Deborah Matthias

deborahmatthias's activity

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

upvoted 17 papers 1 day ago

Efficient Reasoning with Balanced Thinking

Paper • 2603.12372 • Published Mar 12 • 156

WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation

Paper • 2608.24479 • Published Aug 25 • 134

Agent-Reflex: Teaching Language Agents to Act Reflectively

Paper • 2610.17953 • Published 5 days ago • 204

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Paper • 2610.01762 • Published 17 days ago • 237

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published Sep 14 • 333

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published May 9 • 240

Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue

Paper • 2609.31948 • Published 23 days ago • 90

Reflex: Visually Grounded Reactive Humanoid Control

Paper • 2610.12772 • Published 10 days ago • 154

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 19 days ago • 138

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published Sep 2 • 503

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

Paper • 2610.09823 • Published 11 days ago • 194

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Paper • 2606.11042 • Published Jun 9 • 216

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 369

Omni-IO Skills: Harnessing Your Agent Omni-Native

Paper • 2609.31847 • Published 23 days ago • 458

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published Sep 8 • 483

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 408

VideoJev: System One Model for Video Understanding and Interaction

Paper • 2610.18615 • Published 5 days ago • 358

upvoted a paper 2 days ago

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

Paper • 2610.06293 • Published 13 days ago • 145

upvoted 2 papers 15 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 413

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 160