activity
20152026
most citedSoft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

355 citations · 2.7k across the 325 of their papers we have counts for

collaborators
Showing 2025Show all

69 papers · 1 filter

cs.LG2025

LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts

Krunal Jesani, Dmitry Ignatov, Radu Timofte

Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guide…

cs.CV2025

Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data

Georgy Perevozchikov, Nancy Mehta, Egor Ershov +1

Learned Image Signal Processing (ISP) pipelines offer powerful end-to-end performance but are critically dependent on large-scale paired raw-to-sRGB datasets. This reliance on cost…

cs.CV2025

Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design

Raghuvir Duvvuri, Chandini Vysyaraju, Avi Goyal +2

Automated neural network architecture design remains a significant challenge in computer vision. Task diversity and computational constraints require both effective architectures a…

cs.CV2025

A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks

Waleed Khalid, Dmitry Ignatov, Radu Timofte

Reusing existing neural-network components is central to research efficiency, yet discovering, extracting, and validating such modules across thousands of open-source repositories…

cs.CV2025

Layover or Direct Flight: Rethinking Audio-Guided Image Segmentation

Joel Alberto Santos, Zongwei Wu, Xavier Alameda-Pineda +1

Understanding human instructions is essential for enabling smooth human-robot interaction. In this work, we focus on object grounding, i.e., localizing an object of interest in a v…

cs.CV2025

Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization

Sina Mokhtarzadeh Azar, Emad Bahrami, Enrico Pallotta +3

In this work, we investigate diffusion-based video prediction models, which forecast future video frames, for continuous video streams. In this context, the models observe continuo…