John Perez

Ember-Wisp's activity

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

upvoted a paper 8 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 11 days ago • 136

upvoted a paper 12 days ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 14 days ago • 428

upvoted a paper 15 days ago

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

Paper • 2609.09076 • Published 20 days ago • 24

upvoted a paper 17 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 30 days ago • 480

upvoted a paper 18 days ago

Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation

Paper • 2609.06373 • Published 22 days ago • 17

upvoted 2 papers 23 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 25 days ago • 187

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published Aug 27 • 155

upvoted a paper 25 days ago

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

Paper • 2609.02749 • Published 26 days ago • 402

upvoted 4 papers about 1 month ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 160

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

Paper • 2608.18565 • Published Aug 19 • 76

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 Aug 14 • 286

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 126

upvoted 8 papers about 2 months ago

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

Paper • 2608.05604 • Published Aug 6 • 81

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

Paper • 2608.00677 • Published Aug 1 • 265

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 180

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

Paper • 2608.08285 • Published Aug 8 • 7

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 103

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

Paper • 2608.03632 • Published Aug 4 • 25

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Paper • 2607.28590 • Published Jul 30 • 46

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

Paper • 2608.02023 • Published Aug 3 • 161