Ge Zhang

zhangysk's activity

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

upvoted a paper 3 days ago

OAgents: An Empirical Study of Building Effective Agents

Paper • 2506.15741 • Published 10 days ago • 31

upvoted a paper 10 days ago

Scaling Test-time Compute for LLM Agents

Paper • 2506.12928 • Published 12 days ago • 57

upvoted a paper 11 days ago

TaskCraft: Automated Generation of Agentic Tasks

Paper • 2506.10055 • Published 16 days ago • 31

upvoted 3 papers about 1 month ago

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design

Paper • 2505.16175 • Published May 22 • 40

Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning

Paper • 2505.15966 • Published May 21 • 51

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published May 20 • 130

upvoted a paper about 2 months ago

AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection

Paper • 2505.07293 • Published May 12 • 26

upvoted an article about 2 months ago

view article

Article

Reasoning Datasets Competition

By and 6 others •

Apr 9

• 37

upvoted a paper about 2 months ago

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Paper • 2505.02735 • Published May 5 • 31

upvoted 7 papers 2 months ago

QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining

Paper • 2504.16511 • Published Apr 23 • 20

Efficient Pretraining Length Scaling

Paper • 2504.14992 • Published Apr 21 • 20

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs

Paper • 2504.15415 • Published Apr 21 • 22

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Paper • 2504.11536 • Published Apr 15 • 60

Self-Steering Language Models

Paper • 2504.07081 • Published Apr 9 • 18

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9 • 74

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published Apr 11 • 128

upvoted 4 papers 3 months ago

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

Paper • 2504.05535 • Published Apr 7 • 44

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published Mar 30 • 135

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Paper • 2503.22230 • Published Mar 28 • 44

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models

Paper • 2503.21380 • Published Mar 27 • 37