Yury Kuratov

yurakuratov's activity

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

upvoted a paper 6 days ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published 9 days ago • 55

upvoted a paper 15 days ago

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities

Paper • 2602.05281 • Published 19 days ago • 15

upvoted 2 papers 3 months ago

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

Paper • 2512.00590 • Published Nov 29, 2025 • 49

Sentence-Anchored Gist Compression for Long-Context LLMs

Paper • 2511.08128 • Published Nov 11, 2025 • 1

upvoted 2 papers 4 months ago

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization

Paper • 2510.25616 • Published Oct 29, 2025 • 105

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6, 2025 • 115

upvoted 3 papers 6 months ago

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

Paper • 2508.16745 • Published Aug 22, 2025 • 29

CAMAR: Continuous Actions Multi-Agent Routing

Paper • 2508.12845 • Published Aug 18, 2025 • 7

HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

Paper • 2508.12782 • Published Aug 18, 2025 • 25

upvoted 7 papers 9 months ago

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

Paper • 2506.06395 • Published Jun 5, 2025 • 133

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published Jun 9, 2025 • 29

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5, 2025 • 38

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27, 2025 • 140

AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment

Paper • 2506.04089 • Published Jun 4, 2025 • 47

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Paper • 2505.20411 • Published May 26, 2025 • 93

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

Paper • 2505.21189 • Published May 27, 2025 • 61

upvoted 2 papers 11 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8, 2025 • 110

A Comprehensive Survey on Long Context Language Modeling

Paper • 2503.17407 • Published Mar 20, 2025 • 49

upvoted a collection 11 months ago

Gemma 3 Release

Collection

28 items • Updated Aug 11, 2025 • 613

upvoted a paper 12 months ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published Mar 12, 2025 • 75