清水七海

dongxao's activity

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

upvoted a paper 5 days ago

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Paper • 2607.15263 • Published 13 days ago • 8

upvoted 2 papers about 1 month ago

DreamX-World 1.0: A General-Purpose Interactive World Model

Paper • 2606.16993 • Published Jun 15 • 114

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published Jun 16 • 77

upvoted 5 papers about 2 months ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published Jun 3 • 126

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 241

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 252

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Paper • 2605.28655 • Published May 27 • 12

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

Paper • 2605.25189 • Published May 24 • 4

upvoted a paper 2 months ago

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

Paper • 2605.26114 • Published May 25 • 66

upvoted 2 papers 3 months ago

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Paper • 2605.05566 • Published May 7 • 38

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 243

upvoted 5 papers 4 months ago

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 248

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published Apr 2 • 510

DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

Paper • 2604.04215 • Published Apr 5 • 22

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published Apr 3 • 639

The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

Paper • 2603.14375 • Published Mar 15 • 20