Zhao Lei

valsco's activity

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

upvoted a paper 15 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 19 days ago • 81

upvoted a paper 22 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 24 days ago • 88

upvoted a paper about 1 month ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published Aug 10 • 176

upvoted a paper about 2 months ago

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published Jul 28 • 65

upvoted a paper 2 months ago

MuScriptor: An Open Model for Multi-Instrument Music Transcription

Paper • 2607.08168 • Published Jul 9 • 16

upvoted 2 papers 3 months ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 178

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 103

upvoted 11 papers 4 months ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Paper • 2605.29801 • Published May 28 • 145

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published May 27 • 149

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Paper • 2605.27366 • Published May 26 • 29

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 57

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards

Paper • 2605.14539 • Published May 14 • 6

MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Paper • 2605.18565 • Published May 19 • 4

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

Paper • 2605.06527 • Published May 7 • 48

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Paper • 2605.07755 • Published May 8 • 22

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published May 7 • 74

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published May 1 • 47

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

Paper • 2604.28196 • Published Apr 30 • 27

upvoted 2 papers 5 months ago

From Context to Skills: Can Language Models Learn from Context Skillfully?

Paper • 2604.27660 • Published May 3 • 74

Crowded in B-Space: Calibrating Shared Directions for LoRA Merging

Paper • 2604.16826 • Published Apr 18 • 7