Xin Li

lixin67's activity

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

upvoted 3 papers 1 day ago

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

Paper • 2610.11366 • Published 3 days ago • 12

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published 3 days ago • 130

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Paper • 2610.11959 • Published 3 days ago • 72

upvoted a paper 2 days ago

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published 5 days ago • 91

upvoted a paper 3 days ago

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

Paper • 2610.04109 • Published 9 days ago • 33

upvoted a paper 18 days ago

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published 23 days ago • 80

upvoted a paper 19 days ago

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 23 days ago • 138

upvoted a paper 23 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 24 days ago • 228

upvoted a paper 27 days ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published Sep 10 • 232

liked a dataset about 1 month ago

open-thoughts/OpenThoughts-Agent-v1-SFT

Viewer • Updated Jan 27 • 15.2k • 2.51k • 105

upvoted a collection about 1 month ago

OpenThinker-Agent2

Collection

OpenThinker-Agent2: agentic SFT/RL datasets and 8B/32B models (cold-start SFT, RL, and the OpenThinkerAgent-32B release). • 11 items • Updated Jun 11 • 11

liked a dataset about 1 month ago

openbmb/UltraData-SFT-Agent-2609

Viewer • Updated Sep 6 • 240k • 27.2k • 292

upvoted 7 papers about 1 month ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 27

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published Aug 31 • 63

Omni Interaction Agent Technical Report

Paper • 2609.08977 • Published Sep 8 • 94

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published Sep 7 • 36

Miles v0.1: Production-Level Post-Training

Paper • 2609.08368 • Published Sep 8 • 62

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 274

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published Sep 3 • 104

upvoted a paper about 2 months ago

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback

Paper • 2608.13120 • Published Aug 13 • 32