Rosswill

Kutches

AI & ML interests

Recent Activity

liked a model 26 minutes ago

maximsobolev275/LTX-10Eros-LoRA-r768

updated a model about 2 hours ago

Kutches/Anim4

liked a model about 2 hours ago

Zyphra/ZAYA1-8B

View all activity

Organizations

None yet

upvoted a paper 2 days ago

Video Generation with Predictive Latents

Paper • 2605.02134 • Published 5 days ago • 14

upvoted a paper 10 days ago

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

Paper • 2604.24764 • Published 12 days ago • 116

upvoted a paper about 1 month ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 113

upvoted a collection about 1 month 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. • 8 items • Updated Apr 5 • 74

upvoted 2 papers about 1 month ago

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

Paper • 2603.19835 • Published Mar 20 • 350

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

Paper • 2603.25730 • Published Mar 26 • 53

upvoted 3 papers about 2 months ago

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 184

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

upvoted a collection 2 months ago

Qwen3.5 Unredacted MAX

Collection

Continual “abliteration” models – experimental. • 8 items • Updated 11 days ago • 4

upvoted 3 papers 2 months ago

upvoted 2 papers 3 months ago

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published Feb 13 • 44

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Paper • 2602.12675 • Published Feb 13 • 58

upvoted an article 3 months ago

Article

Qwen3.5: Nobody Agrees on Attention Anymore

Feb 17

•

upvoted 2 papers 3 months ago

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published Feb 11 • 55

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Paper • 2602.03139 • Published Feb 3 • 44

upvoted an article 3 months ago

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

Feb 4

•

upvoted a paper 3 months ago

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

Paper • 2602.02092 • Published Feb 2 • 18