Publication Robust Root Cause Diagnosis using In-Distribution Interventions Lokesh Nagalapatti, Ashutosh Srivastava, Sunita Sarawagi, Amit Sharma 2025 International Conference on Learning Representations | April 2025 Project
Publication RustAssistant: Using LLMs to Fix Compilation Errors in Rust Code Pantazis Deligiannis, Akash Lal, Nikita Mehrotra, Rishi Poddar, Aseem Rastogi 47th International Conference on Software Engineering (ICSE) | April 2025 Video
Publication DEDUCE: Deductive Consistency as a Frame Work to Evaluate LLM Reasoning Atharva Pandey, Kshitij Dubey, Rahul Sharma, Amit Sharma ICLR 2025 – Workshop on Reasoning and Planning for LLMs | March 2025
Publication Re-Imagine: Symbolic Benchmark Synthesis for Reasoning Evaluation Xinnuo Xu, Rachel Lawrence, Kshitij Dubey, Atharva Pandey, Fabian Falck, Risa Ueno, Aditya Nori, Rahul Sharma, Amit Sharma, Javier González ICLR 2025 – Workshop on Reasoning and Planning for LLMs | March 2025
Publication Teaching Transformers Causal Reasoning through Axiomatic Training Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Kabir Ahuja, Vineeth N. Balasubramanian, Amit Sharma ICLR 2025 – Workshop on Reasoning and Planning for LLMs | March 2025
Publication Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation Prakhar Verma, Sukruta Prakash Midigeshi, Gaurav Sinha, Arno Solin, Nagarajan Natarajan, Amit Sharma ICLR 2025 – Workshop on Reasoning and Planning for LLMs | March 2025
Publication POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025 Project
Publication KnapsackLB: Enabling Performance-Aware Layer-4 Load Balancing Rohan Gandhi, Srinivas Narayana ACM CoNEXT | March 2025
Publication vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025 Github Project
Publication Towards Efficient Large Multimodal Model Serving Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca February 2025 Project Project