Qi Dai

ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Subject-driven Video Generation Emerges from Experience Replays

InfoAgent: Advancing Autonomous Information‑Seeking Agents

Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation

PACR: Progressively Ascending Confidence Reward for LLM Reasoning

ReasonGen-R1: Cot for Autoregressive Image Generation Models Through SFT and RL

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

TinyMem: Condensing Multimodal Memory for Long-form Video Action Detection

LLM2CLIP: Extending the Capability Boundaries of CLIP through Large Language Models

VideoDiT: Bridging Image Diffusion Transformers for Streamlined Video Generation