Yin Zhang

Full Professor@Zhejiang University·中国·OpenReview

研究方向

pre-trained language models · code representation learning · question answering · dialogue system · reinforcement learning · multimedia content analysis

4.5

VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models

ICLR 2026Rejected

通讯

3.0

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

NeurIPS 2025Poster

通讯

3.8

Strategy-centric Synthesis: Connecting Billions of Image-Text Pairs to High-Quality Visual Instruction Data

合作者 (20)

Yin Zhang

VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models

Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning

Expert-Integrated Active Learning for Optimizing LLM Agents

Adaptive Fast-and-Slow Visual Program Reasoning for Long-Form VideoQA

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

Strategy-centric Synthesis: Connecting Billions of Image-Text Pairs to High-Quality Visual Instruction Data