
• MVDream: Multi-view Diffusion for 3D Generation
• Can Programming Languages Boost Each Other via Instruction Tuning?

Support the show

• WeatherBench 2: A benchmark for the next generation of data-driven global weather models
• RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
• LLaSM: Large Language and Speech Model

Support the show

• Reward-Respecting Subtasks for Model-Based Reinforcement Learning
• Relightify: Relightable 3D Faces from a Single Image via Diffusion Models
• MagicEdit: High-Fidelity and Temporally Coherent Video Editing

Support the show

• Break-A-Scene: Extracting Multiple Concepts from a Single Image
• The Poison of Alignment
• MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
• ORES: Open-vocabulary Responsible Visual Synthesis

Support the show

• PMET: Precise Model Editing in a Transformer
• Interpretable Graph Neural Networks for Tabular Data
• Nougat: Neural Optical Understanding for Academic Documents
• Relighting Neural Radiance Fields with Shadow and Highlight Hints

Support the show

• WavJourney: Compositional Audio Creation with Large Language Models
• Differentially Private Diffusion Models
• Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization

Support the show

• Scalable Diffusion Models with Transformers
• BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
• StableVideo: Text-driven Consistency-aware Diffusion Video Editing
• Exploiting Diffusion Prior for Real-World Image Super-Resolution

Support the show

• Extrapolating Large Language Models to Non-English by Aligning Languages
• SeamlessM4T—Massively Multilingual & Multimodal Machine Translation
• ReVersion: Diffusion-Based Relation Inversion from Images

Support the show

• Diversifying AI: Towards Creative Chess with AlphaZero
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• Dataset Quantization
• We Don't Need No Adam, All We Need Is EVE: On The Variance of Dual Learning Rate And Beyond
• SRFormer: Empowering Regression-Based Text Detection Transformer with Segmentation

Support the show