Benjamingr25

benjamingr25's activity

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

upvoted a paper about 6 hours ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 3 days ago • 158

upvoted a paper 4 days ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published 9 days ago • 116

upvoted 2 papers 14 days ago

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 16 days ago • 151

ISO: An RLVR-Native Optimization Stack

Paper • 2607.19331 • Published 17 days ago • 8

upvoted a paper 18 days ago

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

Paper • 2607.11523 • Published 26 days ago • 13

upvoted a paper 27 days ago

From Foundation to Application: Improving VLA Models in Practice

Paper • 2607.06403 • Published Jul 7 • 20

upvoted a paper about 2 months ago

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 194

upvoted 2 papers 2 months ago

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Paper • 2601.07525 • Published May 28 • 10

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 191

upvoted 3 papers 3 months ago

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 118

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

Paper • 2605.06130 • Published May 7 • 116

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

Paper • 2604.09408 • Published Apr 29 • 5

upvoted 5 papers 4 months ago

Structured Distillation of Web Agent Capabilities Enables Generalization

Paper • 2604.07776 • Published Apr 9 • 23

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 265

Less Detail, Better Answers: Degradation-Driven Prompting for VQA

Paper • 2604.04838 • Published Apr 6 • 13

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Paper • 2603.24414 • Published Mar 25 • 183

GenMask: Adapting DiT for Segmentation via Direct Mask

Paper • 2603.23906 • Published Mar 25 • 11

upvoted 3 papers 5 months ago

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published Mar 4 • 211

Believe Your Model: Distribution-Guided Confidence Calibration

Paper • 2603.03872 • Published Mar 4 • 40

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 88