Berkeley AI Research

Gradient-based Planning for World Models at Longer Horizons

grasp-results-table table { font-size: 0. 875rem; line-height: 1.

Berkeley AI Research

Jul 26

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

abbel-fig { display: block; text-align: center; margin: 2. 4em 0; line-height: 1.

llms agents nlp reinforcement-learning fine-tuning efficiency benchmarks

Berkeley AI Research

May 8

Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling

apr-fig { text-align: center; margin: 1. 35em 0; line-height: 1.

llms rag agents nlp reinforcement-learning fine-tuning efficiency benchmarks

Berkeley AI Research

Nov 1, 2025

RL without TD learning

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks.

llms reinforcement-learning robotics benchmarks

Google AI Blog

Feb 14, 2024

Learning the importance of training data under concept drift

Posted by Nishant Jain, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research The constantly changing nature of the world around us poses a significant challenge for the development of AI models. Often, models are trained on longitudinal data with the hope that the training data used will accurately represent inputs the model may receive in the future.

By Google AI

benchmarks

arXiv Machine Learning

Sep 25

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

The paper demonstrates that planners using frozen visual world models can achieve better control by changing the target used for action scoring. Instead of scoring actions solely by distance to the final goal image, the authors propose Anchored Planning, which retrieves a recorded trajectory segment that matches the current and goal observations and then scores actions toward an intermediate observation shortly after the segment’s start. Experiments on Cube, PushT, Reacher, and TwoRoom show that this intermediate-target approach outperforms the released LeWM planner on all long‑range tasks, while simple final‑goal search fails to achieve the same gains.

By Xvyuan Liu, Jianjie Fang, Chen Gao, Yong Li

Berkeley AI Research

Jul 1

2026 BAIR Graduate Showcase

Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.

llms rag agents diffusion computer-vision nlp reinforcement-learning robotics multimodal benchmarks safety

Simon Willison

Aug 29

Introducing Hy4 Preview

Simon Willison introduces Hy4 Preview, a new large language model from Tencent featuring 770 B total parameters, 49 B active parameters, a 1 M token context window, and 1.56 TB of storage on Hugging Face. The release marks a significant increase over Hy3, which had 295 B total parameters, 21 B active parameters, a 256 k token context window, and 598 GB of storage. Willison also shares the model’s chat template, highlighting two reasoning effort levels—‘high’ (default) and ‘no_think’—and demonstrates a sample prompt that showcases the model’s reasoning trace. whyItMatters":"The article provides concrete details on Hy4’s scale and configuration, illustrating Tencent’s advancement in large‑language‑model capabilities and offering practical insights into its usage through the chat template and reasoning settings."

llms

arXiv Machine Learning

Jun 29

Qwen-Image-2.0-RL Technical Report

arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.

By Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan Cao, Jiahao Li, Jie Zhang, Liang Peng, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yi Wang, Yu Wu, Yujia Wu, Zekai Zhang, Zhendong Wang, Xiao Xu, Kun Yan, Chenfei Wu

llms diffusion reinforcement-learning fine-tuning efficiency multimodal safety

arXiv Computer Vision

6d ago

WorldLine: Action-Driven Visual Simulation for Robotic Manipulation

arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a sca...

By Shenghe Zheng, Wenbo Li, Jiyao Zhang, Bin Xia, Haoyang Huang, Nan Duan, Jiaya Jia

diffusion robotics efficiency

arXiv AI

1d ago

World Action Modeling with Progressive Visual Planning

arXiv:2610.02508v1 Announce Type: new Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an in...

By Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar

diffusion robotics benchmarks

Hugging Face Trending Papers

Jun 11

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation.

llms agents diffusion reinforcement-learning robotics fine-tuning multimodal benchmarks

Google AI Blog

Feb 23, 2024

VideoPrism: A foundational visual encoder for video understanding

Posted by Long Zhao, Senior Research Scientist, and Ting Liu, Senior Staff Software Engineer, Google Research An astounding number of videos are available on the Web, covering a variety of content from everyday moments people share to historical moments to scientific observations, each of which contains a unique record of the world. The right tools could help researchers analyze these videos, transforming how we understand the world around us.

By Google AI

llms rag computer-vision nlp multimodal benchmarks

Related stories