liyaxuan

lllyx

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

upvoted a collection 21 days ago

upvoted a collection 21 days ago

View all activity

Organizations

upvoted a paper 11 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 25 days ago • 97

upvoted 2 collections 21 days ago

Rethinking OPD

This collection includes the models used in paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe" • 5 items • Updated 21 days ago • 2

One Shot OPD

2 items • Updated 21 days ago • 3

upvoted a paper 21 days ago

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

Paper • 2609.04172 • Published 22 days ago • 101

updated a collection 22 days ago

Rethinking OPD

This collection includes the models used in paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe" • 5 items • Updated 21 days ago • 2

upvoted a collection about 1 month ago

JustRL

3 items • Updated May 2 • 6

upvoted a paper about 1 month ago

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

Paper • 2608.14441 • Published Aug 14 • 29

upvoted a paper about 2 months ago

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Paper • 2512.16649 • Published Dec 18, 2025 • 34

liked a model about 2 months ago

endless-frontier/BigBang-v1

Image-Text-to-Text • 36B • Updated Aug 6 • 1.35k • • 230

upvoted a paper about 2 months ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published Jul 30 • 188

upvoted a paper 2 months ago

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

Paper • 2607.05394 • Published Jul 8 • 144

upvoted a paper 3 months ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 165

liked 2 models 3 months ago

empero-ai/Qwythos-9B-Claude-Mythos-5-1M

Text Generation • 9B • Updated Jul 14 • 19.4k • • 956

AliesTaha/fable-traces

Text Generation • 4B • Updated Jul 4 • 263 • • 210

upvoted a paper 3 months ago

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

Paper • 2606.23654 • Published Jun 22 • 81