Publications

2026

Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
Rounak Saha, Gurusha Juneja, Dayita Chaudhuri, Naveeja Sajeevan, Nihar B Shah, and Danish Pruthi
International Conference on Machine Learning (ICML 2026)

Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
Ayushman Raghuvanshi, Thummaluru Siddartha Reddy, Sundeep Prabhakar Chepuri, and Mahesh Chandran
International Conference on Machine Learning (ICML 2026)

Blending Neural Control Density Functions for Stabilization and Safety
Sahil Chaudhary, Chaitanya Murti, and Chiranjib Bhattacharyya
International Conference on Machine Learning (ICML 2026)

Interpretable Discovery of One-parameter Subgroups: A Modular Framework for Elliptical, Hyperbolic, and Parabolic Symmetries
Pavan Karjol, Vivek V Kashyap, Rohan Kashyap, and Prathosh A P
International Conference on Machine Learning (ICML 2026)

Evaluating Reasoning Models for Queries with Presuppositions
Rose Sathyanathan, Kinshuk Vasisht, Danish Pruthi
Findings of the Association for Computational Linguistics (ACL 2026)

Rethinking Dataset Distillation: Hard Truths about Soft Labels
Priyam Dey, Aditya Sahdev, Sunny Bhati, Konda Reddy Mopuri, and R Venkatesh Babu
Conference on Computer Vision and Pattern Recognition (CVPR 2026) (oral presentation)

SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation
Vaibhav Agrawal, Rishubh Parihar, Pradhaan S Bhat, Ravi Kiran Sarvadevabhatla, and R Venkatesh Babu
Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
Rishubh Parihar, Or Patashnik, Daniil Ostashev, R Venkatesh Babu, Daniel Cohen-Or, and Kuan-Chieh Jackson Wang
Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
Ankit Dhiman, Tao Lu, Srinath R, Emre Arslan, Angela Xing, Yuanbo Xiangli, R Venkatesh Babu, and Srinath Sridhar
Conference on Computer Vision and Pattern Recognition (CVPR 2026) (highlight presentation)

Objects in Generated Videos Are Slower Than They Appear: They Follow Sub-Earth Gravity and Don’t Know Galileo’s Principle…for nowObjects in Generated Videos Are Slower Than They Appear: They Follow Sub-Earth Gravity and Don’t Know Galileo’s Principle…
Varun Varma Thozhiyoor, Shivam Tripathi, R Venkatesh Babu, and Anand Bhattad
Conference on Computer Vision and Pattern Recognition (CVPR 2026) (Findings)

Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning in Vision-Language Models
Abhishek Kumar Sinha, Nitant Dube, and Soma Biswas
Conference on Computer Vision and Pattern Recognition (CVPR 2026)

GenErase: Generalizable and Semantically-Aware Concept Erasure in Diffusion Models
Korada Sri Vardhana and Soma Biswas
Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Defending CLIP via Noise-Induced Feature Dynamics for Training-Free, Zero-shot Adversarial Robustness
Debarshi Brahma and Soma Biswas
Conference on Computer Vision and Pattern Recognition (CVPR 2026) (Findings)

GeoDiv: Framework for Measuring Geographical Diversity in Text-to-Image Models
Abhipsa Basu, Mohana Singh, Shashank Agnihotri, Margret Keuper, and R Venkatesh Babu
International Conference on Learning Representations (ICLR 2026)

Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models
Kailash Gopal Darmasubramanian, Akash Pareek, Arindam Khan, and Arpit Agarwal
International Conference on Learning Representations (ICLR 2026)

Why DPO is a Misspecified Estimator and How to Fix It
Aditya Gopalan, Sayak Ray Chowdhury, and Debangshu Banerjee
International Conference on Learning Representations (ICLR 2026) (oral presentation)

Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
Kumar Shubham, Nishant Sharma, Karn Tiwari, and Prathosh A P
International Conference on Learning Representations (ICLR 2026)

f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
Subhodip Panda, Dhruv Tarsadiya, Shashwat Sourav, Prathosh A P, and Sai Praneeth Karimireddy
International Conference on Learning Representations (ICLR 2026)

Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models
Korada Sri Vardhana, Shrikrishna Lolla, and Soma Biswas
Winter Conference on Applications of Computer Vision (WACV 2026)

O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model
R Gupta, M Karuppasamy, S Marjit, A Tripathi, and A Chakraborty
AAAI Conference on Artificial Intelligence (AAAI 2026)

UniC-Lift: Unified 3D Instance Segmentation via Contrastive learning
Ankit Dhiman, Srinath R, Jaswanth Reddy, Lokesh R Boregowda, and Venkatesh Babu Radhakrishnan
AAAI Conference on Artificial Intelligence (AAAI 2026)

Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification
Abhipsa Basu, Aviral Gupta, Abhijnya B, and R Venkatesh Babu
AAAI Conference on Artificial Intelligence (AAAI 2026) (AI for Social Impact track)

Beyond World Models: Rethinking Understanding in AI Models
Tarun Gupta and Danish Pruthi
AAAI Conference on Artificial Intelligence (AAAI 2026)

2025

Partially Blinded Unlearning: Class Unlearning for Deep Networks from Bayesian Perspective
Subhodip Panda, Shashwat Sourav, and Prathosh A P
AAAI Conference on Artificial Intelligence (AAAI 2025)

Two-timescale Critic-Actor for Average Reward MDPs with Function Approximation
Prashansa Panda and Shalabh Bhatnagar
AAAI Conference on Artificial Intelligence (AAAI 2025)

AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting
Gurutva Patle, Nilay Girgaonkar, Nagabhushan Somraj, and Rajiv Soundararajan
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia 2025)

GNN Inferencing on Large Streaming Graphs
Pranjal Naman and Yogesh Simmhan
45th IEEE International Conference on Distributed Computing Systems (IEEE ICDCS 2025)

Semantic Prototype-guided sampling for long-tailed generalized category discovery
Nitu Pathak, Anwesha Banerjee, and Soma Biswas
Internation Conference on Image Processing (ICIP 2025)

Segmentation Assisted Incremental Test Time Adaptation in an Open World
Manogna Sreenivas and Soma Biswas
British Machine Vision Conference (BMVC 2025)

Sequential Attention-based Sampling for Histopathological Analysis
Tarun G, Naman Malpani, Gugan Thoppe, and Devarajan Sridharan
39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

Concept Forgetting via Label Annealing
Subhodip Panda, Ananda Theertha Suresh, Atri Guha, and Prathosh A P
41st Conference on Uncertainty in Artificial Intelligence (UAI 2025)

Zero-Shot Depth Aware Image Editing with Diffusion Models
Rishubh Parihar, Sachidanand V S, and R Venkatesh Babu
International Conference on Computer Vision (ICCV 2025)
[Project page]

UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors
Srinath, Suhas, Aditya Chandrasekar, Hemang Jamadagni, Rajiv Soundararajan, and Prathosh A P
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)

All That Glitters is Not Novel: Plagiarism in AI Generated Research
Tarun Gupta and Danish Pruthi
Association for Computational Linguistics (ACL 2025)
Received the Outstanding Paper Award

FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes
Janki Atul Nawale, Mohammed Safi Ur Rahman Khan, Janani D, Mansi Gupta, Danish Pruthi, and Mitesh M Khapra
Association for Computational Linguistics (ACL 2025)
[Code] [Data]

Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on Twitch
Prarabdh Shukla, Wei Yin Chong, Yash Patel, Brennan Schaffner, Danish Pruthi, and Arjun Bhagoji
Association for Computational Linguistics (ACL 2025)
Senior Area Chairs’ Highlights (Top 3% of accepted papers)

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Saksham Rastogi, Pratyush Maini, and Danish Pruthi
International Conference on Machine Learning (ICML 2025)

Discovering a Zero (Zero-Vector Class of Machine Learning)
Harikrishna Metta and R Venkatesh Babu
International Conference on Machine Learning (ICML 2025) (Spotlight)

Latent Mamba Operator for Partial Differential Equations
Karn Tiwari, Niladri Dutta, N M Anoop Krishnan, and Prathosh A P
International Conference on Machine Learning (ICML 2025) 

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation
Piyush Tiwary, Kinjawl Bhattacharyya, and Prathosh A P
International Conference on Machine Learning (ICML 2025) 

Knowledge Graph Guided Evaluation of Abstention Techniques
Kinshuk Vasisht, Navreet Kaur, and Danish Pruthi
Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
Kirti Bhagat, Kinshuk Vasisht, and Danish Pruthi
Findings of the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)

Compass Control: Multi-Object Orientation Control for Text-to-Image Generation
Rishubh Parihar, Vaibhav Agarwal, Sachidanand V S, and R Venkatesh Babu
Conference on Computer Vision and Pattern Recognition (CVPR 2025)
[Project Page]

MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World
Ankit Dhiman, Manan Shah, and R Venkatesh Babu
Conference on Computer Vision and Pattern Recognition (CVPR 2025)
[Project Page]

MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection
Rishubh Parihar, Srinjay Sarkar, Sarthak Vora, Jogendra Nath Kundu, and R Venkatesh Babu
Conference on Computer Vision and Pattern Recognition (CVPR 2025)
[Project Page]

Composing Parts for Expressive Object Generation
Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni, R Venkatesh Babu, and Srikrishna Karanam
Conference on Computer Vision and Pattern Recognition (CVPR 2025)
In collaboration with Adobe Research, India
[Paper]

2024

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
Saksham Rastogi and Danish Pruthi
Empirical Methods in Natural Language Processing (EMNLP 2024)

Performance Trade-offs of a Family of Text Watermarks
Anirudh Ajith, Sameer Singh, and Danish Pruthi
Findings of the Conference on Empirical Methods in NLP (EMNLP 2024)

Evaluating Large Language Models for Health-related Queries with Presuppositions
Navreet Kaur, Monojit Choudhury, and Danish Pruthi
Findings of the Association for Computational Linguistics (ACL 2024)