Ge Zhang

zhangysk's activity

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

authored a paper 14 days ago

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Paper • 2509.13160 • Published 17 days ago • 29

authored a paper 24 days ago

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published 26 days ago • 145

authored 2 papers 28 days ago

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Paper • 2509.02544 • Published about 1 month ago • 121

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

Paper • 2509.04292 • Published 29 days ago • 57

authored 5 papers about 1 month ago

M3TQA: Massively Multilingual Multitask Table Question Answering

Paper • 2508.16265 • Published Aug 22

TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Paper • 2508.17445 • Published Aug 24 • 80

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

Paper • 2508.13186 • Published Aug 14 • 18

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

Paper • 2508.11987 • Published Aug 16 • 69

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

Paper • 2508.13167 • Published Aug 6 • 127

authored 5 papers about 2 months ago

Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

Paper • 2507.23726 • Published Jul 31 • 112

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Paper • 2508.02193 • Published Aug 4 • 129

Efficient Agents: Building Effective Agents While Reducing Cost

Paper • 2508.02694 • Published Jul 24 • 85

VeriGUI: Verifiable Long-Chain GUI Dataset

Paper • 2508.04026 • Published Aug 6 • 157

WideSearch: Benchmarking Agentic Broad Info-Seeking

Paper • 2508.07999 • Published Aug 11 • 109

authored 5 papers 2 months ago

Multilingual Multimodal Software Developer for Code Generation

Paper • 2507.08719 • Published Jul 11

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Paper • 2505.14552 • Published May 20

First Return, Entropy-Eliciting Explore

Paper • 2507.07017 • Published Jul 9 • 23

A Systematic Analysis of Hybrid Linear Attention

Paper • 2507.06457 • Published Jul 8 • 23

A Survey on Latent Reasoning

Paper • 2507.06203 • Published Jul 8 • 91

authored a paper 3 months ago

SciDA: Scientific Dynamic Assessor of LLMs

Paper • 2506.12909 • Published Jun 15