activity
20242026
collaborators

5 papers

cs.CV2026

Interpretability Transfer from Language to Vision via Sparse Autoencoders

Alexey Kravets, Da Li, Chuan Li +2

Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambigui…

cs.CV2025

Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting

Alexey Kravets, Da Chen, Vinay P. Namboodiri

CLIP is a foundational model with transferable classification performance in the few-shot setting. Several methods have shown improved performance of CLIP using few-shot examples.…

cs.CL2025

Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models

Olga Loginova, Oleksandr Bezrukov, Ravi Shekhar +1

Evaluating Video Language Models (VLMs) is a challenging task. Due to its transparency, Multiple-Choice Question Answering (MCQA) is widely used to measure the performance of these…

cs.CV2024

Zero-Shot Class Unlearning in CLIP with Synthetic Samples

A. Kravets, V. Namboodiri

Machine unlearning is a crucial area of research. It is driven by the need to remove sensitive information from models to safeguard individuals' right to be forgotten under rigorou…

cs.CV2024

CLIP Adaptation by Intra-modal Overlap Reduction

Alexey Kravets, Vinay Namboodiri

Numerous methods have been proposed to adapt a pre-trained foundational CLIP model for few-shot classification. As CLIP is trained on a large corpus, it generalises well through ad…