Xiangxin Zhou

zhouxiangxin's activity

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

upvoted a paper 1 day ago

Best Practice Critic Optimization

Paper • 2608.23566 • Published 2 days ago • 13

upvoted 5 papers about 1 month ago

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

Paper • 2508.04482 • Published Aug 6, 2025 • 10

Exploring the Design Space of Reward Backpropagation for Flow Matching

Paper • 2606.11075 • Published Jun 9 • 12

TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL

Paper • 2606.28016 • Published Jun 26 • 1

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

Paper • 2607.15273 • Published Jul 16 • 17

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published Jul 21 • 36

upvoted 4 papers 3 months ago

Reinforcing Few-step Generators via Reward-Tilted Distribution Matching

Paper • 2605.26108 • Published May 25 • 7

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

Paper • 2606.10968 • Published Jun 9 • 42

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

Paper • 2606.11025 • Published Jun 9 • 41

Rethinking the Divergence Regularization in LLM RL

Paper • 2606.09821 • Published Jun 8 • 34

upvoted a collection 3 months ago

RTDMD

Collection

Reinforcing Few-step Generators via Reward-Tilted Distribution Matching • 5 items • Updated Jun 2 • 3

upvoted a paper 7 months ago

Rethinking the Trust Region in LLM Reinforcement Learning

Paper • 2602.04879 • Published Feb 4 • 38

upvoted 2 papers 10 months ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published Nov 5, 2025 • 132

Defeating the Training-Inference Mismatch via FP16

Paper • 2510.26788 • Published Oct 30, 2025 • 32

upvoted 4 papers 11 months ago

GEM: A Gym for Agentic LLMs

Paper • 2510.01051 • Published Oct 1, 2025 • 92

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29, 2025 • 147

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

Paper • 2509.23188 • Published Sep 27, 2025 • 3

Variational Reasoning for Language Models

Paper • 2509.22637 • Published Sep 26, 2025 • 70

upvoted a collection 11 months ago

Variational Reasoning

Collection

19 items • Updated Sep 28, 2025 • 1

upvoted a paper about 1 year ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 119