A Gravitational Interpretation of Fine-Tuning Reversion
Paper • 2606.28525 • Published • 4
배연우
luoyuxuan36
AI & ML interests
Embodied AI and robotics prototypes. Mostly focused on experiments.
Recent Activity
liked a dataset about 8 hours ago
JiakangYu/ChartSync liked a dataset 4 days ago
Project-AgML/plant_doc_classification liked a Space 5 days ago
AimeeBingmouQu/ProtectBirdsOrganizations
None yet
upvoted a paper 5 days ago
upvoted a paper about 1 month ago
upvoted 3
papers about 2 months ago
Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection
Paper • 2605.08583 • Published • 2
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers
Paper • 2605.06169 • Published • 238
World Model for Robot Learning: A Comprehensive Survey
Paper • 2605.00080 • Published • 17
upvoted 3
papers 2 months ago
Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
Paper • 2605.00529 • Published • 6
PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
Paper • 2605.02240 • Published • 9
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 171
upvoted 6
papers 3 months ago
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 245
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 117
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509
Self-Distilled RLVR
Paper • 2604.03128 • Published • 179
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 344
When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning
Paper • 2603.21289 • Published • 35
upvoted 3
papers 4 months ago
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
Paper • 2603.17051 • Published • 109
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
Paper • 2603.16859 • Published • 248
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 373