# Somak Aditya

**Type:** Researchers  
**Canonical URL:** https://scholariq.org/researchers/somak-aditya/

## Facts

| Field | Value |
| --- | --- |
| Citations | 423 |
| Field | Topic Modeling |
| h-index | 8 |
| i10-index | 6 |
| Last Known Institution | Indian Institute of Technology Kharagpur |
| OpenAlex ID | https://openalex.org/A5071844229 |
| Works | 66 |

## Researcher papers

- [Image Understanding using vision and reasoning through Scene Description Graph](https://scholariq.org/papers/image-understanding-using-vision-and-reasoning-through-scene-description-graph/)
- [Towards addressing the winograd schema challenge: building and using a semantic parser and a knowledge hunting module](https://scholariq.org/papers/towards-addressing-the-winograd-schema-challenge-building-and-using-a-semantic/)
- [Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering](https://scholariq.org/papers/explicit-reasoning-over-end-to-end-neural-architectures-for-visual-question/)
- [From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge](https://scholariq.org/papers/from-images-to-sentences-through-scene-description-graphs-using-commonsense/)
- [Visual Commonsense for Scene Understanding Using Perception, Semantic Parsing and Reasoning.](https://scholariq.org/papers/visual-commonsense-for-scene-understanding-using-perception-semantic-parsing-and/)
- [Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks](https://scholariq.org/papers/tricking-llms-into-disobedience-formalizing-analyzing-and-detecting-jailbreaks/)
- [Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task](https://scholariq.org/papers/trusting-roberta-over-bert-insights-from-checklisting-the-natural-language/)
- [Emotion Recognition From Speech Using Telugu Language and Deep Learning Models](https://scholariq.org/papers/emotion-recognition-from-speech-using-telugu-language-and-deep-learning-models/)
- [Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance](https://scholariq.org/papers/analyzing-the-effects-of-reasoning-types-on-cross-lingual-transfer-performance/)
- [MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning](https://scholariq.org/papers/mathsensei-a-tool-augmented-large-language-model-for-mathematical-reasoning/)
- [An Empirical Study of ResNet50 Hyperparameter Tuning for Plant Disease Classification](https://scholariq.org/papers/an-empirical-study-of-resnet50-hyperparameter-tuning-for-plant-disease/)

## Researcher topics

- [Topic Modeling](https://scholariq.org/topics/topic-modeling/)
- [Natural Language Processing Techniques](https://scholariq.org/topics/natural-language-processing-techniques/)
- [Multimodal Machine Learning Applications](https://scholariq.org/topics/multimodal-machine-learning-applications/)
- [Advanced Image and Video Retrieval Techniques](https://scholariq.org/topics/advanced-image-and-video-retrieval-techniques/)
- [Domain Adaptation and Few-Shot Learning](https://scholariq.org/topics/domain-adaptation-and-few-shot-learning/)

## Researcher university

- [Indian Institute of Technology Kharagpur](https://scholariq.org/institutions/indian-institute-of-technology-kharagpur/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.