Listener-Rewarded Thinking in VLMs for Image Preferences
Paper • 2506.22832 • Published • 22
Ivan Oseledets
oseledets
AI & ML interests
Machine learning, deep learning, tensors
Recent Activity
authored a paper 6 days ago
Listener-Rewarded Thinking in VLMs for Image Preferences authored a paper 6 days ago
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations
and Sentences authored a paper 6 days ago
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution AlgorithmsOrganizations
None yet
authored 20
papers 6 days ago
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
Paper • 2508.03542 • Published • 7
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Paper • 2511.17592 • Published • 122
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Paper • 2509.22033 • Published • 19
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Paper • 2509.22067 • Published • 28
Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking
Paper • 2510.14586 • Published • 1
Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching
Paper • 2603.24428 • Published • 2
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
Paper • 2606.00683 • Published • 102
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
Paper • 2602.05281 • Published • 14
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
Paper • 2602.14111 • Published • 57
Certification of Speaker Recognition Models to Additive Perturbations
Paper • 2404.18791 • Published
IDLM: Inverse-distilled Diffusion Language Models
Paper • 2602.19066 • Published
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Paper • 2203.10833 • Published
Translate your gibberish: black-box adversarial attack on machine translation systems
Paper • 2303.10974 • Published
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Paper • 2609.15504 • Published • 37
One Task Vector is not Enough: A Large-Scale Study for In-Context Learning
Paper • 2505.23911 • Published
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Paper • 2609.29845 • Published • 105
Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers
Paper • 2609.32814 • Published • 22
LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models
Paper • 2609.32264 • Published • 50
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
Paper • 2609.37533 • Published • 67