Showing 1–50 of 213 results for author: Dutta, A

Cross-Modal Visuo-Tactile Object Perception

Authors: Anirvan Dutta, Simone Tasciotti, Claudia Cusseddu, Ang Li, Panayiota Poirazi, Julijana Gjorgjieva, Etienne Burdet, Patrick van der Smagt, Mohsen Kaboli

Abstract: Estimating physical properties is critical for safe and efficient autonomous robotic manipulation, particularly during contact-rich interactions. In such settings, vision and tactile sensing provide complementary information about object geometry, pose, inertia, stiffness, and contact dynamics, such as stick-slip behavior. However, these properties are only indirectly observable and cannot always… ▽ More Estimating physical properties is critical for safe and efficient autonomous robotic manipulation, particularly during contact-rich interactions. In such settings, vision and tactile sensing provide complementary information about object geometry, pose, inertia, stiffness, and contact dynamics, such as stick-slip behavior. However, these properties are only indirectly observable and cannot always be modeled precisely (e.g., deformation in non-rigid objects coupled with nonlinear contact friction), making the estimation problem inherently complex and requiring sustained exploitation of visuo-tactile sensory information during action. Existing visuo-tactile perception frameworks have primarily emphasized forceful sensor fusion or static cross-modal alignment, with limited consideration of how uncertainty and beliefs about object properties evolve over time. Inspired by human multi-sensory perception and active inference, we propose the Cross-Modal Latent Filter (CMLF) to learn a structured, causal latent state-space of physical object properties. CMLF supports bidirectional transfer of cross-modal priors between vision and touch and integrates sensory evidence through a Bayesian inference process that evolves over time. Real-world robotic experiments demonstrate that CMLF improves the efficiency and robustness of latent physical properties estimation under uncertainty compared to baseline approaches. Beyond performance gains, the model exhibits perceptual coupling phenomena analogous to those observed in humans, including susceptibility to cross-modal illusions and similar trajectories in learning cross-sensory associations. Together, these results constitutes a significant step toward generalizable, robust and physically consistent cross-modal integration for robotic multi-sensory perception. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: 23 pages, 8 figures, 1 table. Submitted for review to journal

VILLA: Versatile Information Retrieval From Scientific Literature Using Large LAnguage Models

Authors: Blessy Antony, Amartya Dutta, Sneha Aggarwal, Vasu Gatne, Ozan Gökdemir, Samantha Grimes, Adam Lauring, Brian R. Wasik, Anuj Karpatne, T. M. Murali

Abstract: The lack of high-quality ground truth datasets to train machine learning (ML) models impedes the potential of artificial intelligence (AI) for science research. Scientific information extraction (SIE) from the literature using LLMs is emerging as a powerful approach to automate the creation of these datasets. However, existing LLM-based approaches and benchmarking studies for SIE focus on broad to… ▽ More The lack of high-quality ground truth datasets to train machine learning (ML) models impedes the potential of artificial intelligence (AI) for science research. Scientific information extraction (SIE) from the literature using LLMs is emerging as a powerful approach to automate the creation of these datasets. However, existing LLM-based approaches and benchmarking studies for SIE focus on broad topics such as biomedicine and chemistry, are limited to choice-based tasks, and focus on extracting information from short and well-formatted text. The potential of SIE methods in complex, open-ended tasks is considerably under-explored. In this study, we used a domain that has been virtually ignored in SIE, namely virology, to address these research gaps. We design a unique, open-ended SIE task of extracting mutations in a given virus that modify its interaction with the host. We develop a new, multi-step retrieval augmented generation (RAG) framework called VILLA for SIE. In parallel, we curate a novel dataset of 629 mutations in ten influenza A virus proteins obtained from 239 scientific publications to serve as ground truth for the mutation extraction task. Finally, we demonstrate VILLA's superior performance using a novel and comprehensive evaluation and comparison with vanilla RAG and other state-of-the art RAG- and agent-based tools for SIE. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Comments: Under review at ACM KDD 2026 (AI for Sciences Track)

FinTradeBench: A Financial Reasoning Benchmark for LLMs

Authors: Yogesh Agrawal, Aniruddha Dutta, Md Mahadi Hasan, Santu Karmaker, Aritra Dutta

Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with the advancement of Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial qu… ▽ More Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with the advancement of Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning over how company stocks trade in the market or their interactions with fundamentals. To take advantage of the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence. △ Less

Submitted 20 March, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

Comments: 8 pages main text, 22 pages total (including references and appendix). 5 figures, 14 tables. Preprint under review. Code and data will be made available upon publication

MSC Class: 68T50 (Primary); 91Gxx (Secondary) ACM Class: I.2.7

Adaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction

Authors: Lin Yang, Anirvan Dutta, Yuan Ji, Yanxin Zhou, Shilin Shan, Lv Chen, Etienne Burdet, Domenico Campolo

Abstract: Achieving human-level dexterity in contact-rich, tool-mediated manipulation remains a significant challenge due to visual occlusion and the underdetermined nature of haptic sensing. This paper introduces a parameterized Equilibrium Manifold (EM) as a unified representation for tool-mediated interaction, and develops a closed-loop framework that integrates haptic estimation, online planning, and ad… ▽ More Achieving human-level dexterity in contact-rich, tool-mediated manipulation remains a significant challenge due to visual occlusion and the underdetermined nature of haptic sensing. This paper introduces a parameterized Equilibrium Manifold (EM) as a unified representation for tool-mediated interaction, and develops a closed-loop framework that integrates haptic estimation, online planning, and adaptive stiffness control. We establish a physical-geometric duality using an adaptive manipulation potential incorporating a differentiable contact model, which induces the manifold's geometric structure and ensures that complex physical interactions are encapsulated as continuous operations on the EM. Within this framework, we reformulate haptic estimation as a manifold parameter estimation problem. Specifically, a hybrid inference strategy (haptic SLAM) is employed in which discrete object shapes are classified via particle filtering, while the continuous object pose is estimated using analytical gradients for efficient optimization. By continuously updating the parameters of the manipulation potential, the framework dynamically reshapes the induced EM to guide online trajectory replanning and implement uncertainty-aware impedance control, thereby closing the perception-action loop. The system is validated through simulation and over 260 real-world screw-loosening trials. Experimental results demonstrate robust identification and manipulation success in standard scenarios while maintaining accurate tracking. Furthermore, ablation studies confirm that haptic SLAM and uncertainty-aware stiffness modulation outperform fixed impedance baselines, effectively preventing jamming during tight tolerance interactions. △ Less

Submitted 10 March, 2026; originally announced March 2026.

PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks

Authors: Uday Bondhugula, Akshay Baviskar, Navdeep Katel, Vimal Patel, Anoop JS, Arnab Dutta

Abstract: We present the design and implementation of PolyBlocks, a modular and reusable MLIR-based compiler infrastructure for AI programming frameworks and AI chips. PolyBlocks is based on pass pipelines that compose transformations on loop nests and SSA, primarily relying on lightweight affine access analysis; the transformations are stitched together in specialized ways to realize high-performance code… ▽ More We present the design and implementation of PolyBlocks, a modular and reusable MLIR-based compiler infrastructure for AI programming frameworks and AI chips. PolyBlocks is based on pass pipelines that compose transformations on loop nests and SSA, primarily relying on lightweight affine access analysis; the transformations are stitched together in specialized ways to realize high-performance code automatically by the use of analytical cost models and heuristics. The optimizations in these passes include multi-level tiling, fusion, on-chip scratchpad usage, mapping matmuls and convolutions to matrix units, fusing the attention layer, and several other transformations for parallelism and locality. They have been developed in a way that makes it easy to build PolyBlocks-based compilers to target new chips, reusing much of the infrastructure. PolyBlocks' design and architecture enable fully automatic code generation from high-level frameworks to low-level target-specific intrinsics. Experimental results from evaluating PolyBlocks-powered just-in-time compilation for PyTorch and JAX targeting NVIDIA GPUs show that it is able to match or outperform Torch Inductor and XLA in several cases, although the latter rely on a combination of vendor libraries and code generation. For individual operators like matmuls and convolutions, PolyBlocks-generated code is competitive with the best vendor-tuned libraries or hand-written kernels. △ Less

Submitted 10 March, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

Comments: Fixed the "Acknowledgments" section that was missing phrases

Characterizing and Predicting Wildfire Evacuation Behavior: A Dual-Stage ML Approach

Authors: Sazzad Bin Bashar Polock, Anandi Dutta, Subasish Das

Abstract: Wildfire evacuation behavior is highly variable and influenced by complex interactions among household resources, preparedness, and situational cues. Using a large-scale MTurk survey of residents in California, Colorado, and Oregon, this study integrates unsupervised and supervised machine learning methods to uncover latent behavioral typologies and predict key evacuation outcomes. Multiple Corres… ▽ More Wildfire evacuation behavior is highly variable and influenced by complex interactions among household resources, preparedness, and situational cues. Using a large-scale MTurk survey of residents in California, Colorado, and Oregon, this study integrates unsupervised and supervised machine learning methods to uncover latent behavioral typologies and predict key evacuation outcomes. Multiple Correspondence Analysis, K-Modes clustering, and Latent Class Analysis reveal consistent subgroups differentiated by vehicle access, disaster planning, technological resources, pet ownership, and residential stability. Complementary supervised models show that transportation mode can be predicted with high reliability from household characteristics, whereas evacuation timing remains difficult to classify due to its dependence on dynamic, real-time fire conditions. These findings advance data-driven understanding of wildfire evacuation behavior and demonstrate how machine learning can support targeted preparedness strategies, resource allocation, and equitable emergency planning. △ Less

Submitted 10 February, 2026; originally announced March 2026.

Comments: This is the author's preprint version of a paper accepted for presentation at SoutheastConn 2026. The final published version will appear in the official conference proceedings. Conference site: https://ieeesoutheastcon.org/

Security at the Border? The Lived Experiences of Refugees and Asylum Seekers in the UK

Authors: Arshia Dutta, Rikke Bjerg Jensen

Abstract: We bring to light how some asylum seekers and refugees arriving in the UK experience border control and wider immigration systems, as well as the impact that these have on their subsequent lives in the UK. We do so through participant observation in a support organisation and interviews with caseworkers, asylum seekers and refugees. Specifically, our findings show how the first meeting with the bo… ▽ More We bring to light how some asylum seekers and refugees arriving in the UK experience border control and wider immigration systems, as well as the impact that these have on their subsequent lives in the UK. We do so through participant observation in a support organisation and interviews with caseworkers, asylum seekers and refugees. Specifically, our findings show how the first meeting with the border, combined with a 'hostile' immigration system, has a longer-term impact on their sense of belonging. Our observations highlight feelings of insecurity, anxiety and uncertainty that accompanied participants' experiences with immigration systems and processes. We contribute to the growing body of HCI scholarship on the tensions between immigration and (security) technology. In so doing, we point to future directions for participatory and collaborative design practices that centre on the lived experiences and everyday security of asylum seekers and refugees. △ Less

Submitted 19 February, 2026; originally announced February 2026.

Comments: To appear at ACM CHI 2026

WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata

Authors: Prasanna Sridhar, Horace Lee, David M. S. Pinto, Andrew Zisserman, Abhishek Dutta

Abstract: In this paper, we present WISE, an open-source audiovisual search engine which integrates a range of multimodal retrieval capabilities into a single, practical tool accessible to users without machine learning expertise. WISE supports natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g. horse) across images and videos; face-based search for… ▽ More In this paper, we present WISE, an open-source audiovisual search engine which integrates a range of multimodal retrieval capabilities into a single, practical tool accessible to users without machine learning expertise. WISE supports natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g. horse) across images and videos; face-based search for specific individuals; audio retrieval of acoustic events using text (e.g. wood creak) or an audio file; search over automatically transcribed speech; and filtering by user-provided metadata. Rich insights can be obtained by combining queries across modalities -- for example, retrieving German trains from a historical archive by applying the object query "train" and the metadata query "Germany", or searching for a face in a place. By employing vector search techniques, WISE can scale to support efficient retrieval over millions of images or thousands of hours of video. Its modular architecture facilitates the integration of new models. WISE can be deployed locally for private or sensitive collections, and has been applied to various real-world use cases. Our code is open-source and available at https://gitlab.com/vgg/wise/wise. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Comments: Software: https://www.robots.ox.ac.uk/~vgg/software/wise/ , Online demos: https://www.robots.ox.ac.uk/~vgg/software/wise/demo/ , Example Queries: https://www.robots.ox.ac.uk/~vgg/software/wise/examples/

ACM Class: H.3.3

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network

Authors: Abhigyan Dutta, Itay Safran, Paul Valiant

Abstract: We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small approximation error with respect to the uniform distribution over the unit hypercube. By further establishing a general reduction from the maximum to the median, our r… ▽ More We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small approximation error with respect to the uniform distribution over the unit hypercube. By further establishing a general reduction from the maximum to the median, our results break a barrier suggested by prior work on the maximum function, which indicated that linear width should require depth growing at least as $\log\log d$ to achieve comparable accuracy. Our construction relies on a multi-stage procedure that iteratively eliminates non-central elements while preserving a candidate set around the median. We overcome obstacles that do not arise for the maximum to yield approximation results that are strictly stronger than those previously known for the maximum itself. △ Less

Submitted 6 February, 2026; originally announced February 2026.

RAIGen: Rare Attribute Identification in Text-to-Image Generative Models

Authors: Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie, Muhammad Awais, Anjan Dutta

Abstract: Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias id… ▽ More Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultural, or stylistic) yet still encoded in model representations. We introduce RAIGen, the first framework, to our knowledge, for un-supervised rare-attribute discovery in diffusion models. RAIGen leverages Matryoshka Sparse Autoencoders and a novel minority metric combining neuron activation frequency with semantic distinctiveness to identify interpretable neurons whose top-activating images reveal underrepresented attributes. Experiments show RAIGen discovers attributes beyond fixed fairness categories in Stable Diffusion, scales to larger models such as SDXL, supports systematic auditing across architectures, and enables targeted amplification of rare attributes during generation. △ Less

Submitted 6 February, 2026; originally announced February 2026.

An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions

Authors: Avik Dutta, Harshit Nigam, Hosein Hasanbeig, Arjun Radhakrishna, Sumit Gulwani

Abstract: We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and correct subtle distortions in table representations. Only when provided with an explicit prior, via a system prompt, do models partially adjust their reasoning strate… ▽ More We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and correct subtle distortions in table representations. Only when provided with an explicit prior, via a system prompt, do models partially adjust their reasoning strategies and correct some distortions, though not consistently or completely. To study this phenomenon, we introduce a small, expert-curated dataset that explicitly evaluates LLMs on table question answering (TQA) tasks requiring an additional error-correction step prior to analysis. Our results reveal systematic differences in how LLMs ingest and interpret tabular information under distortion, with even SoTA models such as GPT-5.2 model exhibiting a drop of minimum 22% accuracy under distortion. These findings raise important questions for future research, particularly regarding when and how models should autonomously decide to realign tabular inputs, analogous to human behavior, without relying on explicit prompts or tabular data pre-processing. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: 4 pages, 1 figure, 1 table

Introducing AI-Driven IoT Energy Management Framework

Authors: Shivani Mruthyunjaya, Anandi Dutta, Kazi Sifatul Islam

Abstract: Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical reliability. The proposal of a holistic framework to establish a foundation for IoT systems with a focus on contextual decision making, proactive adaptation… ▽ More Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical reliability. The proposal of a holistic framework to establish a foundation for IoT systems with a focus on contextual decision making, proactive adaptation, and scalable structure. A structured process for IoT systems with accuracy and interconnected development would support reducing power consumption and support grid stability. This study presents the feasibility of this proposal through the application of each aspect of the framework. This system would have long term forecasting, short term forecasting, anomaly detection, and consideration of qualitative data with any energy management decisions taken. Performance was evaluated on Power Consumption Time Series data to display the direct application of the framework. △ Less

Submitted 29 November, 2025; originally announced December 2025.

Comments: Accepted in IEEE Smart World Congress 2025, Calgary, Canada

Stabilizing Policy Gradient Methods via Reward Profiling

Authors: Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang

Abstract: Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework tha… ▽ More Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments. △ Less

Submitted 24 January, 2026; v1 submitted 20 November, 2025; originally announced November 2025.

What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

Authors: Arka Dutta, Sujan Dutta, Rijul Magu, Soumyajit Datta, Munmun De Choudhury, Ashiqur R. KhudaBukhsh

Abstract: Hallucinations pose a critical challenge to the real-world deployment of large language models (LLMs) in high-stakes domains. In this paper, we present a framework for stress testing factual fidelity in LLMs in the presence of adversarial nudge. Our framework consists of three steps. In the first step, we instruct the LLM to produce sets of truths and lies consistent with the closed domain in ques… ▽ More Hallucinations pose a critical challenge to the real-world deployment of large language models (LLMs) in high-stakes domains. In this paper, we present a framework for stress testing factual fidelity in LLMs in the presence of adversarial nudge. Our framework consists of three steps. In the first step, we instruct the LLM to produce sets of truths and lies consistent with the closed domain in question. In the next step, we instruct the LLM to verify the same set of assertions as truths and lies consistent with the same closed domain. In the final step, we test the robustness of the LLM against the lies generated (and verified) by itself. Our extensive evaluation, conducted using five widely known proprietary LLMs across two closed domains of popular movies and novels, reveals a wide range of susceptibility to adversarial nudges: \texttt{Claude} exhibits strong resilience, \texttt{GPT} and \texttt{Grok} demonstrate moderate resilience, while \texttt{Gemini} and \texttt{DeepSeek} show weak resilience. Considering that a large population is increasingly using LLMs for information seeking, our findings raise alarm. △ Less

Submitted 30 October, 2025; originally announced November 2025.

AI Powered Urban Green Infrastructure Assessment Through Aerial Imagery of an Industrial Township

Authors: Anisha Dutta

Abstract: Accurate assessment of urban canopy coverage is crucial for informed urban planning, effective environmental monitoring, and mitigating the impacts of climate change. Traditional practices often face limitations due to inadequate technical requirements, difficulties in scaling and data processing, and the lack of specialized expertise. This study presents an efficient approach for estimating green… ▽ More Accurate assessment of urban canopy coverage is crucial for informed urban planning, effective environmental monitoring, and mitigating the impacts of climate change. Traditional practices often face limitations due to inadequate technical requirements, difficulties in scaling and data processing, and the lack of specialized expertise. This study presents an efficient approach for estimating green canopy coverage using artificial intelligence, specifically computer vision techniques, applied to aerial imageries. Our proposed methodology utilizes object-based image analysis, based on deep learning algorithms to accurately identify and segment green canopies from high-resolution drone images. This approach allows the user for detailed analysis of urban vegetation, capturing variations in canopy density and understanding spatial distribution. To overcome the computational challenges associated with processing large datasets, it was implemented over a cloud platform utilizing high-performance processors. This infrastructure efficiently manages space complexity and ensures affordable latency, enabling the rapid analysis of vast amounts of drone imageries. Our results demonstrate the effectiveness of this approach in accurately estimating canopy coverage at the city scale, providing valuable insights for urban forestry management of an industrial township. The resultant data generated by this method can be used to optimize tree plantation and assess the carbon sequestration potential of urban forests. By integrating these insights into sustainable urban planning, we can foster more resilient urban environments, contributing to a greener and healthier future. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: Presented at IIIE Conference 2024, Jamshedpur

Development of an Automated Web Application for Efficient Web Scraping: Design and Implementation

Authors: Alok Dutta, Nilanjana Roy, Rhythm Sen, Sougata Dutta, Prabhat Das

Abstract: This paper presents the design and implementation of a user-friendly, automated web application that simplifies and optimizes the web scraping process for non-technical users. The application breaks down the complex task of web scraping into three main stages: fetching, extraction, and execution. In the fetching stage, the application accesses target websites using the HTTP protocol, leveraging th… ▽ More This paper presents the design and implementation of a user-friendly, automated web application that simplifies and optimizes the web scraping process for non-technical users. The application breaks down the complex task of web scraping into three main stages: fetching, extraction, and execution. In the fetching stage, the application accesses target websites using the HTTP protocol, leveraging the requests library to retrieve HTML content. The extraction stage utilizes powerful parsing libraries like BeautifulSoup and regular expressions to extract relevant data from the HTML. Finally, the execution stage structures the data into accessible formats, such as CSV, ensuring the scraped content is organized for easy use. To provide personalized and secure experiences, the application includes user registration and login functionalities, supported by MongoDB, which stores user data and scraping history. Deployed using the Flask framework, the tool offers a scalable, robust environment for web scraping. Users can easily input website URLs, define data extraction parameters, and download the data in a simplified format, without needing technical expertise. This automated tool not only enhances the efficiency of web scraping but also democratizes access to data extraction by empowering users of all technical levels to gather and manage data tailored to their needs. The methodology detailed in this paper represents a significant advancement in making web scraping tools accessible, efficient, and easy to use for a broader audience. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Quantifying Climate Policy Action and Its Links to Development Outcomes: A Cross-National Data-Driven Analysis

Authors: Aditi Dutta

Abstract: Addressing climate change effectively requires more than cataloguing the number of policies in place; it calls for tools that can reveal their thematic priorities and their tangible impacts on development outcomes. Existing assessments often rely on qualitative descriptions or composite indices, which can mask crucial differences between key domains such as mitigation, adaptation, disaster risk ma… ▽ More Addressing climate change effectively requires more than cataloguing the number of policies in place; it calls for tools that can reveal their thematic priorities and their tangible impacts on development outcomes. Existing assessments often rely on qualitative descriptions or composite indices, which can mask crucial differences between key domains such as mitigation, adaptation, disaster risk management, and loss and damage. To bridge this gap, we develop a quantitative indicator of climate policy orientation by applying a multilingual transformer-based language model to official national policy documents, achieving a classification accuracy of 0.90 (F1-score). Linking these indicators with World Bank development data in panel regressions reveals that mitigation policies are associated with higher GDP and GNI; disaster risk management correlates with greater GNI and debt but reduced foreign direct investment; adaptation and loss and damage show limited measurable effects. This integrated NLP-econometric framework enables comparable, theme-specific analysis of climate governance, offering a scalable method to monitor progress, evaluate trade-offs, and align policy emphasis with development goals. △ Less

Submitted 13 November, 2025; v1 submitted 20 October, 2025; originally announced October 2025.

Comments: This paper/proposal has been accepted as a poster in the NeurIPS 2025

ConDABench: Interactive Evaluation of Language Models for Data Analysis

Authors: Avik Dutta, Priyanshu Gupta, Hosein Hasanbeig, Rahul Pratap Singh, Harshit Nigam, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari

Abstract: Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, essential to solving these complex tasks. Existing benchmarks for evaluating LLMs on data analysis tasks do not capture these complexities or provide first-class support for interactivity. We introduce ConDABench, a framewor… ▽ More Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, essential to solving these complex tasks. Existing benchmarks for evaluating LLMs on data analysis tasks do not capture these complexities or provide first-class support for interactivity. We introduce ConDABench, a framework for generating conversational data analysis (ConDA) benchmarks and evaluating external tools on the generated benchmarks. \bench consists of (a) a multi-agent workflow for generating realistic benchmarks from articles describing insights gained from public datasets, (b) 1,420 ConDA problems generated using this workflow, and (c) an evaluation harness that, for the first time, makes it possible to systematically evaluate conversational data analysis tools on the generated ConDA problems. Evaluation of state-of-the-art LLMs on the benchmarks reveals that while the new generation of models are better at solving more instances, they are not necessarily better at solving tasks that require sustained, long-form engagement. ConDABench is an avenue for model builders to measure progress towards truly collaborative models that can complete complex interactive tasks. △ Less

Submitted 10 October, 2025; originally announced October 2025.

Where Have All the Kaczmarz Iterates Gone?

Authors: El Houcine Bergou, Soumia Boucherouite, Aritra Dutta, Xin Li, Anna Ma

Abstract: The randomized Kaczmarz (RK) algorithm is one of the most computationally and memory-efficient iterative algorithms for solving large-scale linear systems. However, practical applications often involve noisy and potentially inconsistent systems. While the convergence of RK is well understood for consistent systems, the study of RK on noisy, inconsistent linear systems is limited. This paper invest… ▽ More The randomized Kaczmarz (RK) algorithm is one of the most computationally and memory-efficient iterative algorithms for solving large-scale linear systems. However, practical applications often involve noisy and potentially inconsistent systems. While the convergence of RK is well understood for consistent systems, the study of RK on noisy, inconsistent linear systems is limited. This paper investigates the asymptotic behavior of RK iterates in expectation when solving noisy and inconsistent systems, addressing the locations of their limit points. We explore the roles of singular vectors of the (noisy) coefficient matrix and derive bounds on the convergence horizon, which depend on the noise levels and system characteristics. Finally, we provide extensive numerical experiments that validate our theoretical findings, offering practical insights into the algorithm's performance under realistic conditions. These results establish a deeper understanding of the RK algorithm's limitations and robustness in noisy environments, paving the way for optimized applications in real-world scientific and engineering problems. △ Less

Submitted 9 October, 2025; originally announced October 2025.

MSC Class: 15A06; 15A09; 15A10; 15A18; 65F10; 65Y20; 68Q25; 68W20; 68W40

TACO-Net: Topological Signatures Triumph in 3D Object Classification

Authors: Anirban Ghosh, Ayan Dutta

Abstract: 3D object classification is a crucial problem due to its significant practical relevance in many fields, including computer vision, robotics, and autonomous driving. Although deep learning methods applied to point clouds sampled on CAD models of the objects and/or captured by LiDAR or RGBD cameras have achieved remarkable success in recent years, achieving high classification accuracy remains a ch… ▽ More 3D object classification is a crucial problem due to its significant practical relevance in many fields, including computer vision, robotics, and autonomous driving. Although deep learning methods applied to point clouds sampled on CAD models of the objects and/or captured by LiDAR or RGBD cameras have achieved remarkable success in recent years, achieving high classification accuracy remains a challenging problem due to the unordered point clouds and their irregularity and noise. To this end, we propose a novel state-of-the-art (SOTA) 3D object classification technique that combines topological data analysis with various image filtration techniques to classify objects when they are represented using point clouds. We transform every point cloud into a voxelized binary 3D image to extract distinguishing topological features. Next, we train a lightweight one-dimensional Convolutional Neural Network (1D CNN) using the extracted feature set from the training dataset. Our framework, TACO-Net, sets a new state-of-the-art by achieving $99.05\%$ and $99.52\%$ accuracy on the widely used synthetic benchmarks ModelNet40 and ModelNet10, and further demonstrates its robustness on the large-scale real-world OmniObject3D dataset. When tested with ten different kinds of corrupted ModelNet40 inputs, the proposed TACO-Net demonstrates strong resiliency overall. △ Less

Submitted 29 September, 2025; originally announced September 2025.

Memory Efficient and Staleness Free Pipeline Parallel DNN Training Framework with Improved Convergence Speed

Authors: Ankita Dutta, Nabendu Chaki, Rajat K. De

Abstract: High resource requirement for Deep Neural Network (DNN) training across multiple GPUs necessitates development of various parallelism techniques. In this paper, we introduce two interconnected DNN training frameworks, namely, V-TiMePReSt and I-TiMePReSt, based on pipeline parallelism, a variant of model parallelism. V-TiMePReSt is a completely staleness-free system which enables the DNNs to be tra… ▽ More High resource requirement for Deep Neural Network (DNN) training across multiple GPUs necessitates development of various parallelism techniques. In this paper, we introduce two interconnected DNN training frameworks, namely, V-TiMePReSt and I-TiMePReSt, based on pipeline parallelism, a variant of model parallelism. V-TiMePReSt is a completely staleness-free system which enables the DNNs to be trained on the latest updated weights in each stage of all forward and backward passes. Developing staleness-aware systems at the expense of weight stashing reduces GPU-memory consumption, however, increases the number of epochs to converge. Thus, we introduce I-TiMePReSt, which is also a staleness-aware system, but not at the expense of weight stashing. It does not rely solely on the stale weights or the latest updated weights. I-TiMePReSt computes an intermediate weight towards the latter and performs backward pass on it. Additionally, we formulate the significance of the stale weights mathematically depending on the degree of staleness. In contrast to V-TiMePReSt, I-TiMePReSt works based on the assumption that stale weights have a significant contribution in training, which can be quantified mathematically based on the degree of staleness, although there are other contributory factors which should not be ignored. Experimental results show that V-TiMePReSt is advantageous over existing models in terms of $1)$ the extent of staleness of the weight parameter values and $2)$ GPU memory efficiency, while I-TiMePReSt is superior in terms of $1)$ removing staleness of the weight parameters without removing weight stashing and $2)$ maintaining the trade-off between GPU memory consumption and convergence speed (number of epochs). △ Less

Submitted 27 September, 2025; originally announced September 2025.

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

Authors: Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, Muhammad Awais, Serge Belongie, Anjan Dutta

Abstract: The rapid advancement of diffusion models has enabled high-fidelity and semantically rich text-to-image generation; however, ensuring fairness and safety remains an open challenge. Existing methods typically improve fairness and safety at the expense of semantic fidelity and image quality. In this work, we propose RespoDiff, a novel framework for responsible text-to-image generation that incorpora… ▽ More The rapid advancement of diffusion models has enabled high-fidelity and semantically rich text-to-image generation; however, ensuring fairness and safety remains an open challenge. Existing methods typically improve fairness and safety at the expense of semantic fidelity and image quality. In this work, we propose RespoDiff, a novel framework for responsible text-to-image generation that incorporates a dual-module transformation on the intermediate bottleneck representations of diffusion models. Our approach introduces two distinct learnable modules: one focused on capturing and enforcing responsible concepts, such as fairness and safety, and the other dedicated to maintaining semantic alignment with neutral prompts. To facilitate the dual learning process, we introduce a novel score-matching objective that enables effective coordination between the modules. Our method outperforms state-of-the-art methods in responsible generation by ensuring semantic alignment while optimizing both objectives without compromising image fidelity. Our approach improves responsible and semantically coherent generation by 20% across diverse, unseen prompts. Moreover, it integrates seamlessly into large-scale models like SDXL, enhancing fairness and safety. Code will be released upon acceptance. △ Less

Submitted 8 October, 2025; v1 submitted 18 September, 2025; originally announced September 2025.

Comments: Accepted at NeurIPS 2025

JU-NLP at Touché: Covert Advertisement in Conversational AI-Generation and Detection Strategies

Authors: Arka Dutta, Agrik Majumdar, Sombrata Biswas, Dipankar Das, Sivaji Bandyopadhyay

Abstract: This paper proposes a comprehensive framework for the generation of covert advertisements within Conversational AI systems, along with robust techniques for their detection. It explores how subtle promotional content can be crafted within AI-generated responses and introduces methods to identify and mitigate such covert advertising strategies. For generation (Sub-Task~1), we propose a novel framew… ▽ More This paper proposes a comprehensive framework for the generation of covert advertisements within Conversational AI systems, along with robust techniques for their detection. It explores how subtle promotional content can be crafted within AI-generated responses and introduces methods to identify and mitigate such covert advertising strategies. For generation (Sub-Task~1), we propose a novel framework that leverages user context and query intent to produce contextually relevant advertisements. We employ advanced prompting strategies and curate paired training data to fine-tune a large language model (LLM) for enhanced stealthiness. For detection (Sub-Task~2), we explore two effective strategies: a fine-tuned CrossEncoder (\texttt{all-mpnet-base-v2}) for direct classification, and a prompt-based reformulation using a fine-tuned \texttt{DeBERTa-v3-base} model. Both approaches rely solely on the response text, ensuring practicality for real-world deployment. Experimental results show high effectiveness in both tasks, achieving a precision of 1.0 and recall of 0.71 for ad generation, and F1-scores ranging from 0.99 to 1.00 for ad detection. These results underscore the potential of our methods to balance persuasive communication with transparency in conversational AI. △ Less

Submitted 12 September, 2025; originally announced September 2025.

CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

Authors: Gaurab Chhetri, Anandi Dutta, Subasish Das

Abstract: The emergence of decentralized social media platforms presents new opportunities and challenges for real-time analysis of public discourse. This study introduces CognitiveSky, an open-source and scalable framework designed for sentiment, emotion, and narrative analysis on Bluesky, a federated Twitter or X.com alternative. By ingesting data through Bluesky's Application Programming Interface (API),… ▽ More The emergence of decentralized social media platforms presents new opportunities and challenges for real-time analysis of public discourse. This study introduces CognitiveSky, an open-source and scalable framework designed for sentiment, emotion, and narrative analysis on Bluesky, a federated Twitter or X.com alternative. By ingesting data through Bluesky's Application Programming Interface (API), CognitiveSky applies transformer-based models to annotate large-scale user-generated content and produces structured and analyzable outputs. These summaries drive a dynamic dashboard that visualizes evolving patterns in emotion, activity, and conversation topics. Built entirely on free-tier infrastructure, CognitiveSky achieves both low operational cost and high accessibility. While demonstrated here for monitoring mental health discourse, its modular design enables applications across domains such as disinformation detection, crisis response, and civic sentiment analysis. By bridging large language models with decentralized networks, CognitiveSky offers a transparent, extensible tool for computational social science in an era of shifting digital ecosystems. △ Less

Submitted 14 September, 2025; originally announced September 2025.

Comments: This is the author's preprint version of a paper accepted for presentation at HICSS 59 (Hawaii International Conference on System Sciences), 2026, Hawaii, USA. The final published version will appear in the official conference proceedings. Conference site: https://hicss.hawaii.edu/

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks

Authors: Jason Gardner, Ayan Dutta, Swapnoneel Roy, O. Patrick Kreidl, Ladislau Boloni

Abstract: The growing computational demands of deep reinforcement learning (DRL) have raised concerns about the environmental and economic costs of training large-scale models. While algorithmic efficiency in terms of learning performance has been extensively studied, the energy requirements, greenhouse gas emissions, and monetary costs of DRL algorithms remain largely unexplored. In this work, we present a… ▽ More The growing computational demands of deep reinforcement learning (DRL) have raised concerns about the environmental and economic costs of training large-scale models. While algorithmic efficiency in terms of learning performance has been extensively studied, the energy requirements, greenhouse gas emissions, and monetary costs of DRL algorithms remain largely unexplored. In this work, we present a systematic benchmarking study of the energy consumption of seven state-of-the-art DRL algorithms, namely DQN, TRPO, A2C, ARS, PPO, RecurrentPPO, and QR-DQN, implemented using Stable Baselines. Each algorithm was trained for one million steps each on ten Atari 2600 games, and power consumption was measured in real-time to estimate total energy usage, CO2-Equivalent emissions, and electricity cost based on the U.S. national average electricity price. Our results reveal substantial variation in energy efficiency and training cost across algorithms, with some achieving comparable performance while consuming up to 24% less energy (ARS vs. DQN), emitting nearly 68% less CO2, and incurring almost 68% lower monetary cost (QR-DQN vs. RecurrentPPO) than less efficient counterparts. We further analyze the trade-offs between learning performance, training time, energy use, and financial cost, highlighting cases where algorithmic choices can mitigate environmental and economic impact without sacrificing learning performance. This study provides actionable insights for developing energy-aware and cost-efficient DRL practices and establishes a foundation for incorporating sustainability considerations into future algorithmic design and evaluation. △ Less

Submitted 5 September, 2025; originally announced September 2025.

Comments: Submitted to a journal - under review

Mentalic Net: Development of RAG-based Conversational AI and Evaluation Framework for Mental Health Support

Authors: Anandi Dutta, Shivani Mruthyunjaya, Jessica Saddington, Kazi Sifatul Islam

Abstract: The emergence of large language models (LLMs) has unlocked boundless possibilities, along with significant challenges. In response, we developed a mental health support chatbot designed to augment professional healthcare, with a strong emphasis on safe and meaningful application. Our approach involved rigorous evaluation, covering accuracy, empathy, trustworthiness, privacy, and bias. We employed… ▽ More The emergence of large language models (LLMs) has unlocked boundless possibilities, along with significant challenges. In response, we developed a mental health support chatbot designed to augment professional healthcare, with a strong emphasis on safe and meaningful application. Our approach involved rigorous evaluation, covering accuracy, empathy, trustworthiness, privacy, and bias. We employed a retrieval-augmented generation (RAG) framework, integrated prompt engineering, and fine-tuned a pre-trained model on novel datasets. The resulting system, Mentalic Net Conversational AI, achieved a BERT Score of 0.898, with other evaluation metrics falling within satisfactory ranges. We advocate for a human-in-the-loop approach and a long-term, responsible strategy in developing such transformative technologies, recognizing both their potential to change lives and the risks they may pose if not carefully managed. △ Less

Submitted 26 August, 2025; originally announced September 2025.

Comments: Preprint Version, Accepted in ISEMV 2025

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering

Authors: Ayan Banerjee, Josep Lladós, Umapada Pal, Anjan Dutta

Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an itera… ▽ More Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an iterative process, maintaining character consistency, and accurate dialogue assignment via postprocessing. Given a story, we use a pre-trained LLM to generate per-frame descriptions, character details, and dialogues via in-context learning, followed by a bounded attention-based per-box mask technique to control character interactions and minimize artifacts. We then apply an identity-consistent self-attention mechanism to ensure character consistency across frames and region-aware cross-attention for precise object placement. Dialogues are also rendered as bubbles and assigned to characters via CLIPSeg. Experimental results demonstrate that TaleDiffusion outperforms existing methods in consistency, noise reduction, and dialogue rendering. △ Less

Submitted 4 September, 2025; originally announced September 2025.

NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

Authors: Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghosal, Somak Aditya

Abstract: Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language fact… ▽ More Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLMs respectively across two commonsense VQA datasets (CRIC, AOKVQA) and a visual-entailment dataset (e-SNLI-VE). Facts retrieved using a fine-tuned ColBERTv2 and an object information-enriched prompt yield explanations that largely cut down hallucinations, while lifting the end-to-end answer accuracy by up to 7% (across 3 datasets), making FLAVA and other models in NLKI match or exceed medium-sized VLMs such as Qwen-2 VL-2B and SmolVLM-2.5B. As these benchmarks contain 10-25% label noise, additional finetuning using noise-robust losses (such as symmetric cross entropy and generalised cross entropy) adds another 2.5% in CRIC, and 5.5% in AOKVQA. Our findings expose when LLM-based commonsense knowledge beats retrieval from commonsense knowledge bases, how noise-aware training stabilises small models in the context of external knowledge augmentation, and why parameter-efficient commonsense reasoning is now within reach for 250M models. △ Less

Submitted 28 August, 2025; v1 submitted 27 August, 2025; originally announced August 2025.

CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance

Authors: Anindya Mondal, Ayan Banerjee, Sauradip Nag, Josep Lladós, Xiatian Zhu, Anjan Dutta

Abstract: Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative, structured feedback. Our method alternates between synthesis and evaluation: a VLM-based planner generates structured scene layouts, while a VLM-based critic provi… ▽ More Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative, structured feedback. Our method alternates between synthesis and evaluation: a VLM-based planner generates structured scene layouts, while a VLM-based critic provides explicit feedback on object counts, spatial arrangements, and visual quality to refine the layout iteratively. Instance-driven attention masking and cumulative attention composition further prevent semantic leakage, ensuring clear object separation even in densely occluded scenes. Evaluations on COCO-Count, T2I-CompBench, and two newly introduced high instance benchmarks show that COUNTLOOP reduces counting error by up to 57% and achieves the highest or comparable spatial quality scores across all benchmarks, while maintaining photorealism. △ Less

Submitted 16 March, 2026; v1 submitted 18 August, 2025; originally announced August 2025.

Towards Source-Free Machine Unlearning

Authors: Sk Miraj Ahmed, Umit Yigit Basaran, Dripta S. Raychaudhuri, Arindam Dutta, Rohit Kundu, Fahim Faisal Niloy, Basak Guler, Amit K. Roy-Chowdhury

Abstract: As machine learning becomes more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasingly critical requirement. Existing unlearning methods often rely on the assumption of having access to the entire training dataset during the forgetting process. However, this assumption may not hold true in practical s… ▽ More As machine learning becomes more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasingly critical requirement. Existing unlearning methods often rely on the assumption of having access to the entire training dataset during the forgetting process. However, this assumption may not hold true in practical scenarios where the original training data may not be accessible, i.e., the source-free setting. To address this challenge, we focus on the source-free unlearning scenario, where an unlearning algorithm must be capable of removing specific data from a trained model without requiring access to the original training dataset. Building on recent work, we present a method that can estimate the Hessian of the unknown remaining training data, a crucial component required for efficient unlearning. Leveraging this estimation technique, our method enables efficient zero-shot unlearning while providing robust theoretical guarantees on the unlearning performance, while maintaining performance on the remaining data. Extensive experiments over a wide range of datasets verify the efficacy of our method. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Comments: Accepted by CVPR 2025

Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse

Authors: Aditi Dutta, Susan Banducci

Abstract: Anti-sexist speech, i.e., public expressions that challenge or resist gendered abuse and sexism, plays a vital role in shaping democratic debate online. Yet automated content moderation systems, increasingly powered by large language models (LLMs), may struggle to distinguish such resistance from the sexism it opposes. This study examines how five LLMs classify sexist, anti-sexist, and neutral pol… ▽ More Anti-sexist speech, i.e., public expressions that challenge or resist gendered abuse and sexism, plays a vital role in shaping democratic debate online. Yet automated content moderation systems, increasingly powered by large language models (LLMs), may struggle to distinguish such resistance from the sexism it opposes. This study examines how five LLMs classify sexist, anti-sexist, and neutral political tweets from the UK, focusing on high-salience trigger events involving female Members of Parliament in the year 2022. Our analysis show that models frequently misclassify anti-sexist speech as harmful, particularly during politically charged events where rhetorical styles of harm and resistance converge. These errors risk silencing those who challenge sexism, with disproportionate consequences for marginalised voices. We argue that moderation design must move beyond binary harmful/not-harmful schemas, integrate human-in-the-loop review during sensitive events, and explicitly include counter-speech in training data. By linking feminist scholarship, event-based analysis, and model evaluation, this work highlights the sociotechnical challenges of safeguarding resistance speech in digital political spaces. △ Less

Submitted 15 August, 2025; originally announced August 2025.

Embodied Tactile Perception of Soft Objects Properties

Authors: Anirvan Dutta, Alexis WM Devillard, Zhihuan Zhang, Xiaoxiao Cheng, Etienne Burdet

Abstract: To enable robots to develop human-like fine manipulation, it is essential to understand how mechanical compliance, multi-modal sensing, and purposeful interaction jointly shape tactile perception. In this study, we use a dedicated modular e-Skin with tunable mechanical compliance and multi-modal sensing (normal, shear forces and vibrations) to systematically investigate how sensing embodiment and… ▽ More To enable robots to develop human-like fine manipulation, it is essential to understand how mechanical compliance, multi-modal sensing, and purposeful interaction jointly shape tactile perception. In this study, we use a dedicated modular e-Skin with tunable mechanical compliance and multi-modal sensing (normal, shear forces and vibrations) to systematically investigate how sensing embodiment and interaction strategies influence robotic perception of objects. Leveraging a curated set of soft wave objects with controlled viscoelastic and surface properties, we explore a rich set of palpation primitives-pressing, precession, sliding that vary indentation depth, frequency, and directionality. In addition, we propose the latent filter, an unsupervised, action-conditioned deep state-space model of the sophisticated interaction dynamics and infer causal mechanical properties into a structured latent space. This provides generalizable and in-depth interpretable representation of how embodiment and interaction determine and influence perception. Our investigation demonstrates that multi-modal sensing outperforms uni-modal sensing. It highlights a nuanced interaction between the environment and mechanical properties of e-Skin, which should be examined alongside the interaction by incorporating temporal dynamics. △ Less

Submitted 13 August, 2025; originally announced August 2025.

VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions

Authors: Yash Garg, Saketh Bachu, Arindam Dutta, Rohit Lal, Sarosij Bose, Calvin-Khang Ta, M. Salman Asif, Amit Roy-Chowdhury

Abstract: Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these methods often struggle in challenging scenarios involving complex human poses or significant occlusions. Although some studies address 3D human pose estimation under occlusion, they typically evaluate performance on dataset… ▽ More Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these methods often struggle in challenging scenarios involving complex human poses or significant occlusions. Although some studies address 3D human pose estimation under occlusion, they typically evaluate performance on datasets that lack realistic or substantial occlusions, e.g., most existing datasets introduce occlusions with random patches over the human or clipart-style overlays, which may not reflect real-world challenges. To bridge this gap in realistic occlusion datasets, we introduce a novel benchmark dataset, VOccl3D, a Video-based human Occlusion dataset with 3D body pose and shape annotations. Inspired by works such as AGORA and BEDLAM, we constructed this dataset using advanced computer graphics rendering techniques, incorporating diverse real-world occlusion scenarios, clothing textures, and human motions. Additionally, we fine-tuned recent HPS methods, CLIFF and BEDLAM-CLIFF, on our dataset, demonstrating significant qualitative and quantitative improvements across multiple public datasets, as well as on the test split of our dataset, while comparing its performance with other state-of-the-art methods. Furthermore, we leveraged our dataset to enhance human detection performance under occlusion by fine-tuning an existing object detector, YOLO11, thus leading to a robust end-to-end HPS estimation system under occlusions. Overall, this dataset serves as a valuable resource for future research aimed at benchmarking methods designed to handle occlusions, offering a more realistic alternative to existing occlusion datasets. See the Project page for code and dataset:https://yashgarg98.github.io/VOccl3D-dataset/ △ Less

Submitted 8 August, 2025; originally announced August 2025.

Journal ref: ICCV 2025

Automating Thematic Review of Prevention of Future Deaths Reports: Replicating the ONS Child Suicide Study using Large Language Models

Authors: Sam Osian, Arpan Dutta, Sahil Bhandari, Iain E. Buchan, Dan W. Joyce

Abstract: Prevention of Future Deaths (PFD) reports, issued by coroners in England and Wales, flag systemic hazards that may lead to further loss of life. Analysis of these reports has previously been constrained by the manual effort required to identify and code relevant cases. In 2025, the Office for National Statistics (ONS) published a national thematic review of child-suicide PFD reports ($\leq$ 18 yea… ▽ More Prevention of Future Deaths (PFD) reports, issued by coroners in England and Wales, flag systemic hazards that may lead to further loss of life. Analysis of these reports has previously been constrained by the manual effort required to identify and code relevant cases. In 2025, the Office for National Statistics (ONS) published a national thematic review of child-suicide PFD reports ($\leq$ 18 years), identifying 37 cases from January 2015 to November 2023 - a process based entirely on manual curation and coding. We evaluated whether a fully automated, open source "text-to-table" language-model pipeline (PFD Toolkit) could reproduce the ONS's identification and thematic analysis of child-suicide PFD reports, and assessed gains in efficiency and reliability. All 4,249 PFD reports published from July 2013 to November 2023 were processed via PFD Toolkit's large language model pipelines. Automated screening identified cases where the coroner attributed death to suicide in individuals aged 18 or younger, and eligible reports were coded for recipient category and 23 concern sub-themes, replicating the ONS coding frame. PFD Toolkit identified 72 child-suicide PFD reports - almost twice the ONS count. Three blinded clinicians adjudicated a stratified sample of 144 reports to validate the child-suicide screening. Against the post-consensus clinical annotations, the LLM-based workflow showed substantial to almost-perfect agreement (Cohen's $κ$ = 0.82, 95% CI: 0.66-0.98, raw agreement = 91%). The end-to-end script runtime was 8m 16s, transforming a process that previously took months into one that can be completed in minutes. This demonstrates that automated LLM analysis can reliably and efficiently replicate manual thematic reviews of coronial data, enabling scalable, reproducible, and timely insights for public health and safety. The PFD Toolkit is openly available for future research. △ Less

Submitted 28 July, 2025; originally announced July 2025.

Comments: 8 pages, 1 figure

The Challenge of Teaching Reasoning to LLMs Without RL or Distillation

Authors: Wei Du, Branislav Kisacanin, George Armstrong, Shubham Toshniwal, Ivan Moshkov, Alexan Ayrapetyan, Sadegh Mahdavi, Dan Zhao, Shizhe Diao, Dragan Masulovic, Marius Stanean, Advaith Avadhanam, Max Wang, Ashmit Dutta, Shitij Govil, Sri Yanamandara, Mihir Tandon, Sriram Ananthakrishnan, Vedant Rathi, David Zhang, Joonseok Kang, Leon Luo, Titu Andreescu, Boris Ginsburg, Igor Gitman

Abstract: Reasoning-capable language models achieve state-of-the-art performance in diverse complex tasks by generating long, explicit Chain-of-Thought (CoT) traces. While recent works show that base models can acquire such reasoning traces via reinforcement learning or distillation from stronger models like DeepSeek-R1, previous works demonstrate that even short CoT prompting without fine-tuning is able to… ▽ More Reasoning-capable language models achieve state-of-the-art performance in diverse complex tasks by generating long, explicit Chain-of-Thought (CoT) traces. While recent works show that base models can acquire such reasoning traces via reinforcement learning or distillation from stronger models like DeepSeek-R1, previous works demonstrate that even short CoT prompting without fine-tuning is able to improve reasoning. We ask whether long CoT can be induced in a base model using only prompting or minimal tuning. Using just 20 long CoT examples from the reasoning model \texttt{QwQ-32B-Preview}, we lightly fine-tune the base model \texttt{Qwen2.5-32B}. The resulting model outperforms the much larger \texttt{Qwen2.5-Math-72B-Instruct}, showing that a handful of high-quality examples can unlock strong reasoning capabilities. We further explore using CoT data from non-reasoning models and human annotators, enhanced with prompt engineering, multi-pass editing, and structural guidance. However, neither matches the performance of reasoning model traces, suggesting that certain latent qualities of expert CoT are difficult to replicate. We analyze key properties of reasoning data, such as problem difficulty, diversity, and answer length, that influence reasoning distillation. While challenges remain, we are optimistic that carefully curated human-written CoT, even in small quantities, can activate reasoning behaviors in base models. We release our human-authored dataset across refinement stages and invite further investigation into what makes small-scale reasoning supervision so effective. △ Less

Submitted 16 July, 2025; v1 submitted 13 July, 2025; originally announced July 2025.

Comments: Accepted at the Second AI for Math Workshop at the 42nd International Conference on Machine Learning (ICML 2025)

A Language-Driven Framework for Improving Personalized Recommendations: Merging LLMs with Traditional Algorithms

Authors: Aaron Goldstein, Ayan Dutta

Abstract: Traditional recommendation algorithms are not designed to provide personalized recommendations based on user preferences provided through text, e.g., "I enjoy light-hearted comedies with a lot of humor". Large Language Models (LLMs) have emerged as one of the most promising tools for natural language processing in recent years. This research proposes a novel framework that mimics how a close frien… ▽ More Traditional recommendation algorithms are not designed to provide personalized recommendations based on user preferences provided through text, e.g., "I enjoy light-hearted comedies with a lot of humor". Large Language Models (LLMs) have emerged as one of the most promising tools for natural language processing in recent years. This research proposes a novel framework that mimics how a close friend would recommend items based on their knowledge of an individual's tastes. We leverage LLMs to enhance movie recommendation systems by refining traditional algorithm outputs and integrating them with language-based user preference inputs. We employ Singular Value Decomposition (SVD) or SVD++ algorithms to generate initial movie recommendations, implemented using the Surprise Python library and trained on the MovieLens-Latest-Small dataset. We compare the performance of the base algorithms with our LLM-enhanced versions using leave-one-out validation hit rates and cumulative hit rates. Additionally, to compare the performance of our framework against the current state-of-the-art recommendation systems, we use rating and ranking metrics with an item-based stratified 0.75 train, 0.25 test split. Our framework can generate preference profiles automatically based on users' favorite movies or allow manual preference specification for more personalized results. Using an automated approach, our framework overwhelmingly surpassed SVD and SVD++ on every evaluation metric used (e.g., improvements of up to ~6x in cumulative hit rate, ~3.7x in NDCG, etc.), albeit at the cost of a slight increase in computational overhead. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Bounomodes: the grazing ox algorithm for exploration of clustered anomalies

Authors: Samuel Matloob, Ayan Dutta, O. Patrick Kreidl, Swapnonel Roy, Ladislau Bölöni

Abstract: A common class of algorithms for informative path planning (IPP) follows boustrophedon ("as the ox turns") patterns, which aim to achieve uniform area coverage. However, IPP is often applied in scenarios where anomalies, such as plant diseases, pollution, or hurricane damage, appear in clusters. In such cases, prioritizing the exploration of anomalous regions over uniform coverage is beneficial. T… ▽ More A common class of algorithms for informative path planning (IPP) follows boustrophedon ("as the ox turns") patterns, which aim to achieve uniform area coverage. However, IPP is often applied in scenarios where anomalies, such as plant diseases, pollution, or hurricane damage, appear in clusters. In such cases, prioritizing the exploration of anomalous regions over uniform coverage is beneficial. This work introduces a class of algorithms referred to as bounomōdes ("as the ox grazes"), which alternates between uniform boustrophedon sampling and targeted exploration of detected anomaly clusters. While uniform sampling can be designed using geometric principles, close exploration of clusters depends on the spatial distribution of anomalies and must be learned. In our implementation, the close exploration behavior is learned using deep reinforcement learning algorithms. Experimental evaluations demonstrate that the proposed approach outperforms several established baselines. △ Less

Submitted 9 July, 2025; originally announced July 2025.

From Tiny Machine Learning to Tiny Deep Learning: A Survey

Authors: Shriyank Somvanshi, Md Monzurul Islam, Gaurab Chhetri, Rohit Chakraborty, Mahmuda Sultana Mimi, Sawgat Ahmed Shuvo, Kazi Sifatul Islam, Syed Aaqib Javed, Sharif Ahmed Rafat, Anandi Dutta, Subasish Das

Abstract: The rapid growth of edge devices has driven the demand for deploying artificial intelligence (AI) at the edge, giving rise to Tiny Machine Learning (TinyML) and its evolving counterpart, Tiny Deep Learning (TinyDL). While TinyML initially focused on enabling simple inference tasks on microcontrollers, the emergence of TinyDL marks a paradigm shift toward deploying deep learning models on severely… ▽ More The rapid growth of edge devices has driven the demand for deploying artificial intelligence (AI) at the edge, giving rise to Tiny Machine Learning (TinyML) and its evolving counterpart, Tiny Deep Learning (TinyDL). While TinyML initially focused on enabling simple inference tasks on microcontrollers, the emergence of TinyDL marks a paradigm shift toward deploying deep learning models on severely resource-constrained hardware. This survey presents a comprehensive overview of the transition from TinyML to TinyDL, encompassing architectural innovations, hardware platforms, model optimization techniques, and software toolchains. We analyze state-of-the-art methods in quantization, pruning, and neural architecture search (NAS), and examine hardware trends from MCUs to dedicated neural accelerators. Furthermore, we categorize software deployment frameworks, compilers, and AutoML tools enabling practical on-device learning. Applications across domains such as computer vision, audio recognition, healthcare, and industrial monitoring are reviewed to illustrate the real-world impact of TinyDL. Finally, we identify emerging directions including neuromorphic computing, federated TinyDL, edge-native foundation models, and domain-specific co-design approaches. This survey aims to serve as a foundational resource for researchers and practitioners, offering a holistic view of the ecosystem and laying the groundwork for future advancements in edge AI. △ Less

Submitted 25 June, 2025; v1 submitted 21 June, 2025; originally announced June 2025.

Journal ref: ACM CS 2025

TopoRec: Point Cloud Recognition Using Topological Data Analysis

Authors: Anirban Ghosh, Iliya Kulbaka, Ian Dahlin, Ayan Dutta

Abstract: Point cloud-based object/place recognition remains a problem of interest in applications such as autonomous driving, scene reconstruction, and localization. Extracting a meaningful global descriptor from a query point cloud that can be matched with the descriptors of the database point clouds is a challenging problem. Furthermore, when the query point cloud is noisy or has been transformed (e.g.,… ▽ More Point cloud-based object/place recognition remains a problem of interest in applications such as autonomous driving, scene reconstruction, and localization. Extracting a meaningful global descriptor from a query point cloud that can be matched with the descriptors of the database point clouds is a challenging problem. Furthermore, when the query point cloud is noisy or has been transformed (e.g., rotated), it adds to the complexity. To this end, we propose a novel methodology, named TopoRec, which utilizes Topological Data Analysis (TDA) for extracting local descriptors from a point cloud, thereby eliminating the need for resource-intensive GPU-based machine learning training. More specifically, we used the ATOL vectorization method to generate vectors for point clouds. To test the quality of the proposed TopoRec technique, we have implemented it on multiple real-world (e.g., Oxford RobotCar, NCLT) and realistic (e.g., ShapeNet) point cloud datasets for large-scale place and object recognition, respectively. Unlike existing learning-based approaches such as PointNetVLAD and PCAN, our method does not require extensive training, making it easily adaptable to new environments. Despite this, it consistently outperforms both state-of-the-art learning-based and handcrafted baselines (e.g., M2DP, ScanContext) on standard benchmark datasets, demonstrating superior accuracy and strong generalization. △ Less

Submitted 31 July, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Intelligent Image Sensing for Crime Analysis: A ML Approach towards Enhanced Violence Detection and Investigation

Authors: Aritra Dutta, Pushpita Boral, G Suseela

Abstract: The increasing global crime rate, coupled with substantial human and property losses, highlights the limitations of traditional surveillance methods in promptly detecting diverse and unexpected acts of violence. Addressing this pressing need for automatic violence detection, we leverage Machine Learning to detect and categorize violent events in video streams. This paper introduces a comprehensive… ▽ More The increasing global crime rate, coupled with substantial human and property losses, highlights the limitations of traditional surveillance methods in promptly detecting diverse and unexpected acts of violence. Addressing this pressing need for automatic violence detection, we leverage Machine Learning to detect and categorize violent events in video streams. This paper introduces a comprehensive framework for violence detection and classification, employing Supervised Learning for both binary and multi-class violence classification. The detection model relies on 3D Convolutional Neural Networks, while the classification model utilizes the separable convolutional 3D model for feature extraction and bidirectional LSTM for temporal processing. Training is conducted on a diverse customized datasets with frame-level annotations, incorporating videos from surveillance cameras, human recordings, hockey fight, sohas and wvd dataset across various platforms. Additionally, a camera module integrated with raspberry pi is used to capture live video feed, which is sent to the ML model for processing. Thus, demonstrating improved performance in terms of computational resource efficiency and accuracy. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Open World Scene Graph Generation using Vision Language Models

Authors: Amartya Dutta, Kazi Sajeed Mehrab, Medha Sawhney, Abhilash Neog, Mridul Khurana, Sepideh Fatemi, Aanish Pradhan, M. Maruf, Ismini Lourentzou, Arka Daw, Anuj Karpatne

Abstract: Scene-Graph Generation (SGG) seeks to recognize objects in an image and distill their salient pairwise relationships. Most methods depend on dataset-specific supervision to learn the variety of interactions, restricting their usefulness in open-world settings, involving novel objects and/or relations. Even methods that leverage large Vision Language Models (VLMs) typically require benchmark-specif… ▽ More Scene-Graph Generation (SGG) seeks to recognize objects in an image and distill their salient pairwise relationships. Most methods depend on dataset-specific supervision to learn the variety of interactions, restricting their usefulness in open-world settings, involving novel objects and/or relations. Even methods that leverage large Vision Language Models (VLMs) typically require benchmark-specific fine-tuning. We introduce Open-World SGG, a training-free, efficient, model-agnostic framework that taps directly into the pretrained knowledge of VLMs to produce scene graphs with zero additional learning. Casting SGG as a zero-shot structured-reasoning problem, our method combines multimodal prompting, embedding alignment, and a lightweight pair-refinement strategy, enabling inference over unseen object vocabularies and relation sets. To assess this setting, we formalize an Open-World evaluation protocol that measures performance when no SGG-specific data have been observed either in terms of objects and relations. Experiments on Visual Genome, Open Images V6, and the Panoptic Scene Graph (PSG) dataset demonstrate the capacity of pretrained VLMs to perform relational understanding without task-level training. △ Less

Submitted 9 June, 2025; originally announced June 2025.

Comments: Accepted in CVPR 2025 Workshop (CVinW)

Beyond the Buzz: A Pragmatic Take on Inference Disaggregation

Authors: Tiyasa Mitra, Ritika Borkar, Nidhi Bhatia, Ramon Matas, Shivam Raj, Dheevatsa Mudigere, Ritchie Zhao, Maximilian Golub, Arpan Dutta, Sailaja Madduri, Dharmesh Jani, Brian Pharris, Bita Darvish Rouhani

Abstract: As inference scales to multi-node deployments, disaggregation - splitting inference into distinct phases - offers a promising path to improving the throughput-interactivity Pareto frontier. Despite growing enthusiasm and a surge of open-source efforts, practical deployment of disaggregated serving remains limited due to the complexity of the optimization search space and system-level coordination.… ▽ More As inference scales to multi-node deployments, disaggregation - splitting inference into distinct phases - offers a promising path to improving the throughput-interactivity Pareto frontier. Despite growing enthusiasm and a surge of open-source efforts, practical deployment of disaggregated serving remains limited due to the complexity of the optimization search space and system-level coordination. In this paper, we present the first systematic study of disaggregated inference at scale, evaluating hundreds of thousands of design points across diverse workloads and hardware configurations. We find that disaggregation is most effective for prefill-heavy traffic patterns and larger models. Our results highlight the critical role of dynamic rate matching and elastic scaling in achieving Pareto-optimal performance. Our findings offer actionable insights for efficient disaggregated deployments to navigate the trade-off between system throughput and interactivity. △ Less

Submitted 5 June, 2025; originally announced June 2025.

A Review on Influx of Bio-Inspired Algorithms: Critique and Improvement Needs

Authors: Shriyank Somvanshi, Md Monzurul Islam, Syed Aaqib Javed, Gaurab Chhetri, Kazi Sifatul Islam, Tausif Islam Chowdhury, Sazzad Bin Bashar Polock, Anandi Dutta, Subasish Das

Abstract: Bio-inspired algorithms utilize natural processes such as evolution, swarm behavior, foraging, and plant growth to solve complex, nonlinear, high-dimensional optimization problems. However, a plethora of these algorithms require a more rigorous review before making them applicable to the relevant fields. This survey categorizes these algorithms into eight groups: evolutionary, swarm intelligence,… ▽ More Bio-inspired algorithms utilize natural processes such as evolution, swarm behavior, foraging, and plant growth to solve complex, nonlinear, high-dimensional optimization problems. However, a plethora of these algorithms require a more rigorous review before making them applicable to the relevant fields. This survey categorizes these algorithms into eight groups: evolutionary, swarm intelligence, physics-inspired, ecosystem and plant-based, predator-prey, neural-inspired, human-inspired, and hybrid approaches, and reviews their principles, strengths, novelty, and critical limitations. We provide a critique on the novelty issues of many of these algorithms. We illustrate some of the suitable usage of the prominent algorithms in machine learning, engineering design, bioinformatics, and intelligent systems, and highlight recent advances in hybridization, parameter tuning, and adaptive strategies. Finally, we identify open challenges such as scalability, convergence, reliability, and interpretability to suggest directions for future research. This work aims to serve as a resource for both researchers and practitioners interested in understanding the current landscape and future directions of reliable and authentic advancement of bio-inspired algorithms. △ Less

Submitted 15 September, 2025; v1 submitted 25 May, 2025; originally announced June 2025.

Applying MambaAttention, TabPFN, and TabTransformers to Classify SAE Automation Levels in Crashes

Authors: Shriyank Somvanshi, Anannya Ghosh Tusti, Mahmuda Sultana Mimi, Md Monzurul Islam, Sazzad Bin Bashar Polock, Anandi Dutta, Subasish Das

Abstract: The increasing presence of automated vehicles (AVs) presents new challenges for crash classification and safety analysis. Accurately identifying the SAE automation level involved in each crash is essential to understanding crash dynamics and system accountability. However, existing approaches often overlook automation-specific factors and lack model sophistication to capture distinctions between d… ▽ More The increasing presence of automated vehicles (AVs) presents new challenges for crash classification and safety analysis. Accurately identifying the SAE automation level involved in each crash is essential to understanding crash dynamics and system accountability. However, existing approaches often overlook automation-specific factors and lack model sophistication to capture distinctions between different SAE levels. To address this gap, this study evaluates the performance of three advanced tabular deep learning models MambaAttention, TabPFN, and TabTransformer for classifying SAE automation levels using structured crash data from Texas (2024), covering 4,649 cases categorized as Assisted Driving (SAE Level 1), Partial Automation (SAE Level 2), and Advanced Automation (SAE Levels 3-5 combined). Following class balancing using SMOTEENN, the models were trained and evaluated on a unified dataset of 7,300 records. MambaAttention demonstrated the highest overall performance (F1-scores: 88% for SAE 1, 97% for SAE 2, and 99% for SAE 3-5), while TabPFN excelled in zero-shot inference with high robustness for rare crash categories. In contrast, TabTransformer underperformed, particularly in detecting Partial Automation crashes (F1-score: 55%), suggesting challenges in modeling shared human-system control dynamics. These results highlight the capability of deep learning models tailored for tabular data to enhance the accuracy and efficiency of automation-level classification. Integrating such models into crash analysis frameworks can support policy development, AV safety evaluation, and regulatory decisions, especially in distinguishing high-risk conditions for mid- and high-level automation technologies. △ Less

Submitted 22 May, 2025; originally announced June 2025.

A Closer Look at Multimodal Representation Collapse

Authors: Abhra Chaudhuri, Anjan Dutta, Tu Bui, Serban Georgescu

Abstract: We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that modality collapse happens when noisy features from one modality are entangled, via a shared set of neurons in the fusion head, with predictive features from another,… ▽ More We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that modality collapse happens when noisy features from one modality are entangled, via a shared set of neurons in the fusion head, with predictive features from another, effectively masking out positive contributions from the predictive features of the former modality and leading to its collapse. We further prove that cross-modal knowledge distillation implicitly disentangles such representations by freeing up rank bottlenecks in the student encoder, denoising the fusion-head outputs without negatively impacting the predictive features from either modality. Based on the above findings, we propose an algorithm that prevents modality collapse through explicit basis reallocation, with applications in dealing with missing modalities. Extensive experiments on multiple multimodal benchmarks validate our theoretical claims. Project page: https://abhrac.github.io/mmcollapse/. △ Less

Submitted 14 August, 2025; v1 submitted 28 May, 2025; originally announced May 2025.

Comments: International Conference on Machine Learning (ICML) 2025 (Spotlight)

Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups

Authors: Rijul Magu, Arka Dutta, Sean Kim, Ashiqur R. KhudaBukhsh, Munmun De Choudhury

Abstract: Large Language Models (LLMs) have been shown to demonstrate imbalanced biases against certain groups. However, the study of unprovoked targeted attacks by LLMs towards at-risk populations remains underexplored. Our paper presents three novel contributions: (1) the explicit evaluation of LLM-generated attacks on highly vulnerable mental health groups; (2) a network-based framework to study the prop… ▽ More Large Language Models (LLMs) have been shown to demonstrate imbalanced biases against certain groups. However, the study of unprovoked targeted attacks by LLMs towards at-risk populations remains underexplored. Our paper presents three novel contributions: (1) the explicit evaluation of LLM-generated attacks on highly vulnerable mental health groups; (2) a network-based framework to study the propagation of relative biases; and (3) an assessment of the relative degree of stigmatization that emerges from these attacks. Our analysis of a recently released large-scale bias audit dataset reveals that mental health entities occupy central positions within attack narrative networks, as revealed by a significantly higher mean centrality of closeness (p-value = 4.06e-10) and dense clustering (Gini coefficient = 0.7). Drawing from an established stigmatization framework, our analysis indicates increased labeling components for mental health disorder-related targets relative to initial targets in generation chains. Taken together, these insights shed light on the structural predilections of large language models to heighten harmful discourse and highlight the need for suitable approaches for mitigation. △ Less

Submitted 28 January, 2026; v1 submitted 8 April, 2025; originally announced April 2025.

ACM Class: J.4; K.4.1; K.4.2

Journal ref: Second Conference on Language Modeling (COLM 2025)

Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation

Authors: Sarosij Bose, Hannah Dela Cruz, Arindam Dutta, Elena Kokkoni, Konstantinos Karydis, Amit K. Roy-Chowdhury

Abstract: Human pose estimation is a critical tool across a variety of healthcare applications. Despite significant progress in pose estimation algorithms targeting adults, such developments for infants remain limited. Existing algorithms for infant pose estimation, despite achieving commendable performance, depend on fully supervised approaches that require large amounts of labeled data. These algorithms a… ▽ More Human pose estimation is a critical tool across a variety of healthcare applications. Despite significant progress in pose estimation algorithms targeting adults, such developments for infants remain limited. Existing algorithms for infant pose estimation, despite achieving commendable performance, depend on fully supervised approaches that require large amounts of labeled data. These algorithms also struggle with poor generalizability under distribution shifts. To address these challenges, we introduce SHIFT: Leveraging SyntHetic Adult Datasets for Unsupervised InFanT Pose Estimation, which leverages the pseudo-labeling-based Mean-Teacher framework to compensate for the lack of labeled data and addresses distribution shifts by enforcing consistency between the student and the teacher pseudo-labels. Additionally, to penalize implausible predictions obtained from the mean-teacher framework, we incorporate an infant manifold pose prior. To enhance SHIFT's self-occlusion perception ability, we propose a novel visibility consistency module for improved alignment of the predicted poses with the original image. Extensive experiments on multiple benchmarks show that SHIFT significantly outperforms existing state-of-the-art unsupervised domain adaptation (UDA) pose estimation methods by 5% and supervised infant pose estimation methods by a margin of 16%. The project page is available at: https://sarosijbose.github.io/SHIFT. △ Less

Submitted 8 April, 2025; originally announced April 2025.

Comments: Accepted at ABAW@CVPR 2025

GAEA: A Geolocation Aware Conversational Assistant

Authors: Ron Campos, Ashmal Vayani, Parth Parag Kulkarni, Rohit Gupta, Aizan Zafar, Aritra Dutta, Mubarak Shah

Abstract: Image geolocalization, in which an AI model traditionally predicts the precise GPS coordinates of an image, is a challenging task with many downstream applications. However, the user cannot utilize the model to further their knowledge beyond the GPS coordinates; the model lacks an understanding of the location and the conversational ability to communicate with the user. In recent days, with the tr… ▽ More Image geolocalization, in which an AI model traditionally predicts the precise GPS coordinates of an image, is a challenging task with many downstream applications. However, the user cannot utilize the model to further their knowledge beyond the GPS coordinates; the model lacks an understanding of the location and the conversational ability to communicate with the user. In recent days, with the tremendous progress of large multimodal models (LMMs) -- proprietary and open-source -- researchers have attempted to geolocalize images via LMMs. However, the issues remain unaddressed; beyond general tasks, for more specialized downstream tasks, such as geolocalization, LMMs struggle. In this work, we propose solving this problem by introducing a conversational model, GAEA, that provides information regarding the location of an image as the user requires. No large-scale dataset enabling the training of such a model exists. Thus, we propose GAEA-1.4M, a comprehensive dataset comprising over 800k images and approximately 1.4M question-answer pairs, constructed by leveraging OpenStreetMap (OSM) attributes and geographical context clues. For quantitative evaluation, we propose a diverse benchmark, GAEA-Bench, comprising 3.5k image-text pairs to evaluate conversational capabilities equipped with diverse question types. We consider 11 state-of-the-art open-source and proprietary LMMs and demonstrate that GAEA significantly outperforms the best open-source model, LLaVA-OneVision, by 18.2% and the best proprietary model, GPT-4o, by 7.2%. Our dataset, model and codes are available. △ Less

Submitted 2 September, 2025; v1 submitted 20 March, 2025; originally announced March 2025.

Comments: The dataset and code used in this submission is available at: https://ucf-crcv.github.io/GAEA/

ACM Class: I.4; I.2.7; I.5

Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes

Authors: Sarosij Bose, Arindam Dutta, Sayak Nag, Junge Zhang, Jiachen Li, Konstantinos Karydis, Amit K. Roy Chowdhury

Abstract: Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered from novel camera views, existing single image to 3D reconstruction methods render incoherent and blurry views. This problem is exacerbated when the unseen regions are far away from the input camera. In this work, we ad… ▽ More Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered from novel camera views, existing single image to 3D reconstruction methods render incoherent and blurry views. This problem is exacerbated when the unseen regions are far away from the input camera. In this work, we address these inherent limitations in existing single image-to-3D scene feedforward networks. To alleviate the poor performance due to insufficient information beyond the input image's view, we leverage a strong generative prior in the form of a pre-trained latent video diffusion model, for iterative refinement of a coarse scene represented by optimizable Gaussian parameters. To ensure that the style and texture of the generated images align with that of the input image, we incorporate on-the-fly Fourier-style transfer between the generated images and the input image. Additionally, we design a semantic uncertainty quantification module that calculates the per-pixel entropy and yields uncertainty maps used to guide the refinement process from the most confident pixels while discarding the remaining highly uncertain ones. We conduct extensive experiments on real-world scene datasets, including in-domain RealEstate-10K and out-of-domain KITTI-v2, showing that our approach can provide more realistic and high-fidelity novel view synthesis results compared to existing state-of-the-art methods. △ Less

Submitted 8 October, 2025; v1 submitted 19 March, 2025; originally announced March 2025.

Comments: ICCV 2025

CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image

Authors: Arindam Dutta, Meng Zheng, Zhongpai Gao, Benjamin Planche, Anwesha Choudhuri, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu

Abstract: Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction solutions have shown promising results, they often rely on the assumption that the human subject is in an occlusion-free environment. Thus, when encountering in-the-wild occluded images, these algorithms produce multivie… ▽ More Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction solutions have shown promising results, they often rely on the assumption that the human subject is in an occlusion-free environment. Thus, when encountering in-the-wild occluded images, these algorithms produce multiview inconsistent and fragmented reconstructions. Additionally, most algorithms for monocular 3D human reconstruction leverage geometric priors such as SMPL annotations for training and inference, which are extremely challenging to acquire in real-world applications. To address these limitations, we propose CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-ConsistEncy from a Single Image, a novel pipeline designed to reconstruct occlusion-resilient 3D humans with multiview consistency from a single occluded image, without requiring either ground-truth geometric prior annotations or 3D supervision. Specifically, CHROME leverages a multiview diffusion model to first synthesize occlusion-free human images from the occluded input, compatible with off-the-shelf pose control to explicitly enforce cross-view consistency during synthesis. A 3D reconstruction model is then trained to predict a set of 3D Gaussians conditioned on both the occluded input and synthesized views, aligning cross-view details to produce a cohesive and accurate 3D representation. CHROME achieves significant improvements in terms of both novel view synthesis (upto 3 db PSNR) and geometric reconstruction under challenging conditions. △ Less

Submitted 17 October, 2025; v1 submitted 19 March, 2025; originally announced March 2025.

Comments: Accepted at ICCV 2025