Ivan Oseledets

oseledets's activity

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

upvoted a paper 9 days ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published 12 days ago • 24

authored 9 papers 28 days ago

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing

Paper • 2309.16710 • Published Aug 17, 2023

NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer

Paper • 2209.14937 • Published Sep 29, 2022

Sparse and Transferable Universal Singular Vectors Attack

Paper • 2401.14031 • Published Jan 25, 2024

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers

Paper • 2410.07383 • Published Oct 9, 2024

Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network

Paper • 2008.05441 • Published Aug 12, 2020

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5 • 37

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

Paper • 2506.06751 • Published Jun 7 • 72

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

Paper • 2506.06395 • Published Jun 5 • 126

Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards

Paper • 2503.19948 • Published Mar 25

upvoted 3 papers 28 days ago

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

Paper • 2505.22914 • Published May 28 • 35

Seedance 1.0: Exploring the Boundaries of Video Generation Models

Paper • 2506.09113 • Published 29 days ago • 95

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

Paper • 2506.06395 • Published Jun 5 • 126

upvoted a paper 29 days ago

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

Paper • 2506.06751 • Published Jun 7 • 72

upvoted a paper 30 days ago

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published about 1 month ago • 29

upvoted 2 papers about 1 month ago

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

Paper • 2505.21115 • Published May 27 • 135

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5 • 37

authored a paper about 1 month ago

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

Paper • 2505.21189 • Published May 27 • 62

upvoted a paper about 1 month ago

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

Paper • 2505.21189 • Published May 27 • 62

authored a paper 4 months ago

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models

Paper • 2311.05928 • Published Nov 10, 2023 • 1