Publications

2026

1. ICLR

   OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens

   Konstantin Friedrich Willeke, Polina Turishcheva, Alex Gilbert, and 18 more authors

   In International Conference on Learning Representations, 2026

2025

1. NeurIPS-W

   Beyond Pixels: A Differentiable Pipeline for Probing Neuronal Selectivity in 3D

   Pavithra Elumalai, Mohammad Bashiri, Goirik Chakrabarty, and 2 more authors

   In NeurIPS Workshop on Representational Alignment (NeurReps), 2025

   Oral
2. Springer

   From pixels to profits: a novel approach to identify rare events for a group of US equities

   Lubdhak Mondal, Kapil Chandak, Goirik Chakrabarty, and 1 more author

   Annals of Data Science, 2025

   Abs

   Investors are interested in the growth of their portfolios. The investment strategy focuses primarily on investing in low-risk and low-volatility companies. Nevertheless, it is important to acknowledge that every investment portfolio carries an inherent danger of experiencing financial losses due to negative progression and market crashes. This paper proposes an innovative methodology for forecasting rare events in financial time series based on the analysis of “images”. In addition, this paper deals with an enhancement to the current image formulation techniques, with the objective of addressing specific limitations that hinder their practical application in the financial analysis. In contrast to prior studies, which impose limitations on the “image-based-examination” of multiple securities, the approach presented in this paper enables the evaluation of various US Large Cap Securities, hence expanding its breadth and significance. Furthermore, the increased scope of applicability enhances the underlying algorithm’s adaptability and pertinence. One notable advancement is the incorporation of CVaR as a key measure for distinguishing between rare-event and non-rare-event scenarios. Expanding upon the limitations identified in the preceding studies, this paper presents a comprehensive enhancement in the study of financial data based on image analysis techniques.

2024

1. ACMMM

   LoMOE: Localized Multi-Object Editing via Multi-Diffusion

   Goirik Chakrabarty, Aditya Chandrasekar, Ramya Hebbalaguppe, and 1 more author

   In Proceedings of the 32nd ACM International Conference on Multimedia, 2024

   Abs Code Website

   Recent developments in diffusion models have demonstrated an exceptional capacity to generate high-quality, prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image editing, which tend to be less effective when making precise edits to specific objects or fine-grained regions within a scene containing single/multiple objects. We introduce a novel framework for zero-shot localized multi-object editing through a multi-diffusion process to overcome this challenge. This framework empowers users to perform various operations on objects within an image, such as adding, replacing, or editing many objects in a complex scene in one pass. Our approach leverages foreground masks and corresponding simple text prompts that exert localized influences on the target regions resulting in high-fidelity image editing. A combination of cross-attention and background preservation losses within the latent space ensures that the characteristics of the object being edited are preserved while simultaneously achieving a high-quality, seamless reconstruction of the background with fewer artifacts compared to the state-of-the-art (SOTA). We also curate and release a dataset dedicated to multi-object editing, named LoMOE-Bench. Our experiments against existing SOTA demonstrate the improved effectiveness of our approach in terms of both image editing quality, and inference speed.

2. CVPRW

   ReMOVE: A Reference-free Metric for Object Erasure

   Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024

   Abs Code

   We introduce ReMOVE a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore ReMOVE addresses the challenge of evaluating inpainting without a reference image common in practical scenarios. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity. ReMOVE not only correlates with state-of-the-art metrics and aligns with human perception but also captures the nuanced aspects of the inpainting process providing a finer-grained evaluation of the generated outputs.

3. WACV

   pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation

   Manogna Sreenivas, Goirik Chakrabarty, and Soma Biswas

   In Winter Conference on Applications of Computer Vision, Jun 2024

   Abs Code Website

   Test Time Adaptation (TTA) is a pivotal concept in machine learning, enabling models to perform well in real-world scenarios, where test data distribution differs from training. In this work, we propose a novel approach called pseudo Source guided Target Clustering (pSTarC) addressing the relatively unexplored area of TTA under real-world domain shifts. This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples. The test samples are strategically aligned with these pseudo-source samples, facilitating their clustering and thereby enhancing TTA performance. pSTarC operates solely within the fully test-time adaptation protocol, removing the need for actual source data. Experimental validation on a variety of domain shift datasets, namely VisDA, Office-Home, DomainNet-126, CIFAR-100C verifies pSTarC’s effectiveness. This method exhibits significant improvements in prediction accuracy along with efficient computational requirements. Furthermore, we also demonstrate the universality of the pSTarC framework by showing its effectiveness for the continuous TTA framework.

2023

1. TMLR

   SANTA: Source Anchoring Network and Target Alignment for Continual Test Time Adaptation

   Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas

   In Transactions on Machine Learning Research, Jun 2023

   Abs Code Website

   Adapting a trained model to perform satisfactorily on continually changing test environments is an important and challenging task. In this work, we propose a novel framework, SANTA, which aims to satisfy the following characteristics required for online adaptation: 1) can work effectively for different (even small) batch sizes; 2) should continue to work well on the source domain; 3) should have minimal tunable hyperparameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed framework modifies the affine parameters of the batch normalization layers using source anchoring based self-distillation. This ensures that the model incorporates knowledge from the newly encountered domains, without catastrophically forgetting the previously seen domains. We also propose a source-prototype driven contrastive alignment to ensure natural grouping of the target samples, while maintaining the already learnt semantic information. Extensive evaluation on three benchmark datasets under challenging settings justify the effectiveness of SANTA for real-world applications.

2. ICCVW

   A Simple Signal for Domain Shift

   Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas

   In ICCV Workshops, Jun 2023

   Abs

   Test time domain adaptation has come to the forefront as a challenging scenario in recent times. Although single domain test-time adaptation has been well studied and shown impressive performance, this can be limiting when the model is deployed in a dynamic test environment. We explore this continual domain test time adaptation problem here. Specifically, we question if we can translate the effectiveness of single domain adaptation methods to continuous test-time adaptation scenario. We take a step towards bridging the gap between these two settings by proposing a domain shift detection mechanism and hence allowing us to employ the current test-time adaptation methods even in a continual setting. We propose to use the given source domain trained model to continually measure the similarity between the feature representations of the consecutive batches. A domain shift is detected when this measure crosses a certain threshold, which we use as a trigger to reset the model back to source and continue test-time adaptation. We demonstrate the effectiveness of our method by performing experiments across datasets, batch sizes and different single domain test-time adaptation baselines.

3. ICLRW

   Domain Shift Signal for Low Resource Continuous Test-Time Adaptation

   Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas

   In ICLR Workshops, Jun 2023

   Abs PDF

   Test time domain adaptation has come to the forefront as a challenging scenario in recent times. Although single domain test-time adaptation has been well studied and shown impressive performance, this can be limiting when the model is deployed in a dynamic test environment. We explore this continual domain test time adaptation problem here. Specifically, we question if we can translate the effectiveness of single domain adaptation methods to continuous test-time adaptation scenario. We propose to use the given source domain trained model to continually measure the similarity between the feature representations of the consecutive batches. A domain shift is detected when this measure falls below a certain threshold, which we use as a trigger to reset the model back to source and continue test-time adaptation. We demonstrate the effectiveness of our method by performing experiments across datasets, batch sizes and different single domain test-time adaptation baselines. This can have a significant impact in a variety of applications, from healthcare and agriculture to transportation and finance. As a result, this research has the potential to greatly benefit developing countries by providing new tools and techniques for building more effective and efficient machine learning systems.