Rosswill

Kutches's activity

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

upvoted a paper 3 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 5 days ago • 465

upvoted a collection 19 days ago

Qwen3-Aquarion

Collection

Contains FP8/FP4, INT8/INT4 weight-only safetensors quants of the Qwen3 series, used by Anima, Krea2, Z-Image, Klein and many others. • 20 items • Updated 14 days ago • 1

upvoted an article 19 days ago

view article

Article

What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library

• 

shadow-llm

•

19 days ago

• 24

upvoted a paper 25 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 26 days ago • 327

upvoted 2 papers about 1 month ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published Aug 31 • 97

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published Aug 26 • 60

upvoted 2 papers about 2 months ago

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

Paper • 2608.02023 • Published Aug 3 • 161

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published Aug 3 • 188

upvoted 2 papers 2 months ago

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Paper • 2607.25308 • Published Jul 28 • 42

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published Jul 19 • 101

upvoted 4 papers 3 months ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 105

Scalable Visual Pretraining for Language Intelligence

Paper • 2607.09657 • Published Jul 10 • 56

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published Jun 29 • 50

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Paper • 2607.00248 • Published Jun 30 • 31

upvoted 3 articles 3 months ago

view article

Article

Does Your LLM Know *When It's About to Be Wrong*?

• 

ginigen-ai

•

Jul 1

• 21

view article

Article

Heretic Grimoire

• 

VINAY-UMRETHE

•

Jun 30

• 6

view article

Article

Which tokens does a hybrid model predict better?

• 

allenai

•

Jun 25

• 9

upvoted a paper 3 months ago

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 84

upvoted an article 4 months ago

view article

Article

Beyond LoRA: Can you beat the most popular fine-tuning technique?

• 
• 
• +2

BenjaminB, sayakpaul, hubnemo, kashif

•

Jun 18

• 103

upvoted a paper 4 months ago

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Paper • 2606.14249 • Published Jun 12 • 53