Chenyu Wang

chenyuwang-sjtu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 9 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 14 days ago • 111

upvoted a paper 11 days ago

Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations

Paper • 2609.30867 • Published 20 days ago • 6

upvoted a paper 16 days ago

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published 23 days ago • 104

upvoted 2 papers 18 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 480

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 24 days ago • 77

upvoted a paper 20 days ago

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

Paper • 2609.23377 • Published 25 days ago • 50

upvoted a paper 21 days ago

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

Paper • 2609.09206 • Published Sep 5 • 11

upvoted 2 papers 23 days ago

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 28 days ago • 94

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 28 days ago • 140

upvoted 2 papers 25 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published about 1 month ago • 148

StepAudio 3 Music Technical Report

Paper • 2609.16034 • Published Sep 11 • 111

upvoted a paper 26 days ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published Sep 14 • 217

upvoted a paper 27 days ago

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Paper • 2609.15973 • Published Sep 14 • 33

upvoted a paper 28 days ago

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

Paper • 2609.10895 • Published Sep 9 • 54

upvoted 5 papers about 1 month ago

DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents

Paper • 2609.06703 • Published Sep 6 • 13

Unifying Conformal Language Tasks with In-Context Ensembles

Paper • 2609.03005 • Published Sep 2 • 10

Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers

Paper • 2608.18972 • Published Aug 19 • 13

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published Sep 1 • 122

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published Sep 8 • 55