Ge Zhang

zhangysk's activity

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

upvoted a paper 10 days ago

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Paper • 2512.12730 • Published 12 days ago • 43

upvoted 2 papers 24 days ago

How Far Are We from Genuinely Useful Deep Research Agents?

Paper • 2512.01948 • Published 24 days ago • 53

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Paper • 2511.18538 • Published Nov 23 • 274

upvoted 3 papers about 1 month ago

Virtual Width Networks

Paper • 2511.11238 • Published Nov 14 • 36

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Paper • 2511.08892 • Published Nov 12 • 201

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

Paper • 2511.07250 • Published Nov 10 • 17

upvoted a collection about 2 months ago

Ouro

Collection

a family of pre-trained Looped Language Models. • 4 items • Updated Oct 29 • 21

upvoted a paper about 2 months ago

Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29 • 221

upvoted 4 papers 2 months ago

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

Paper • 2510.10201 • Published Oct 11 • 35

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

Paper • 2510.11652 • Published Oct 13 • 28

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 165

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

Paper • 2510.10689 • Published Oct 12 • 46

upvoted 5 papers 3 months ago

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

Paper • 2509.25849 • Published Sep 30 • 47

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

Paper • 2509.24002 • Published Sep 28 • 173

FlowRL: Matching Reward Distributions for LLM Reasoning

Paper • 2509.15207 • Published Sep 18 • 114

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

Paper • 2509.13160 • Published Sep 16 • 29

LLM-I: LLMs are Naturally Interleaved Multimodal Creators

Paper • 2509.13642 • Published Sep 17 • 9

upvoted 3 papers 4 months ago

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published Sep 9 • 101

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7 • 149

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

Paper • 2509.04292 • Published Sep 4 • 57