John Perez

Ember-Wisp's activity

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

liked a model 9 days ago

TenStrip/10Eros-Max

Image-Text-to-Video • Updated about 20 hours ago • 407

upvoted 2 papers 11 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 13 days ago • 157

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

Paper • 2608.18565 • Published 12 days ago • 116

upvoted 2 papers 13 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 17 days ago • 280

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 17 days ago • 170

upvoted a paper 17 days ago

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

Paper • 2608.05604 • Published 25 days ago • 80

upvoted a paper 18 days ago

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

Paper • 2608.00677 • Published 30 days ago • 263

liked a model 18 days ago

drbaph/MiniMax-H3-Turbo-Lora-ComfyUI

Text-to-Video • Updated 3 days ago • 203k • • 371

upvoted 2 papers 19 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 22 days ago • 218

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

Paper • 2608.08285 • Published 23 days ago • 8

liked a model 21 days ago

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

Image-Text-to-Text • Updated 25 days ago • 542

upvoted a paper 24 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 25 days ago • 100

upvoted a paper 25 days ago

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

Paper • 2608.03632 • Published 27 days ago • 24

liked a model 25 days ago

LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 6 days ago • 196k • 718

liked a model 26 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 11 days ago • 2.79M • • 11.1k

upvoted 2 papers 27 days ago

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 28 days ago • 158

upvoted a paper 28 days ago

Evaluation-Verification Reward for Consistent Multi-Reference Image Editing

Paper • 2607.29025 • Published about 1 month ago • 17

liked a model 28 days ago

HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Image-Text-to-Text • 35B • Updated Apr 17 • 2.14M • 3.55k

liked a model about 1 month ago

unsloth/Kimi-K3

Image-Text-to-Text • 2.8T • Updated Jul 28 • 702 • 249