Pisets: A Robust Speech Recognition System for Lectures and Interviews
Paper • 2601.18415 • Published • 35
Vitaliy Pozdnyakov
vpozdnyakov
AI & ML interests
None yet
Organizations
None yet
upvoted a paper 2 months ago
upvoted a collection 4 months ago
upvoted a paper 5 months ago
upvoted 5
papers 10 months ago
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
Paper • 2506.19103 • Published • 42
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
Paper • 2506.06751 • Published • 71
DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
Paper • 2505.20975 • Published • 36
Image Reconstruction as a Tool for Feature Analysis
Paper • 2506.07803 • Published • 29
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
Paper • 2505.21115 • Published • 143
upvoted 2
papers 11 months ago
upvoted 8
papers about 1 year ago
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 120
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Paper • 2503.16660 • Published • 72
One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
Paper • 2503.13358 • Published • 95
RuCCoD: Towards Automated ICD Coding in Russian
Paper • 2502.21263 • Published • 133
GHOST 2.0: generative high-fidelity one shot transfer of heads
Paper • 2502.18417 • Published • 67
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
Paper • 2502.13063 • Published • 74
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators
Paper • 2502.06394 • Published • 89
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
Paper • 2501.13200 • Published • 70
upvoted 2
papers over 1 year ago