Yuxuan Gao

Lunar-Yuxuan's activity

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

upvoted a paper 3 days ago

WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites

Paper • 2610.03036 • Published 4 days ago • 17

upvoted a paper 4 days ago

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Paper • 2610.04128 • Published 9 days ago • 12

liked a model 5 days ago

SupersonicLabs/Julia-1

Text Classification • 0.1B • Updated 14 days ago • 4.89k • 474

upvoted a paper 21 days ago

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published 26 days ago • 68

upvoted a paper 25 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 376

updated a dataset 30 days ago

Lunar-Yuxuan/neat-storage-952203

Viewer • Updated 30 days ago • 50 • 57

published a dataset 30 days ago

Lunar-Yuxuan/neat-storage-952203

Viewer • Updated 30 days ago • 50 • 57

upvoted a paper about 1 month ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 489

liked a model about 1 month ago

nex-agi/Nex-N2.5-Pro

Text Generation • 397B • Updated 24 days ago • 33.4k • 676

upvoted 4 papers about 1 month ago

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

Paper • 2609.05588 • Published Sep 4 • 57

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

Paper • 2609.04083 • Published Sep 3 • 27

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published Aug 27 • 154

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published Sep 3 • 86

liked a model about 2 months ago

huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

Image-Text-to-Text • 27B • Updated about 22 hours ago • 2.16M • 1.26k

upvoted a paper about 2 months ago

Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review

Paper • 2608.12440 • Published Aug 12 • 11