Publications

53 papers, 41 of them peer-reviewed, with 220+ citations on Google Scholar. I’m the lead author on 19 and senior author on 34, where I mentored the first author or led the design. Each title opens a page with the abstract, links and BibTeX.

Mech Interp Workshop, ICML 2026

C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal

Safety Post-Training & Alignment

2026 · 1 citation

EMNLP 2026 Main Conference · AI for Good Workshop, ICML 2026

ALIGNBEAM: Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Safety Post-Training & Alignment

2026

EMNLP 2026 Findings

Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation

Safety Post-Training & Alignment

2026

Alberta Wells Dataset pipeline for pinpointing oil and gas wells from satellite imagery

ICML 2025 / CCAI ICLR 2025

Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery

Climate Change & Earth Observation

2025 · 6 citations

SELF-PERCEPT introspection pipeline for detecting multi-person mental manipulation

ACL 2025 / NAACL SRW Workshop 2025

SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations

NLP & AI for Social Good

2025 · 3 citations

Laplacian reconstructive network architecture for guided thermal super-resolution

Scientific Reports (Nature)

Laplacian reconstructive network for guided thermal super-resolution

Vision & Super-Resolution

2026 · 3 citations

Area

Status

My role

Year

53 papers

Safety Post-Training & Alignment

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
R E Zera Marveen Lyngkhoi, Chirag Chawla, Pratinav Seth, Utsav Avaiya, Soham Bhattacharjee, Mykola Khandoga, Rui Yuan, Vinay Kumar Sankarapu
Pre-Print2026Senior authorarXiv PDF
C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal
Aditya Kasliwal, Pratinav Seth, Vinay Kumar Sankarapu
Mech Interp Workshop, ICML 20262026Senior authorWorkshoparXiv PDF1 citation
ALIGNBEAM: Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Chirag Chawla, Pratinav Seth, Vinay Kumar Sankarapu
EMNLP 2026 Main Conference · AI for Good Workshop, ICML 20262026Senior authorConferencearXiv PDF
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
Pre-Print2026Senior authorarXiv PDF
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
Pratinav Seth, Vinay Kumar Sankarapu
Pre-Print2026Lead authorarXiv PDF2 citations
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
NeurIPS 2026 Workshop2026Senior authorWorkshoparXiv PDF
Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
Saisab Sadhu, Shreeyans Arora, Pratinav Seth
EMNLP 2026 NLLP Workshop; NeurIPS 2026 Workshop2026Senior authorWorkshoparXiv PDF
Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
EMNLP 2026 NLLP Workshop; NeurIPS 2026 Workshop2026Senior authorWorkshoparXiv PDF
Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu
Pre-Print2026Senior authorarXiv PDF
AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents
R E Zera Marveen Lyngkhoi, Abhivansh Gupta, Vidushee Vats, Ram Mohan Rao Kadiyala, Vinay Kumar Sankarapu, Pratinav Seth
Pre-Print2026Senior authorarXiv PDF
SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs
Pratinav Seth, Saisab Sadhu, Anshul Kaushal, Vinay Kumar Sankarapu
EMNLP 2026 System Demonstrations2026Lead authorDemoPaper
Drift, Then Repair: A Safety Audit of Fine-Tuned Language Models
Pratinav Seth, Anshul Kaushal, Saisab Sadhu, Vinay Kumar Sankarapu
NeurIPS 2026 Workshop2026Lead authorWorkshop
Self-Calibrating Weight-Arithmetic Safety-Drift Repair
Pratinav Seth, Vinay Kumar Sankarapu
Under Review2026Lead author
The Off-Switch Failure: When Safety-Repair Evaluation Rewards Model Collapse
Pratinav Seth
NeurIPS 2026 Workshop2026Lead authorWorkshop
CuratorKIT: Data Curation and Synthetic Data Generation for LLM Post-Training
Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu, Pratinav Seth
Pre-Print2026Senior authorarXiv PDF
Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu, Pratinav Seth
EMNLP 2026 Findings2026Senior authorConferencePaper
Document-as-Function: Verifiable Generation of Long-Form Synthetic Documents
Karun Sharma, Soham Bhattacharjee, Vinay Kumar Sankarapu, Pratinav Seth
Under Review2026Senior author

Mechanistic Interpretability & XAI

Interpretability as Alignment: Making Internal Understanding a Design Principle
Aadit Sengupta, Pratinav Seth, Vinay Kumar Sankarapu
EurIPS Workshop 20252025Senior authorWorkshoparXiv PDF5 citations
Interpretability-aware pruning for efficient medical image analysis
Nikita Malik, Pratinav Seth, Neeraj Kumar Singh, Chintan Chitroda, Vinay Kumar Sankarapu
MICCAI Workshop 20252025Senior authorWorkshoparXiv PDF
Bridging the gap in XAI-why reliable metrics matter for explainability and compliance
Pratinav Seth, Vinay Kumar Sankarapu
EurIPS Workshop 20252025Lead authorWorkshoparXiv PDF25 citations
DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
Vinay Kumar Sankarapu, Chintan Chitroda, Yashwardhan Rathore, Neeraj Kumar Singh, Pratinav Seth
IJCNN 20252025Senior authorConferencearXiv PDF8 citations
xai_evals: A Framework for Evaluating Post-Hoc Local Explanation Methods
Pratinav Seth, Yashwardhan Rathore, Neeraj Kumar Singh, Chintan Chitroda, Vinay Kumar Sankarapu
Technical Report2025Lead authorarXiv PDF5 citations
CircuitKIT: Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
Pratinav Seth, Hem Gosalia, Aditya Kasliwal, Vinay Kumar Sankarapu
NeurIPS 2026 Workshop2026Lead authorWorkshoparXiv PDF
Faithfulness to Refusal: A Causal Audit of Neuron Selectors in LLMs
Ananth Eswar, Pratinav Seth, Utsav Avaiya, Vinay Kumar Sankarapu
Under Review2026Senior authorarXiv PDF
Faithfulness Is Not Actionability: Extrinsic Validation of Circuit Selectors Under Structured Pruning
Hem Gosalia, Pratinav Seth, Aditya Kasliwal, Vinay Kumar Sankarapu
NeurIPS 2026 Workshop2026Senior authorWorkshop
BRIEF: Bounded-Context Regeneration of Long Documents with Verifiable Structural Topology
Aryan Sood, Soham Bhattacharjee, Pratinav Seth
NeurIPS 2026 Workshop2026Senior authorWorkshop
DLBacktrace v2: Extending Model-Agnostic Interpretability for LLMs and MoEs with CUDA Acceleration
Neeraj Kumar Singh, Pratinav Seth, Omkar Kakade, Chintan Chitroda, Vinay Kumar Sankarapu
Pre-Print2026Lead authorPaper

Tabular Foundation Models & Distillation

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
Mohamed Bouadi, Pratinav Seth, Aditya Tanna, Vinay Kumar Sankarapu
AITD Workshop @ EurIPS 20252025Senior authorWorkshoparXiv PDF19 citations
Orion-BiX: Bi-Axial Attention for Tabular In-Context Learning
Mohamed Bouadi, Pratinav Seth, Aditya Tanna, Vinay Kumar Sankarapu
WWW 20262026Senior authorConferencePaper8 citations
Exploring Fine-Tuning for Tabular Foundation Models
Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Vinay Kumar Sankarapu
WWW 20262026Senior authorConferencearXiv PDF7 citations
TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models (Demo)
Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Utsav Avaiya, Vinay Kumar Sankarapu
WWW 20262026Senior authorConferencearXiv PDF11 citations
Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi, Vinay Kumar Sankarapu, Pratinav Seth
FMSD Workshop, ICML 20262026Senior authorWorkshoparXiv PDF
Ensembling Tabular Foundation Models: A Diversity Ceiling and a Calibration Trap
Aditya Tanna, Yash Jignesh Desai, Pratinav Seth, Mohamed Bouadi, Nassim Bouarour, Vinay Kumar Sankarapu
FMSD Workshop, ICML 20262026Senior authorWorkshoparXiv PDF
Distilling Tabular Foundation Models for Structured Health Data
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi, Vinay Kumar Sankarapu, Pratinav Seth
SD4H Workshop, ICML 2026 · Spotlight2026Senior authorWorkshoparXiv PDF
Data Presentation over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
Aditya Tanna, Mitul Solanki, Mohamed Bouadi, Nassim Bouarour, Pratinav Seth, Vinay Kumar Sankarapu
FinDS @ ACM SIGMOD 2026 · Oral2026Senior authorWorkshoparXiv PDF

Climate Change & Earth Observation

Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery
Pratinav Seth^*, Michelle Lin^*, Brefo Dwamena Yaw, Jade Boutot, Mary Kang, David Rolnick
ICML 2025 / CCAI ICLR 20252025Lead authorConferencearXiv PDF6 citations
Performance Evaluation of Deep Segmentation Models for Contrails Detection
Akshat Bhandari, Sriya Rallabandi, Sanchit Singhal, Aditya Kasliwal, Pratinav Seth
NeurIPS 2022 Workshop2022Senior authorWorkshoparXiv PDF6 citations
Sailing Through Spectra: Unveiling the Potential of Multi-Spectral Information in Marine Debris Segmentation
Dyutit Mohanty, Aditya Kasliwal, Bharath Udapa, Pratinav Seth
The Second Tiny Papers Track at ICLR 20242024Senior authorTiny paperPDF Paper

Medical Imaging

Obscure to Observe: A Lesion-Aware MAE for Glaucoma Detection from Retinal Context
Siddhant Bharadwaj, Pratinav Seth, Chandra Sekhar Seelamantula
MIDL 20252025Lead authorConferencePaper
Does the Fairness of Your Pre-Training Hold Up? Examining the Influence of Pre-Training Techniques on Skin Tone Bias in Skin Lesion Classification
Pratinav Seth, Abhilash K Pai
WACV Workshop 20242024Lead authorWorkshopPDF Paper13 citations
ReFuSeg: Regularized Multi-Modal Fusion for Precise Brain Tumour Segmentation
Aditya Kasliwal, Sankarshanaa Sagaram, Laven Srivastava, Pratinav Seth, Adil Khan
BrainLes @ MICCAI 20232023Senior authorWorkshoparXiv PDF4 citations
UATTA-ENS: Uncertainty Aware Test Time Augmented Ensemble for PIRC Diabetic Retinopathy Detection
Pratinav Seth, Adil Khan, Ananya Gupta, Saurabh Kumar Mishra, Akshat Bhandari
NeurIPS 2022 Workshop2022Lead authorWorkshoparXiv PDF1 citation

Uncertainty & Robustness

Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data
Kumud Lakara^*, Akshat Bhandari^*, Pratinav Seth^*, Ujjwal Verma
Bayesian DL Workshop, NeurIPS 20212021Lead authorWorkshoparXiv PDF9 citations
UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Posts
Pratinav Seth^*, Mihir Agarwal^*
1st Tiny Paper Track at ICLR 20232023Lead authorTiny paperarXiv PDF2 citations
Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems
Pratinav Seth^*, Akshat Bhandari^*, Kumud Lakara^*
Pre-Print2023Lead authorarXiv PDF8 citations

SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
Danush Khanna, Pratinav Seth, Sidhaarth Sredharan Murali, Aditya Kumar Guru, Siddharth Shukla, Tanuj Tyagi, Sandeep Chaurasia, Kripabandhu Ghosh
ACL 2025 / NAACL SRW Workshop 20252025Lead authorConferencePaper3 citations
AgriLLM: Harnessing transformers for farmer queries.
Krish Didwania^*, Pratinav Seth^*, Aditya Kasliwal, Amit Agarwal
3rd Workshop on NLP for Positive Impact @ EMNLP 20242024Lead authorWorkshoparXiv PDF23 citations
SSS at SemEval-2023 Task 10: Explainable Detection of Online Sexism using Majority Voted Fine-Tuned Transformers
Sriya Rallabandi, Sanchit Singhal, Pratinav Seth
SemEval-2023 @ ACL 20232023Senior authorShared taskPaper4 citations
RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers
Pratinav Seth, Rashi Goel, Komal Mathur, Swetha Vemulapalli
BLP 2023 @ EMNLP 20232023Lead authorShared taskPaper6 citations
HGP-NLP at Shared Task: Leveraging LoRA for Lay Summarization of Biomedical Research Articles using Seq2Seq Transformers
Hemang Malik, Gaurav Pradeep, Pratinav Seth
BioNLP Workshop @ ACL 20242024Senior authorShared taskPDF Paper4 citations

Vision & Super-Resolution

CoReFusion: Contrastive Regularized Fusion for Guided Thermal Super-Resolution
Aditya Kasliwal, Pratinav Seth, Sriya Rallabandi, Sanchit Singhal
CVPR Workshop 20232023Senior authorWorkshopPaper32 citations
LaMAR: Laplacian Pyramid for Multimodal Adaptive Super Resolution (Student Abstract)
Aditya Kasliwal, Aryan Kamani, Ishaan Gakhar, Pratinav Seth, Sriya Rallabandi
AAAI Student Abstract 20242024Senior authorStudent abstractPDF Paper
Laplacian reconstructive network for guided thermal super-resolution
Aditya Kasliwal, Ishaan Gakhar, Aryan Kamani, Pratinav Seth, Ujjwal Verma
Scientific Reports (Nature)2026Senior authorJournalPaper3 citations

Team releases

Targeted Multilingual and Cybersecurity Safety Repair for Gemma 4 31B
Lexsi Labs Team
Technical Report 20262026Paper

Libraries & tools

Designed & built v1, then mentored★ 137

TabTune

Unified inference, fine-tuning and benchmarking for tabular foundation models (21 models in 7 architecture families).

GitHub Paper

Led & built; design lead & mentor★ 44

AlignTune

Modular post-training toolkit for SFT, DPO, GRPO and RLHF with interchangeable backends; runs production alignment work in BFSI, legal and healthcare.

GitHub Paper