Xin Li

lixin67's activity

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

upvoted a paper about 1 hour ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published 4 days ago • 242

liked a dataset 4 days ago

open-thoughts/OpenThoughts-Agent-v1-SFT

Viewer • Updated Jan 27 • 15.2k • 2.34k • 104

upvoted a collection 4 days 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 4 days ago

openbmb/UltraData-SFT-Agent-2609

Viewer • Updated 8 days ago • 240k • 8.17k • 142

upvoted 5 papers 4 days 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 14 days ago • 59

Omni Interaction Agent Technical Report

Paper • 2609.08977 • Published 6 days ago • 133

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

Paper • 2609.07108 • Published 7 days ago • 34

Miles v0.1: Production-Level Post-Training

Paper • 2609.08368 • Published 6 days ago • 56

upvoted 2 papers 7 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 14 days ago • 231

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

Paper • 2609.04172 • Published 11 days ago • 94

upvoted 2 papers 19 days ago

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

Paper • 2608.13120 • Published Aug 13 • 32

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Paper • 2608.23035 • Published 21 days ago • 41

upvoted a paper 20 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published Jul 8 • 150

liked a model 28 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated about 1 month ago • 7.77M • • 15k

upvoted 2 papers about 1 month ago

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

Paper • 2608.04530 • Published Aug 5 • 14

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published Jul 8 • 33

upvoted a paper about 2 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 519

upvoted a collection about 2 months ago

Kimi K3

Collection

Open Frontier Intelligence • 2 items • Updated Jul 29 • 116

upvoted a paper about 2 months ago

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Paper • 2607.25308 • Published Jul 28 • 42