Kevin Perez

k-perez's activity

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

upvoted a paper about 5 hours ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 13 days ago • 431

upvoted a paper 7 days ago

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published 8 days ago • 80

upvoted a paper 8 days ago

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

Paper • 2609.02749 • Published 9 days ago • 541

upvoted 2 papers 22 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 24 days ago • 159

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

Paper • 2608.17253 • Published 23 days ago • 97

upvoted 3 papers 25 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 28 days ago • 282

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 28 days ago • 170

Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation

Paper • 2608.13391 • Published 29 days ago • 19

upvoted a paper 26 days ago

Intern-S2-Preview: Scientific Agentic Foundation Model

Paper • 2608.13505 • Published 29 days ago • 72

upvoted 2 papers 29 days 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

upvoted 4 papers about 1 month ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 219

FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

Paper • 2608.01049 • Published Aug 2 • 13

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Paper • 2608.00574 • Published Aug 1 • 8

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

Paper • 2608.02023 • Published Aug 3 • 158