출판 Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad, Elias Stengel-Eskin, Akshay Nambi, Mohit Bansal 2025 COLM | October 2026
출판 LLM-42: Enabling Determinism in LLM Inference with Verified Speculation Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar 2026 Symposium on Operating Systems Principles | September 2026 프로젝트
출판 Scalable GPU Acceleration of Scalar Functions in Analytical Databases: Compilation, Benchmarking, and Optimization Kaushik Rajan, Sampath Rajendra, Momin Al-Ghosien, Nicolas Bruno, Carlo Curino, Matteo Interlandi, Yinan Li, Lukas M. Maas, Craig Peeper, Surajit Chaudhuri, Johannes Gehrke VLDB 2026 | August 2026
출판 Hidden Causality Inclusion in Radiology Reports with Multimodal Small Language Models Mercy Ranjit, Tanuja Ganu NTCIR-18 HIDDEN-RAD: Hidden Causality Inclusion in Radiology Reports with Multimodal Small Language Models 프로젝트
출판 Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs Sai Srinivas Kancheti, Aditya Kanade, Vineeth N Balasubramanian, Tanuja Ganu 2026 Annual Meeting of the Association for Computational Linguistics | July 2026
출판 TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems Ishan Kavathekar, Hemang Jain, Ameya Rathod, Ponnurangam Kumaraguru, Tanuja Ganu 2026 Annual Meeting of the Association for Computational Linguistics | July 2026
출판 Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin’ichi Satoh, Tanuja Ganu, R. Shah July 2026 arXiv | July 2026
출판 Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse Raj Jaiswal, Anany Singh Divy, Savar Bhasin, Adi Bajpai, Tanuja Ganu, R. Shah July 2026 arXiv | July 2026
출판 Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use Aradhye Agarwal, Gurdit Siyan, Yash Pandya, Joykirat Singh, Akshay Nambi, Ahmed Awadallah 2026 International Conference on Machine Learning (ICML) | July 2026
출판 HOBIT: Hardness Optimized Batch Sampling for InfoNCE Training Himanshu Dutta, Lokesh Nagalapatti, Yashoteja Prabhu International Conference on Machine Learning | July 2026 Spotlight Acceptance
Research
Research