4 63

Maxim Kurkin

dondosss

Fr0do

AI & ML interests

Multimodal AI, CV, NLP

Recent Activity

upvoted a paper 4 days ago

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

upvoted a paper 10 days ago

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

upvoted a paper 12 days ago

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

View all activity

Organizations

dondosss's activity

upvoted a paper 4 days ago

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

Paper • 2503.01688 • Published 5 days ago • 19

upvoted a paper 10 days ago

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

Paper • 2502.18417 • Published 11 days ago • 62

upvoted 2 papers 12 days ago

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

Paper • 2501.03895 • Published Jan 7 • 50

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

Paper • 2502.15007 • Published 16 days ago • 160

upvoted 3 papers 13 days ago

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published 15 days ago • 26

VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

Paper • 2502.12084 • Published 19 days ago • 29

SurveyX: Academic Survey Automation via Large Language Models

Paper • 2502.14776 • Published 16 days ago • 91

upvoted 2 papers 15 days ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 16 days ago • 94

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Paper • 2502.14499 • Published 17 days ago • 177

upvoted 2 papers 16 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 16 days ago • 127

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published 17 days ago • 83

upvoted a paper 18 days ago

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published 18 days ago • 65

upvoted a paper 21 days ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 26 days ago • 46

upvoted a paper 26 days ago

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published 27 days ago • 86

upvoted a paper about 1 month ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 112

upvoted a collection about 1 month ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 8 items • Updated 13 days ago • 389

upvoted a paper about 2 months ago

Scaling Laws for Floating Point Quantization Training

Paper • 2501.02423 • Published Jan 5 • 26

upvoted a paper 2 months ago

3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding

Paper • 2412.18450 • Published Dec 24, 2024 • 34

upvoted 2 papers 3 months ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 129

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Paper • 2411.18363 • Published Nov 27, 2024 • 10