John Perez

Ember-Wisp's activity

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

upvoted a paper about 22 hours ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 3 days ago • 159

upvoted a paper 1 day ago

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

Paper • 2608.26730 • Published 10 days ago • 149

liked a model 2 days ago

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated 3 days ago • 4.76k • 537

upvoted a paper 3 days ago

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

Paper • 2609.02749 • Published 4 days ago • 519

liked a model 15 days ago

TenStrip/10Eros-Max

Image-Text-to-Video • Updated 7 days ago • 485

upvoted 2 papers 17 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 19 days ago • 158

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

Paper • 2608.18565 • Published 18 days ago • 116

upvoted a paper 19 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 23 days ago • 282

upvoted a paper 20 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 23 days ago • 170

upvoted a paper 23 days ago

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

Paper • 2608.05604 • Published Aug 6 • 80

upvoted a paper 24 days ago

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

Paper • 2608.00677 • Published Aug 1 • 263

liked a model 24 days ago

drbaph/MiniMax-H3-Turbo-Lora-ComfyUI

Text-to-Video • Updated 1 day ago • 242k • • 390

upvoted 2 papers 25 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 28 days ago • 218

Ego-OSCAR: Egocentric Open source Stereo CAptuRe System

Paper • 2608.08285 • Published 29 days ago • 8

liked a model 27 days ago

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

Image-Text-to-Text • Updated Aug 5 • 558

upvoted a paper 30 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 101

upvoted a paper about 1 month ago

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

Paper • 2608.03632 • Published Aug 4 • 24

liked 2 models about 1 month ago

LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 12 days ago • 131k • 735

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 4 days ago • 2.55M • • 11.2k

upvoted a paper about 1 month ago

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

Paper • 2607.28590 • Published Jul 30 • 46