| | | | From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon | Berkeley AI Research |
| | | | Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction | Berkeley AI Research |
| | | | Intelligence is Free, Now What? Data Systems for, of, and by Agents | Berkeley AI Research |
| | | | 2026 BAIR Graduate Showcase | Berkeley AI Research |
| | | | Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling | Berkeley AI Research |
| | | | Gradient-based Planning for World Models at Longer Horizons | Berkeley AI Research |
| | | | Identifying Interactions at Scale for LLMs | Berkeley AI Research |
| | | | Information-Driven Design of Imaging Systems | Berkeley AI Research |
| | | | RL without TD learning | Berkeley AI Research |
| | | | What exactly does word2vec learn? | Berkeley AI Research |
| | | | Whole-Body Conditioned Egocentric Video Prediction | Berkeley AI Research |
| | | | Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign) | Berkeley AI Research |
| | | | Repurposing Protein Folding Models for Generation with Latent Diffusion | Berkeley AI Research |
| | | | Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment | Berkeley AI Research |
| | | | Virtual Personas for Language Models via an Anthology of Backstories | Berkeley AI Research |
| | | | Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination | Berkeley AI Research |
| | | | How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark | Berkeley AI Research |
| | | | Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark! | Berkeley AI Research |
| | | | TinyAgent: Function Calling at the Edge | Berkeley AI Research |
| | | | Modeling Extremely Large Images with xT | Berkeley AI Research |
| | | | 2024 BAIR Graduate Directory | Berkeley AI Research |
| | | | The Shift from Models to Compound AI Systems | Berkeley AI Research |
| | | | Asymmetric Certified Robustness via Feature-Convex Neural Networks | Berkeley AI Research |
| | | | Ghostbuster: Detecting Text Ghostwritten by Large Language Models | Berkeley AI Research |
| | | | Goal Representations for Instruction Following | Berkeley AI Research |
| | | | Rethinking the Role of PPO in RLHF | Berkeley AI Research |
| | | | Training Diffusion Models with Reinforcement Learning | Berkeley AI Research |
| | | | On the Stepwise Nature of Self-Supervised Learning | Berkeley AI Research |
| | | | Generating 3D Molecular Conformers via Equivariant Coarse-Graining and Aggregated Attention | Berkeley AI Research |
| | | | GPT-4 + Stable-Diffusion = ?: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models | Berkeley AI Research |
| | | | Interactive Fleet Learning | Berkeley AI Research |
| | | | Koala: A Dialogue Model for Academic Research | Berkeley AI Research |
| | | | Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation | Berkeley AI Research |
| | | | Keeping Learning-Based Control Safe by Regulating Distributional Shift | Berkeley AI Research |
| | | | Reverse engineering the NTK: towards first-principles architecture design | Berkeley AI Research |
| | | | Why do Policy Gradient Methods work so well in Cooperative MARL? Evidence from Policy Representation | Berkeley AI Research |
| | | | FIGS: Attaining XGBoost-level performance with the interpretability and speed of CART | Berkeley AI Research |
| | | | The Berkeley Crossword Solver | Berkeley AI Research |
| | | | Rethinking Human-in-the-Loop for Artificial Augmented Intelligence | Berkeley AI Research |
| | | | Designing Societally Beneficial Reinforcement Learning Systems | Berkeley AI Research |
| | | | Should I Use Offline RL or Imitation Learning? | Berkeley AI Research |
| | | | Offline RL Made Easier: No TD Learning, Advantage Reweighting, or Transformers | Berkeley AI Research |
| | | | Accelerating Ukraine Intelligence Analysis with Computer Vision on Synthetic Aperture Radar Imagery | Berkeley AI Research |
| | | | Unsupervised Skill Discovery with Contrastive Intrinsic Control | Berkeley AI Research |
| | | | imodels: leveraging the unreasonable effectiveness of rules | Berkeley AI Research |
| | | | The Unsupervised Reinforcement Learning Benchmark | Berkeley AI Research |
| | | | Which Mutual Information Representation Learning Objectives are Sufficient for Control? | Berkeley AI Research |
| | | | Sequence Modeling Solutions for Reinforcement Learning Problems | Berkeley AI Research |
| | | | Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets | Berkeley AI Research |
| | | | Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability | Berkeley AI Research |
| | | | RECON: Learning to Explore the Real World with a Ground Robot | Berkeley AI Research |
| | | | Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability | Berkeley AI Research |
| | | | Designs from Data: Offline Black-Box Optimization via Conservative Training | Berkeley AI Research |
| | | | A First-Principles Theory of Neural Network Generalization | Berkeley AI Research |
| | | | Making RL Tractable by Learning More Informative Reward Functions: Example-Based Control, Meta-Learning, and Normalized Maximum Likelihood | Berkeley AI Research |