Geometry of Decision Making in Language Models.

Abhinav Joshi, Divyanshu Bhatt, and Ashutosh Modi.

NeurIPS 2025, San Diego, USA.

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits.

Areeb Ahmad*, Abhinav Joshi*, and Ashutosh Modi.

NeurIPS 2025, San Diego, USA.

Calibration Across Layers: Understanding Calibration Evolution in LLMs.

Abhinav Joshi, Areeb Ahmad, and Ashutosh Modi.

EMNLP 2025, Suzhou, China.

Linguistic Inspired Pose-Stitching for End-to-End Sign Language Translation.

Abhinav Joshi*, Vaibhav Sharma*, Sanjeet Singh*, and Ashutosh Modi.

EMNLP 2025, Suzhou, China.

Towards Quantifying Commonsense Reasoning with Mechanistic Insights.

Abhinav Joshi, Areeb Ahmad, Divyaksh Shukla and Ashutosh Modi.

NAACL 2025, Albuquerque, New Mexico, USA.

COLD: Causal reasOning in cLosed Daily activities.

Abhinav Joshi*, Areeb Ahmad*, and Ashutosh Modi.

NeurIPS 2024, Vancouver, Canada.

Towards Robust Evaluation of Unlearning in LLMs via Data Transformations.

Abhinav Joshi, Shaswati Saha, Divyaksh Shukla, Sriram Vema, Harsh Jhamtani, Manas Gaur, and Ashutosh Modi.

EMNLP 2024 (Findings), Miami, Florida, USA.

IL-TUR: Benchmark for Legal Text Understanding and Reasoning

Abhinav Joshi*, Shounak Paul*, Akshat Sharma, Pawan Goyal, Saptarshi Ghosh, and Ashutosh Modi.

ACL 2024, Bangkok, Thailand.

iSign: Benchmark for Indian Sign Language Processing

Abhinav Joshi, Romit Mohanty, Mounika Kanakanti, Andesha Mangla, Sudeep Choudhary, Monali Barbate, and Ashutosh Modi.

ACL 2024 (Findings), Bangkok, Thailand.

CheckersGPT: Learning World Models through Language Modeling.

Abhinav Joshi, Vaibhav Sharma, and Ashutosh Modi.

ACL 2024 (Student Research Workshop), Bangkok, Thailand.

ScriptWorld: Text Based Environment For Learning Procedural Knowledge.

Abhinav Joshi, Areeb Ahmad, Umang Pandey, and Ashutosh Modi.

IJCAI 2023, Macao, SAR.

U-CREAT: Unsupervised Case Retrieval using Events extrAcTion.

Abhinav Joshi*, Akshat Sharma*, Sai Kiran Tanikella* and Ashutosh Modi.

ACL 2023, Toronto, Canada.

ISLTranslate: Dataset for Translating Indian Sign Language.

Abhinav Joshi, Susmit Agrawal and Ashutosh Modi.

ACL 2023 (Findings), Toronto, Canada.

SemEval 2023 Task 6: LegalEval - Understanding Legal Texts

Ashutosh Modi, Prathamesh Kalamkar, Saurabh Karn, Aman Tiwari, Abhinav Joshi, Sai Kiran Tanikella, Shouvik Kumar Guha, Sachin Malhan, and Vivek Raghavan.

SemEval 2023, Toronto, Canada.

From Scripts to RL Environments: Towards Imparting Commonsense Knowledge to RL Agents

Abhinav Joshi, Areeb Ahmad, Umang Pandey, and Ashutosh Modi.

AAMAS 2023, London, UK.

CISLR: Corpus for Indian Sign Language Recognition

Abhinav Joshi, Ashwani Bhat, Pradeep S, Priya Gole, Shashwat Gupta, Shreyansh Agarwal, and Ashutosh Modi.

EMNLP 2022, Abu Dhabi, UAE.

ScriptWorld: A Scripts-based RL Environment

Abhinav Joshi, Areeb Ahmad, Umang Pandey, and Ashutosh Modi.

LaReL 2022 (NeurIPS Workshop), New Orleans, USA. (Best Paper Award 🥈)

Foraging in a Dynamic Environment

Kshitij Kumar, Abhinav Joshi, Ashutosh Modi, and Arjun Ramakrishnan.

ACCS9 2022, New Delhi, India.

Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments

Abhinav Joshi, Naman Gupta, Jinang Shah, Binod Bhattarai, Ashutosh Modi, and Danail Stoyanov.

ICMI 2022, Bengaluru, India.

Multimodal Representation Learning For Real-World Applications

Abhinav Joshi.

ICMI 2022, Bengaluru, India.

Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts.

Keshav Bansal, Harsh Agarwal, Abhinav Joshi, and Ashutosh Modi.

COLING 2022, Virtual.

Impact of Working Memory on Patch Foraging

Kshitij Kumar, Abhinav Joshi, Archit Bansal, Ashutosh Modi, and Arjun Ramakrishnan.

RLDM 2022, Prague, Czech Republic.

COGMEN: COntextualized GNN based Multimodal Emotion recognitioN

Abhinav Joshi, Ashwani Bhat, Ayush Jain, Atin Singh, and Ashutosh Modi.

NAACL 2022, Seattle, USA.