Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust…
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision…
Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer…
Hand-Object Interaction (HOI) synthesis is a cornerstone for animation production and embodied AI. Despite the strong priors of video foundation models, multi-view consistent HOI synthesis remains…
Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state --…
In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image modalities within a…
Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausibility only…
Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal…
This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static…
We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training…