Xiao Zihan

xiaozihan2025's activity

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

upvoted 3 papers 1 day ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 378

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published May 9 • 245

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published Jun 16 • 175

upvoted a paper 18 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 20 days ago • 251

liked 3 models 19 days ago

moonshotai/Kimi-K2-Instruct

Text Generation • 1T • Updated Apr 23 • 315k • • 2.99k

deepseek-ai/DeepSeek-R1

Text Generation • 684B • Updated Mar 27, 2025 • 994k • • 14.3k

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 8.44M • • 2.39k

upvoted a paper 20 days ago

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Paper • 2609.05592 • Published 30 days ago • 25

liked a model 24 days ago

TokenRhythm/NeoHorse-1-4B

Text Generation • 4B • Updated 23 days ago • 29.1k • 2.54k

liked a dataset about 1 month ago

dtunkelang/jobs-demo

Viewer • Updated about 15 hours ago • 1 • 12.9k • 1

liked a model about 2 months ago

ERISLab/q2a_openai_whisper-medium_CohereLabs_tiny-aya-earth_ws-ta_in-250-lr0.015

4B • Updated Aug 12 • 4 • 1

liked a dataset 2 months ago

roneneldan/TinyStories

Viewer • Updated Aug 12, 2024 • 2.14M • 104k • 1.18k

upvoted 3 papers 2 months ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published Jul 30 • 18

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published Jul 30 • 159

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Paper • 2607.21655 • Published Jul 22 • 112

liked a dataset 2 months ago

jensjepsen/danish-text-to-question-v2

Viewer • Updated Jul 24 • 34.4k • 29 • 1

upvoted 2 papers 2 months ago

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published Jul 21 • 114

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published Jul 20 • 63

liked a model 3 months ago

jiangzhuo9357/qwen3-tts-0.6b-onnx-bf16

Updated Jul 17 • 10 • 1

liked a dataset 3 months ago

IntelligenceLab/Long-Horizon-Terminal-Bench

Benchmark • Updated 17 days ago • 46 • 12k • 137