LIU Qianyi

liuqil's activity

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

upvoted 2 papers 3 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 4 days ago • 96

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 7 days ago • 209

upvoted 2 papers 4 days ago

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published 17 days ago • 114

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement

Paper • 2609.13406 • Published 10 days ago • 42

upvoted 2 papers 6 days ago

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper • 2609.13356 • Published 10 days ago • 256

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 7 days ago • 239

upvoted 2 papers 7 days ago

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

Paper • 2609.06107 • Published 16 days ago • 163

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Paper • 2609.12641 • Published 10 days ago • 70

liked 6 models 7 days ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated 25 days ago • 761k • • 5.51k

Qwen/Qwen3-8B

Text Generation • 8B • Updated Jul 26, 2025 • 12.9M • • 2.03k

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 9.66M • • 2.22k

mistralai/Mistral-7B-Instruct-v0.3

7B • Updated Dec 3, 2025 • 2.38M • 3.49k

meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.91M • • 7.78k

moonshotai/Kimi-K2-Instruct

Text Generation • 1T • Updated Apr 23 • 219k • • 2.99k

liked a dataset 8 days ago

aps/super_glue

Viewer • Updated May 16, 2025 • 196k • 683k • 208

liked a dataset 9 days ago

jat-project/jat-dataset-tokenized

Viewer • Updated Dec 22, 2023 • 32M • 481k • 32

upvoted a paper 12 days ago

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Paper • 2609.05594 • Published 17 days ago • 36

liked 3 models 13 days ago

TokenRhythm/NeoHorse-1-4B

Text Generation • 4B • Updated 11 days ago • 25k • 2.53k

TokenRhythm/NeoHorse-1-9B

Text Generation • 9B • Updated 11 days ago • 11.9k • 981

openbmb/MiniCPM5-2B

Text Generation • 3B • Updated 9 days ago • 421k • 1.63k