Rosswill

Kutches's activity

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

upvoted an article 7 days ago

view article

Article

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

• 
• 
• +2

BenjaminB, sayakpaul, hubnemo, kashif

•

9 days ago

• 62

upvoted a paper 11 days ago

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

Paper • 2606.14249 • Published 15 days ago • 47

upvoted a paper 19 days ago

ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?

Paper • 2606.05553 • Published 23 days ago • 48

upvoted a paper 29 days ago

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published about 1 month ago • 61

upvoted 5 papers about 1 month ago

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published May 20 • 207

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Paper • 2605.22791 • Published May 21 • 33

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Paper • 2605.14386 • Published May 14 • 62

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published May 13 • 223

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published May 13 • 105

upvoted 4 papers about 2 months ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 237

Flow-OPD: On-Policy Distillation for Flow Matching Models

Paper • 2605.08063 • Published May 8 • 102

Video Generation with Predictive Latents

Paper • 2605.02134 • Published May 4 • 24

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 119

upvoted a paper 3 months ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 116

upvoted a collection 3 months ago

Gemma 4 Uncensored

Collection

Abliterated Gemma 4 models with refusal behavior removed. Biprojection + EGA for MoE. Cross-validated against 686 prompts from 4 datasets. • 10 items • Updated 13 days ago • 99

upvoted 5 papers 3 months ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published Mar 20 • 352

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Paper • 2603.25730 • Published Mar 26 • 53

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 189

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Paper • 2603.12648 • Published Mar 13 • 14

Can Vision-Language Models Solve the Shell Game?

Paper • 2603.08436 • Published Mar 9 • 39