Chen Wei

Play to Generalize: Learning to Reason Through Game Play

TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

COPER: Agentic Context Significantly Improves and Stabilizes LLM in Multi-Player Game

Fake it till You Make it: Reward Modeling as Discriminative Prediction

Perception Encoder: The best visual embeddings are not at the output of the network

Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning