Publications
All authors are listed in order. A superscript asterisk (*) marks a first author, and joint first authors are each asterisked. My name is in bold. Each entry links to a public paper and, when available, its code or project page.
Preprints
Preprint, under review
CopRoute: Dependence-Aware Conformal Routing for Language Models
Siva Rajesh Kasa*, Santhosh Kumar Kasa*, Karan Gupta
Preprint, under review
SatisDive: Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion
Kevin Zhai*, Siva Rajesh Kasa, Soumya Roy, Sumit Negi, Mubarak Shah
Preprint, under review
Correcting the Optimizer’s Curse in World-Model Planning
Siva Rajesh Kasa*
2026
NeurIPS 2026 and SPGIM workshop at ICML 2026
Fast-dLLM++: Fréchet Profile Decoding for Faster Diffusion LLM Inference
Siva Rajesh Kasa*, Yasong Dai*, Sumit Negi, Hongdong Li
TMLR 2026 and Regulatable ML workshop at NeurIPS 2025
AISTATS 2026 and Efficient Reasoning workshop at NeurIPS 2025
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Ziyi Wang*, Siva Rajesh Kasa*, Ankith M S, Santhosh Kumar Kasa, Jiaru Zou, Sumit Negi, Ruqi Zhang, Nan Jiang, Qifan Song
Combining Theory and Benchmarks workshop at ICML 2026
Generative vs Discriminative? Revisiting the Shortcut Learning Debate in Text Classification
Siva Rajesh Kasa*, Karthik Raavi, Nikhil Pattisapu, Ashutosh Kumar, Yaswanth Biruduraju, Santhosh Kasa, Sumegh Roychowdhury, Ankith M S, Sumit Negi
2025
EMNLP 2025, Outstanding Paper Award
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
Siva Rajesh Kasa*, Karan Gupta, Sumegh Roychowdhury, Ashutosh Kumar, Yaswanth Biruduraju, Santhosh Kumar Kasa, Nikhil Priyatam Pattisapu, Arindam Bhattacharya, Shailendra Agarwal, Vijay Huddar
AISTATS 2025
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Qizhang Feng*, Siva Rajesh Kasa*, Santhosh Kumar Kasa, Hyokun Yun, Choon Hui Teo, Sravan Babu Bodapati
WWW 2025, short paper
Leveraging Structural Information in Tree Ensembles for Table Representation Learning
Nikhil Pattisapu*, Siva Rajesh Kasa, Sumegh Roychowdhury, Karan Gupta, Anish Bhanushali, Prasanna Srinivasa Murthy
2024
Findings of ACL 2024
Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques
Siva Rajesh Kasa*, Aniket Goel, Karan Gupta, Sumegh Roychowdhury, Pattisapu Priyatam, Anish Bhanushali, Prasanna Srinivasa Murthy
KDD 2024, Applied Data Science Track
Tackling Concept Shift in Text Classification using Entailment-style Modeling
Sumegh Roychowdhury*, Karan Gupta*, Siva Rajesh Kasa*, Prasanna Srinivasa Murthy, Alok Chandra
Responsible Language Modeling workshop at AAAI 2024
How Robust Are LLMs to In-Context Majority Label Bias?
Karan Gupta*, Sumegh Roychowdhury*, Siva Rajesh Kasa*, Santhosh Kumar Kasa, Anish Bhanushali, Nikhil Pattisapu, Prasanna Srinivasa Murthy
Earlier work
Scientific Reports 2023
Avoiding Inferior Clusterings with Misspecified Gaussian Mixture Models
Siva Rajesh Kasa*, Vaibhav Rajan
ICIS 2021
Dependency Modeling with Copulas in Multi-Armed Bandits
Siva Rajesh Kasa*, Vaibhav Rajan
SN Computer Science 2021
A Statistical Test for Detecting Dependency Breakdown in Financial Markets
Siva Rajesh Kasa*, Malay Bhattacharyya
Econometrics and Statistics
Improved Inference of Gaussian Mixture Copula Model for Clustering and Reproducibility Analysis using Automatic Differentiation
Siva Rajesh Kasa*, Vaibhav Rajan
Bioinformatics 2020
Gaussian Mixture Copulas for High-Dimensional Clustering and Dependency-Based Subtyping
Siva Rajesh Kasa*, Sakyajit Bhattacharya, Vaibhav Rajan
Software paper
arXiv preprint
Mixture-Models: A One-Stop Python Library for Model-Based Clustering using Various Mixture Models
Siva Rajesh Kasa*, Hu Yijie, Santhosh Kumar Kasa, Vaibhav Rajan