The Berkeley Artificial Intelligence Research Blog bair.berkeley.edu

RL without TD learning

bair.berkeley.edu·15w

What exactly does word2vec learn?

bair.berkeley.edu·23w

Whole-Body Conditioned Egocentric Video Prediction

bair.berkeley.edu·32w

Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)

bair.berkeley.edu·44w

Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)

bair.berkeley.edu·44w·

Discuss: Hacker News

Repurposing Protein Folding Models for Generation with Latent Diffusion

bair.berkeley.edu·44w

Repurposing Protein Folding Models for Generation with Latent Diffusion

bair.berkeley.edu·44w

Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment

bair.berkeley.edu·46w

Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment

bair.berkeley.edu·46w·

Discuss: Hacker News

Virtual Personas for Language Models via an Anthology of Backstories

bair.berkeley.edu·65w

Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination

bair.berkeley.edu·73w

Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination

bair.berkeley.edu·73w

How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark

bair.berkeley.edu·76w

How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark

bair.berkeley.edu·76w

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

bair.berkeley.edu·82w

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

bair.berkeley.edu·82w

TinyAgent: Function Calling at the Edge

bair.berkeley.edu·89w

TinyAgent: Function Calling at the Edge

bair.berkeley.edu·89w

Modeling Extremely Large Images with xT

bair.berkeley.edu·99w

Modeling Extremely Large Images with xT

bair.berkeley.edu·99w

Loading...Loading more...