5 papers
DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation
Ao Yu, Weibo Gao, Heng Zhou +6
On-policy distillation (OPD) trains a student on its own responses with token-level feedback from a stronger teacher, yet the teacher can fail on questions the student already answ…
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Heng Zhou, Zelin Tan, Zhemeng Zhang +15
When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-ti…
Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
Heng Zhou, Li Kang, Yiran Qin +12
Understanding the world from distributed, partial viewpoints is a fundamental challenge for embodied multi-agent systems. Each agent perceives the environment through an ego-centri…
BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off
Shuang Liu, Ao Yu, Linkang Cheng +5
Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods…
Reading Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models
Heng Zhou, Ao Yu, Li Kang +5
Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We…