| 2026 | ACL | Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models. | Zhiyuan Hu, Yibo Wang, Hanze Dong, Yuhui Xu, Amrita Saha, Caiming Xiong, Bryan Hooi, Junnan Li |
| 2025 | ICLR | ThinK: Thinner Key Cache by Query-Driven Pruning. | Yuhui Xu, Zhanming Jie, Hanze Dong, Lei Wang, Xudong Lu, Aojun Zhou, Amrita Saha, Caiming Xiong, Doyen Sahoo |
| 2025 | ICLR | Automatic Curriculum Expert Iteration for Reliable LLM Reasoning. | Zirui Zhao, Hanze Dong, Amrita Saha, Caiming Xiong, Doyen Sahoo |
| 2025 | ICML | Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction. | Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu, Caiming Xiong |
| 2024 | ICLR | CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules. | Hung Le, Hailin Chen, Amrita Saha, Akash Gokul, Doyen Sahoo, Shafiq Joty |
| 2023 | EMNLP | Personalized Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation. | Hailin Chen, Amrita Saha, Steven Chu-Hong Hoi, Shafiq Joty |
| 2022 | AAAI | Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning over Text. | Amrita Saha, Shafiq R. Joty, Steven C. H. Hoi |
| 2022 | EMNLP | Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding. | Rishabh Bhardwaj, Amrita Saha, Steven C. H. Hoi, Soujanya Poria |
| 2022 | EMNLP | Learning Label Modular Prompts for Text Classification in the Wild. | Hailin Chen, Amrita Saha, Shafiq R. Joty, Steven C. H. Hoi |
| 2022 | ICSE | Mining Root Cause Knowledge from Cloud Service Incident Investigations for AIOps. | Amrita Saha, Steven C. H. Hoi |
| 2019 | IJCAI | Neural Program Induction for KBQA Without Gold Programs or Query Annotations. | Ghulam Ahmed Ansari, Amrita Saha, Vishwajeet Kumar, Mohan Bhambhani, Karthik Sankaranarayanan, Soumen Chakrabarti |
| 2018 | AAAI | Towards Building Large Scale Multimodal Domain-Aware Conversation Systems. | Amrita Saha, Mitesh M. Khapra, Karthik Sankaranarayanan |
| 2018 | AAAI | Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph. | Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar |
| 2018 | ACL | DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension. | Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan |
| 2018 | WACV | Learning Disentangled Multimodal Representations for the Fashion Domain. | Amrita Saha, Megha Nawhal, Mitesh M. Khapra, Vikas C. Raykar |
| 2017 | EACL | Stance Classification of Context-Dependent Claims. | Roy Bar-Haim, Indrajit Bhattacharya, Francesco Dinuzzo, Amrita Saha, Noam Slonim |
| 2016 | COLING | A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation. | Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho |
| 2014 | COLING | Claims on demand - an initial demonstration of a system for automatic detection and polarity identification of context dependent claims in massive corpora. | Noam Slonim, Ehud Aharoni, Carlos Alzate, Roy Bar-Haim, Yonatan Bilu, Lena Dankin, Iris Eiron, Daniel Hershcovich, Shay Hummel, Mitesh M. Khapra, Tamar Lavee, Ran Levy, Paul Matchen, Anatoly Polnarov, Vikas C. Raykar, Ruty Rinott, Amrita Saha, Naama Zwerdling, David Konopnicki, Dan Gutfreund |
| 2014 | SDM | AUC dominant unsupervised ensemble of binary classifiers. | Priyanka Agrawal, Vikas C. Raykar, Amrita Saha |
| 2013 | COMAD | Optimally Extracting Discriminative Disjunctive Features for Dimensionality Reduction. | Amrita Saha, Naveen Nair, Ganesh Ramakrishnan |
| 2012 | AAAI | Rule Ensemble Learning Using Hierarchical Kernels in Structured Output Spaces. | Naveen Nair, Amrita Saha, Ganesh Ramakrishnan, Shonali Krishnaswamy |
| 2012 | ILP | What Kinds of Relational Features Are Useful for Statistical Learning? | Amrita Saha, Ashwin Srinivasan, Ganesh Ramakrishnan |
| 2010 | MASS | Secure connectivity model in Wireless Sensor Networks (WSN) using first order Reed-Muller codes. | Pinaki Sarkar, Amrita Saha, Morshed U. Chowdhury |