Research Papers

Curated research on AI, language models, and systems that power reliable AI applications.

Page 1 of 2

Modality-Autoregressive World-Action Models

Adam Hung, Bardienus P. Duisterhof, Deva Ramanan& 2 more

World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images. Other visual modalities such ...

Sep 14, 2026Read paper

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

Chuhao Chen, Peter Wonka, Chaoyang Wang& 2 more

Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet ...

Sep 14, 2026Read paper

AI for Games in the Foundation Model Era

Meng Luo, Yanlin Li, Hao Li& 2 more

Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems m...

Sep 14, 2026Read paper

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

Shuhan Xue, Jianyuan Zhong, Ziyuan Nan& 2 more

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researche...

Sep 14, 2026Read paper

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Zixuan Wang, Yufan Zhou, Jinzhou Tang& 2 more

As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the pe...

Sep 13, 2026Read paper

Disentangling Representation Evolution in Transformers through Directional Decomposition

Shwai He, Haichao Zhang, Shen Yan& 2 more

Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this...

Sep 13, 2026Read paper

Stay updated on the latest research

Get research highlights and insights delivered to your inbox.