liusx

non-profit

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

liusx authored a paper 4 days ago

GRACE: Generative Representation Learning via Contrastive Policy Optimization

liusx authored a paper 4 days ago

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window

liusx authored a paper 4 days ago

Soft Adaptive Policy Optimization

View all activity

liusx

authored 4 papers 4 days ago

GRACE: Generative Representation Learning via Contrastive Policy Optimization

Paper • 2510.04506 • Published Oct 6 • 10

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window

Paper • 2510.08276 • Published Oct 9 • 9

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published 12 days ago • 33

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 11 days ago • 107

liusx

authored 6 papers 4 months ago

TeleChat Technical Report

Paper • 2401.03804 • Published Jan 8, 2024 • 8

From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models

Paper • 2503.06260 • Published Mar 8

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 317

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 187

Stable Reinforcement Learning for Efficient Reasoning

Paper • 2505.18086 • Published May 23

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24 • 313