shijie xia

seven-cat's activity

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

upvoted a paper 3 days ago

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Paper • 2510.18927 • Published 4 days ago • 77

upvoted 2 papers about 1 month ago

LIMI: Less is More for Agency

Paper • 2509.17567 • Published Sep 22 • 100

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

Paper • 2509.09286 • Published Sep 11 • 11

upvoted 2 papers 4 months ago

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25 • 47

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

Paper • 2506.09050 • Published Jun 10 • 6

upvoted 2 papers 5 months ago

Thinking with Generated Images

Paper • 2505.22525 • Published May 28 • 15

Efficient Agent Training for Computer Use

Paper • 2505.13909 • Published May 20 • 44

upvoted a paper 6 months ago

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Paper • 2504.13828 • Published Apr 18 • 18

upvoted 2 papers 7 months ago

MegaMath: Pushing the Limits of Open Math Corpora

Paper • 2504.02807 • Published Apr 3 • 34

Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Paper • 2504.02587 • Published Apr 3 • 32

upvoted a paper 10 months ago

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Paper • 2501.03124 • Published Jan 6 • 14

upvoted a collection over 1 year ago

Long Context

Collection

53 items • Updated Jun 5 • 8