伊藤拓海

isabellat71's activity

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

upvoted a paper 1 day ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published 10 days ago • 153

upvoted a paper 8 days ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published 23 days ago • 176

upvoted a paper 12 days ago

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

Paper • 2606.24428 • Published 15 days ago • 52

upvoted a paper 14 days ago

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Paper • 2606.21337 • Published 19 days ago • 74

upvoted 2 papers 18 days ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 21 days ago • 139

Looped World Models

Paper • 2606.18208 • Published 22 days ago • 477

upvoted a paper 25 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Paper • 2606.12087 • Published 28 days ago • 77

upvoted 2 papers 26 days ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published 30 days ago • 486

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published 28 days ago • 71

upvoted a paper 27 days ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published Jun 4 • 69

upvoted a paper 29 days ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published Jun 3 • 126

upvoted 2 papers about 1 month ago

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Paper • 2606.01311 • Published May 31 • 37

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

Paper • 2605.30611 • Published May 28 • 250