Maxim Kurkin

dondosss's activity

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

upvoted a paper 8 days ago

nablaNABLA: Neighborhood Adaptive Block-Level Attention

Paper • 2507.13546 • Published 16 days ago • 117

upvoted a paper 15 days ago

RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization

Paper • 2507.12142 • Published 17 days ago • 35

upvoted a paper about 1 month ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published Jun 28 • 23

upvoted 4 papers about 2 months ago

The Diffusion Duality

Paper • 2506.10892 • Published Jun 12 • 38

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5 • 128

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7 • 71

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 252

upvoted 3 papers 2 months ago

Exploring the Latent Capacity of LLMs for One-Step Text Generation

Paper • 2505.21189 • Published May 27 • 62

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 78

Risk-Averse Reinforcement Learning with Itakura-Saito Loss

Paper • 2505.16925 • Published May 22 • 26

upvoted an article 3 months ago

view article

Article

CircleGuardBench: New Standard for Evaluating AI Moderation Models

By and 7 others •

May 7

• 54

upvoted 3 papers 4 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24 • 121

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20 • 73

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Paper • 2503.13358 • Published Mar 17 • 96

upvoted 6 papers 5 months ago

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Paper • 2503.14456 • Published Mar 18 • 153

When an LLM is apprehensive about its answers -- and when its uncertainty is justified

Paper • 2503.01688 • Published Mar 3 • 21

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 67

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

Paper • 2501.03895 • Published Jan 7 • 53

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 175

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 29