Research Papers
Curated research on AI, language models, and systems that power reliable AI applications.
Modality-Autoregressive World-Action Models
World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images. Other visual modalities such ...
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet ...
AI for Games in the Foundation Model Era
Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems m...
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researche...
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the pe...
Disentangling Representation Evolution in Transformers through Directional Decomposition
Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this...
Stay updated on the latest research
Get research highlights and insights delivered to your inbox.