John Perez

Ember-Wisp's activity

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

liked a model about 4 hours ago

nex-agi/Nex-N2.5-Pro

Text Generation • Updated 2 days ago • 3 • 577

liked a model 1 day ago

Jackrong/Qwopus3.8-27B-Flash-GGUF

Image-Text-to-Text • 0.5B • Updated about 4 hours ago • 192k • 179

upvoted a paper 1 day ago

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

Paper • 2609.06373 • Published 5 days ago • 17

upvoted 2 papers 6 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 8 days ago • 176

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

Paper • 2608.26730 • Published 15 days ago • 153

liked a model 6 days ago

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated 7 days ago • 15.9k • 1.04k

upvoted a paper 7 days ago

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

Paper • 2609.02749 • Published 9 days ago • 539

liked a model 20 days ago

TenStrip/10Eros-Max

Image-Text-to-Video • Updated 1 day ago • 541

upvoted 2 papers 21 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 24 days ago • 159

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

Paper • 2608.18565 • Published 23 days ago • 116

upvoted 2 papers 24 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

upvoted 2 papers 28 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

liked a model 29 days ago

drbaph/MiniMax-H3-Turbo-Lora-ComfyUI

Text-to-Video • Updated 1 day ago • 211k • • 409

upvoted 2 papers 29 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 219

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

Paper • 2608.08285 • Published Aug 8 • 8

liked a model about 1 month ago

ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot

Image-Text-to-Text • Updated Aug 5 • 567

upvoted 2 papers about 1 month ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 102

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

Paper • 2608.03632 • Published Aug 4 • 24