Papers by Shubhashis Roy Dipta

4 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks (2026.findings-acl)

Copied to clipboard

Challenge: Survey aims to identify challenges of multimodal unlearning for vision, language, audio and video . retraining after deletion requests or policy updates is often impractical, survey finds .
Approach: They propose to enable selective removal across modalities while retaining overall utility.
Outcome: This study compares models with existing models to identify weaknesses and improves performance.
VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis (2026.acl-long)

Copied to clipboard

Challenge: Existing metrics for caption evaluation lack factual accuracy and limited context handling . VC-Inspector provides reproducible, fact-aware alternative that aligns closely with human judgments.
Approach: They propose a lightweight, open-source large multimodal model for reference-free evaluation of video captions with a focus on factual accuracy.
Outcome: Experiments show that VC-Inspector can generalize across diverse domains and improve on existing metrics.
Semantically-informed Hierarchical Event Modeling (2023.starsem-1)

Copied to clipboard

Challenge: Existing approaches to event modeling combine sequential latent variables with semantic ontological knowledge to improve representational capabilities.
Approach: They propose a doubly hierarchical semi-supervised event modeling framework that provides structural hierarchy while accounting for ontological hierarchy.
Outcome: The proposed model outperforms state-of-the-art models by 8.5% across two datasets and four metrics.
GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO (2026.findings-acl)

Copied to clipboard

Challenge: Existing LLMs either reason in English and translate, or simply fail on multi-step Bengali math.
Approach: They propose a Bengali mathematical reasoning model called GanitLLM with a difficulty-aware Bengali math corpus and a curriculum-based GRPO pipeline.
Outcome: The proposed model improves on Bn-MGSM and Bn MSVAMP by +8 and +7 accuracy points while increasing the percentage of Bengali reasoning tokens from 14% to over 88% and reducing solution length from 943 to 193 words.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations