Ivan Rubachev

puhsu's activity

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

upvoted a paper about 5 hours ago

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

Paper • 2611.03344 • Published 1 day ago • 16

upvoted a paper 27 days ago

Representation-Space MMD for Diffusion Language Models

Paper • 2610.06648 • Published 30 days ago • 26

upvoted 4 papers about 1 month ago

LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models

Paper • 2609.32264 • Published Sep 26 • 34

LLMs are General Asynchronous Agents

Paper • 2609.35427 • Published Sep 28 • 55

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published Sep 22 • 84

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published Sep 24 • 91

upvoted 2 papers 4 months ago

Registers Matter for Pixel-Space Diffusion Transformers

Paper • 2605.16147 • Published Jul 6 • 19

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Paper • 2606.30634 • Published Jun 29 • 23

upvoted a paper 6 months ago

Unsupervised Process Reward Models

Paper • 2605.10158 • Published May 11 • 21

upvoted a paper 7 months ago

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Paper • 2604.01161 • Published Apr 1 • 31

upvoted a paper 9 months ago

Rethinking Global Text Conditioning in Diffusion Transformers

Paper • 2602.09268 • Published Feb 9 • 9

upvoted 2 papers about 1 year ago

MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML

Paper • 2509.06806 • Published Sep 8, 2025 • 29

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Paper • 2508.11383 • Published Aug 15, 2025 • 40

upvoted a collection over 1 year ago

Kimi-K2

Collection

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Jan 27 • 176

upvoted 4 papers over 1 year ago

MADrive: Memory-Augmented Driving Scene Modeling

Paper • 2506.21520 • Published Jun 26, 2025 • 36

Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models

Paper • 2506.19103 • Published Jun 23, 2025 • 42

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Paper • 2505.20975 • Published May 27, 2025 • 36

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published May 25, 2025 • 87

upvoted a collection over 1 year ago

Alchemist

Collection

📊 Dataset and 🏆 checkpoints for paper 📝 "Alchemist: Turning Public Text-to-Image Data into Generative Gold" • 8 items • Updated Oct 16, 2025 • 20

upvoted a paper over 1 year ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8, 2025 • 111