Ge Zhang

zhangysk's activity

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

upvoted 2 papers 22 days ago

First Return, Entropy-Eliciting Explore

Paper • 2507.07017 • Published 22 days ago • 23

A Systematic Analysis of Hybrid Linear Attention

Paper • 2507.06457 • Published 23 days ago • 22

upvoted 3 papers 23 days ago

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

Paper • 2507.06229 • Published 23 days ago • 69

A Survey on Latent Reasoning

Paper • 2507.06203 • Published 23 days ago • 85

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

Paper • 2507.06181 • Published 23 days ago • 39

upvoted a collection 24 days ago

Hybrid Linear Attention Research

Collection

All 1.3B & 340M hybrid linear-attention experiments. • 60 items • Updated 24 days ago • 8

upvoted a paper 25 days ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published 29 days ago • 57

upvoted a paper 29 days ago

Kwai Keye-VL Technical Report

Paper • 2507.01949 • Published 29 days ago • 126

upvoted 3 papers about 1 month ago

OAgents: An Empirical Study of Building Effective Agents

Paper • 2506.15741 • Published Jun 17 • 36

Scaling Test-time Compute for LLM Agents

Paper • 2506.12928 • Published Jun 15 • 61

TaskCraft: Automated Generation of Agentic Tasks

Paper • 2506.10055 • Published Jun 11 • 32

upvoted 3 papers 2 months ago

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

Paper • 2505.16175 • Published May 22 • 42

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

Paper • 2505.15966 • Published May 21 • 53

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published May 20 • 133

upvoted a paper 3 months ago

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

Paper • 2505.07293 • Published May 12 • 27

upvoted an article 3 months ago

view article

Article

Reasoning Datasets Competition

By and 6 others •

Apr 9

• 37

upvoted 4 papers 3 months ago

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Paper • 2505.02735 • Published May 5 • 32

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