Richard Williams

richardwilliams's activity

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

upvoted a paper 2 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 16 days ago • 446

upvoted a paper 4 days ago

Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks

Paper • 2609.08404 • Published 6 days ago • 25

upvoted a paper 9 days ago

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 13 days ago • 121

upvoted a paper 10 days ago

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

Paper • 2609.02749 • Published 12 days ago • 545

upvoted a paper 11 days ago

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published 14 days ago • 383

upvoted 2 papers 24 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 27 days ago • 159

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 26 days ago • 97

upvoted 2 papers 27 days ago

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published about 1 month ago • 282

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published about 1 month ago • 170

upvoted 10 papers about 1 month ago

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Paper • 2608.05604 • Published Aug 6 • 80

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 263

Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness

Paper • 2608.09766 • Published Aug 10 • 6

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

Paper • 2608.01851 • Published Aug 3 • 12

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Paper • 2608.01837 • Published Aug 3 • 39

DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents

Paper • 2608.00486 • Published Aug 1 • 15

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published Aug 3 • 158

QQWorld: Quantile-Quantile Matching for World Model Regularization

Paper • 2607.28415 • Published Jul 30 • 31

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published Jul 30 • 186

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published Jul 30 • 311