彩花 清水

oliverjones586's activity

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

upvoted a paper 1 day ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 6 days ago • 123

upvoted a paper 4 days ago

Evidence-Backed Video Question Answering

Paper • 2607.11862 • Published 11 days ago • 10

upvoted a paper 8 days ago

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

Paper • 2607.08765 • Published 15 days ago • 22

upvoted 2 papers 18 days ago

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

Paper • 2606.29526 • Published 26 days ago • 171

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published about 1 month ago • 46

upvoted 2 papers 28 days ago

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

Paper • 2606.17162 • Published Jun 15 • 177

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

Paper • 2606.24428 • Published about 1 month ago • 52

upvoted 9 papers about 1 month ago

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published Jun 16 • 210

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 483

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Paper • 2606.11324 • Published Jun 9 • 172

WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation

Paper • 2606.13672 • Published Jun 11 • 4

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

Paper • 2606.09426 • Published Jun 8 • 106

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

Paper • 2606.12087 • Published Jun 10 • 79

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 487

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

Paper • 2606.12344 • Published Jun 10 • 71

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

Paper • 2606.07190 • Published Jun 5 • 35

upvoted 2 papers about 2 months ago

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

Paper • 2606.02437 • Published Jun 1 • 240

Brain-IT-VQA: From Brain Signals to Answers

Paper • 2605.29588 • Published May 28 • 14