Showing 1–50 of 99 results for author: Maiti, A

Jais 2: A Family of Arabic-Centric Open Large Language Models

Authors: Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim, Mostafa Awad, Abdelrahman Sadallah, Gurpreet Gosal, Gokulakrishnan Ramakrishnan, Sarath Chandran, Biswajit Mishra, Rituraj Joshi, Ahmed Frikha, Etienne Goffinet, Abhishek Maiti, Ali El Filali, Sarah AlBarri, Samujjwal Ghosh, Rahul Pal, Parvez Mullah, Awantika Shukla, Sajid siddiki, Samta Kamboj, Onkar Pandit, Sunil Kumar Sahu, AbdelRahman Elbadawy, Amr Mohamed , et al. (35 additional authors not shown)

Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competiti… ▽ More Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive English results. The models obtain leading results among the evaluated open models on OALL2 and AraGen. They also perform strongly on several culturally grounded Arabic benchmarks, including poetry, religion, cuisine, and dream interpretation, as well as in general tasks such as translation and summarization. We release the models in HuggingFace under a commercially permissive license. Jais 2 70B is also released as a chat app on the Web, iOS, and Android; it runs on Cerebras hardware, delivering up to 2,000 tokens per second, and enabling high-throughput Arabic-centric chat serving in our deployment setting. By uniting scale, linguistic diversity, cultural fidelity, openness, and speed, Jais 2 provides an open-weight foundation intended to support further research and development in Arabic-centric LLMs. △ Less

Submitted 7 July, 2026; originally announced August 2026.

The Surplus Parking Gathering Problem in Infinite Grids

Authors: Animesh Maiti, Abhinav Chakraborty, Subhash Bhagat

Abstract: In this paper, we introduce the \emph{Surplus Parking Gathering Problem} ($\mathcal{SPG}$), a new coordination problem for robots deployed on an infinite grid. The input consists of a set of designated parking nodes, each associated with a prescribed capacity, while the total number of robots exceeds the total parking capacity. The objective is to saturate every parking node exactly according to i… ▽ More In this paper, we introduce the \emph{Surplus Parking Gathering Problem} ($\mathcal{SPG}$), a new coordination problem for robots deployed on an infinite grid. The input consists of a set of designated parking nodes, each associated with a prescribed capacity, while the total number of robots exceeds the total parking capacity. The objective is to saturate every parking node exactly according to its capacity while gathering all remaining surplus robots at a common grid node that is not specified a priori. The robots are assumed to be autonomous, anonymous, oblivious, identical, disoriented, and homogeneous. We consider the asynchronous (\textsc{async}) model with global visibility and global strong multiplicity detection. We first establish necessary conditions for the solvability of $\mathcal{SPG}$ by characterizing the initial configurations that admit no deterministic distributed algorithm. For all the remaining solvable configurations, we present a deterministic distributed algorithm that correctly solves the problem. The proposed algorithm proceeds in several phases and avoids collisions throughout its execution. We prove that the algorithm terminates in finite time and, upon termination, every parking node is saturated according to its prescribed capacity while all surplus robots are gathered at a uniquely determined gathering node. We further analyze the move complexity of the proposed algorithm, obtaining an $O(n(a+b)+n^2)$ upper bound together with an $Ω(n(a+b))$ worst-case lower bound for the $\mathcal{SPG}$ problem. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Neural Machine Translation for Low-Resource Tangkhul--English

Authors: Chormi Zimik Vashai, Agniva Maiti

Abstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, a… ▽ More We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, and (2) a contrastive system based on mT5-small fine-tuned on the same corpus. Our primary ByT5-large system achieves a corpus BLEU score of 39.97, chrF++ of 58.07, BERTScore F1 of 0.8104, and COMET (wmt22-comet-da) of 0.7302 on a held-out test set of 3,856 sentences. We further discuss the orthographic challenges specific to Tangkhul's Latin-script diacritics, the domain bias of our training corpus (which comprises biblical text, stories, and conversational data), and avenues for future improvement through data diversification and domain adaptation. △ Less

Submitted 25 July, 2026; v1 submitted 23 June, 2026; originally announced June 2026.

Comments: 11 pages, 3 figures, 9 tables

Block-A-Mole: The Sustainability Frontier of Moving-Target Censorship Resistance

Authors: Anindya Maiti

Abstract: Internet censorship affects over four billion people, and deployed circumvention systems share a common weakness: their endpoints are fixed and discoverable, so a patient censor can enumerate and block them. Moving-target circumvention systems instead rotate endpoints across commercial cloud address space faster than censors can react, but the field lacks a theory of when rotation works, leaving r… ▽ More Internet censorship affects over four billion people, and deployed circumvention systems share a common weakness: their endpoints are fixed and discoverable, so a patient censor can enumerate and block them. Moving-target circumvention systems instead rotate endpoints across commercial cloud address space faster than censors can react, but the field lacks a theory of when rotation works, leaving rotation intervals and pool sizes to intuition. We give the first formal account of moving-target censorship resistance by modeling the censor-defender interaction as a continuous-time timing game over a combinatorial address-domain space, generalizing FlipIt to a collateral-bounded adversary. We prove a sustainability frontier separating configurations a censor can defeat from those it cannot, and show that under the Great Firewall's 2024 shift to blocking QUIC and TLS by domain, raw rotation speed is not the binding constraint. Instead, availability is governed by the domain burn rate, $β=λ_{\mathrm{disc}}/λ_{\mathrm{intro}}$, the ratio between how quickly the censor blocks defender domains and how quickly the defender introduces fresh ones. We derive a closed-form availability law, prove that address rotation alone cannot sustain high availability when $β>1$ regardless of endpoint rotation speed, and characterize the frontier $β^\star$. We validate the analysis with an open, model-level censor-defender simulator requiring no privileged access or cloud deployment. The simulator reproduces the predicted phase transition at $β^\star$ under adversary profiles representative of the GFW, Russia's TSPU, and Iran, and shows robustness to state-dependent discovery and bursty, provider-correlated burns. The result replaces the heuristic of ``rotate faster'' with a precise operating condition: keeping the domain economy ahead of the censor. △ Less

Submitted 7 June, 2026; originally announced June 2026.

On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits

Authors: Arnab Maiti, Yunbei Xu, Kevin Jamieson

Abstract: We study the minimax sample complexity of $\varepsilon$-best arm identification in linear bandits. Given a compact action set $\mathcal{X}$ that spans $\mathbb{R}^d$ and an unknown reward vector $θ\in\mathbb{R}^d$, the goal is to output an arm $\widehat{x}\in\mathcal{X}$ such that $\langle \widehat{x},θ\rangle \ge \max_{x\in\mathcal{X}} \langle x,θ\rangle - \varepsilon$ with probability at least… ▽ More We study the minimax sample complexity of $\varepsilon$-best arm identification in linear bandits. Given a compact action set $\mathcal{X}$ that spans $\mathbb{R}^d$ and an unknown reward vector $θ\in\mathbb{R}^d$, the goal is to output an arm $\widehat{x}\in\mathcal{X}$ such that $\langle \widehat{x},θ\rangle \ge \max_{x\in\mathcal{X}} \langle x,θ\rangle - \varepsilon$ with probability at least $1-δ$, using as few samples as possible. First, we present a non-adaptive fixed-design method with sample complexity $\mathcal{O}\!\left(\frac{d\log(1/δ)}{\varepsilon^2}+\frac{w(\mathcal{X})^2}{\varepsilon^2}\right)$, where $w(\mathcal{X})$ is a Gaussian width term dependent on $\mathcal{X}$, and we prove a matching lower bound $Ω\!\left(\frac{d\log(1/δ)}{\varepsilon^2}+\frac{w(\mathcal{X})^2}{\varepsilon^2}\right)$ for all non-adaptive fixed-design methods. We then turn to adaptive sampling. We raise an important structural question: beyond the canonical basis, are there structured action sets for which adaptivity yields only logarithmic-factor improvements over the optimal non-adaptive rate? We answer in the affirmative for several natural action sets, namely the hypercube, the $\ell_2$ ball, $m$-sets, and multi-task multi-armed bandits. Finally, we provide the first construction of an action set $\mathcal{X}$ for which adaptivity yields a polynomial-factor improvement over every non-adaptive algorithm. A key ingredient behind this separation is an $\ell_2$-norm estimation subroutine: we design an adaptive algorithm that uses $\mathcal{O}\!\left(\frac{d\log(1/δ)}{\varepsilon^2}\right)$ samples from the unit $\ell_2$ ball in $\mathbb{R}^d$ and outputs an estimate $\widehat r$ satisfying $|\widehat r-\|θ\|_2|\le \varepsilon$ with probability at least $1-δ$, where $θ$ is the unknown reward vector. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Comments: Accepted at COLT 2026

CLPIPS: A Personalized Metric for AI-Generated Image Similarity

Authors: Khoi Trinh, Jay Rothenberger, Scott Seidenberger, Dimitrios Diochnos, Anindya Maiti

Abstract: Iterative prompt refinement is central to reproducing target images with text to image generative models. Previous studies have incorporated image similarity metrics (ISMs) as additional feedback to human users. Existing ISMs such as LPIPS and CLIP provide objective measures of image likeness but often fail to align with human judgments, particularly in context specific or user driven tasks. In th… ▽ More Iterative prompt refinement is central to reproducing target images with text to image generative models. Previous studies have incorporated image similarity metrics (ISMs) as additional feedback to human users. Existing ISMs such as LPIPS and CLIP provide objective measures of image likeness but often fail to align with human judgments, particularly in context specific or user driven tasks. In this paper, we introduce Customized Learned Perceptual Image Patch Similarity (CLPIPS), a customized extension of LPIPS that adapts a metric's notion of similarity directly to human judgments. We aim to explore whether lightweight, human augmented fine tuning can meaningfully improve perceptual alignment, positioning similarity metrics as adaptive components for human in the loop workflows with text to image tools. We evaluate CLPIPS on a human subject dataset in which participants iteratively regenerate target images and rank generated outputs by perceived similarity. Using margin ranking loss on human ranked image pairs, we fine tune only the LPIPS layer combination weights and assess alignment via Spearman rank correlation and Intraclass Correlation Coefficient. Our results show that CLPIPS achieves stronger correlation and agreement with human judgments than baseline LPIPS. Rather than optimizing absolute metric performance, our work emphasizes improving alignment consistency between metric predictions and human ranks, demonstrating that even limited human specific fine tuning can meaningfully enhance perceptual alignment in human in the loop text to image workflows. △ Less

Submitted 26 March, 2026; originally announced April 2026.

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs

Authors: Satya Sri Rajiteswari Nimmagadda, Ethan Young, Niladri Sengupta, Ananya Jana, Aniruddha Maiti

Abstract: This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and recon… ▽ More This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and reconstructed sentences using semantic and lexical similarity we show that hierarchical formats are capable of retaining information of scientific texts effectively. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Comments: accepted to 21th International Conference on Semantic Computing (IEEE ICSC 2026)

TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation

Authors: Prajwal Panth, Agniva Maiti

Abstract: The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite a rich oral tradition, Tharu suffers from severe data s… ▽ More The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite a rich oral tradition, Tharu suffers from severe data scarcity and linguistic fragmentation, causing state-of-the-art multilingual models to routinely "hallucinate" or default to dominant high-resource neighbors like Hindi and Nepali due to contamination in pre-training corpora. This paper presents Tharu-LLaMA (3B), a specialized instruction-following model designed to address this exclusion. We introduce TharuChat, a novel dataset constructed via a LLM-to-Human bootstrapping pipeline. We utilized prompt-engineered Gemini models, fed with Rana Tharu grammar and folklore, to synthesize training data. Unlike curated gold-standard corpora, TharuChat reflects the noisy, heterogeneous linguistic reality of the region: it is predominantly anchored in Rana Tharu (~70%) while integrating elements of Dangaura and Kochila dialects. We provide a transparent analysis of the dataset's limitations, including dialectal code-mixing and residual Awadhi/Hindi influence. Through a rigorous empirical ablation study, we demonstrate that despite these imperfections, small-scale synthetic data is highly effective, increasing the dataset volume from 25% to 100% results in a linear reduction in perplexity from 6.42 to 2.88. The resulting model serves as a proof-of-concept for the preservation of under-resourced Himalayan languages via generative AI, achievable on consumer-grade hardware. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: 6 pages, 1 figure, 2 tables. Preprint. Code and dataset available on Hugging Face

Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis

Authors: Ethan Young, Zichun Wang, Aiden Taylor, Chance Jewell, Julian Myers, Satya Sri Rajiteswari Nimmagadda, Anthony White, Aniruddha Maiti, Ananya Jana

Abstract: Diagrams are widely used in teaching computer science courses. They are useful in subjects such as automata and formal languages, data structures, etc. These diagrams, often drawn by students during exams or assignments, vary in structure, layout, and correctness. This study examines whether current vision-language and large language models can process such diagrams and produce accurate textual an… ▽ More Diagrams are widely used in teaching computer science courses. They are useful in subjects such as automata and formal languages, data structures, etc. These diagrams, often drawn by students during exams or assignments, vary in structure, layout, and correctness. This study examines whether current vision-language and large language models can process such diagrams and produce accurate textual and digital representations. In this study, scanned student-drawn diagrams are used as input. Then, textual descriptions are generated from these images using a vision-language model. The descriptions are checked and revised by human reviewers to make them accurate. Both the generated and the revised descriptions are then fed to a large language model to generate TikZ code. The resulting diagrams are compiled and then evaluated against the original scanned diagrams. We found descriptions generated directly from images using vision-language models are often incorrect and human correction can substantially improve the quality of vision language model generated descriptions. This research can help computer science education by paving the way for automated grading and feedback and creating more accessible instructional materials. △ Less

Submitted 9 March, 2026; originally announced March 2026.

Comments: Accepted to ASEE North Central Section 2026

Prompt-Based Caption Generation for Single-Tooth Dental Images Using Vision-Language Models

Authors: Anastasiia Sukhanova, Aiden Taylor, Julian Myers, Zichun Wang, Kartha Veerya Jammuladinne, Satya Sri Rajiteswari Nimmagadda, Aniruddha Maiti, Ananya Jana

Abstract: Digital dentistry has made significant advances with the advent of deep learning. However, the majority of these deep learning-based dental image analysis models focus on very specific tasks such as tooth segmentation, tooth detection, cavity detection, and gingivitis classification. There is a lack of a specialized model that has holistic knowledge of teeth and can perform dental image analysis t… ▽ More Digital dentistry has made significant advances with the advent of deep learning. However, the majority of these deep learning-based dental image analysis models focus on very specific tasks such as tooth segmentation, tooth detection, cavity detection, and gingivitis classification. There is a lack of a specialized model that has holistic knowledge of teeth and can perform dental image analysis tasks based on that knowledge. Datasets of dental images with captions can help build such a model. To the best of our knowledge, existing dental image datasets with captions are few in number and limited in scope. In many of these datasets, the captions describe the entire mouth, while the images are limited to the anterior view. As a result, posterior teeth such as molars are not clearly visible, limiting the usefulness of the captions for training vision-language models. Additionally, the captions focus only on a specific disease (gingivitis) and do not provide a holistic assessment of each tooth. Moreover, tooth disease scores are typically assigned to individual teeth, and each tooth is treated as a separate entity in orthodontic procedures. Therefore, it is important to have captions for single-tooth images. As far as we know, no such dataset of single-tooth images with dental captions exists. In this work, we aim to bridge that gap by assessing the possibility of generating captions for dental images using Vision-Language Models (VLMs) and evaluating the extent and quality of those captions. Our findings suggest that guided prompts help VLMs generate meaningful captions. We show that the prompts generated by our framework are better anchored in describing the visual aspects of dental images. We selected RGB images as they have greater potential in consumer scenarios. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Comments: Accepted to IEEE International Conference on Semantic Computing (IEEE ICSC 2026)

Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners

Authors: Arnab Maiti, Junyan Liu, Kevin Jamieson, Lillian J. Ratliff

Abstract: We study the discrete Bertrand pricing game with a non-increasing demand function. The game has $n \ge 2$ players who simultaneously choose prices from the set $\{1/k, 2/k, \ldots, 1\}$, where $k\in\mathbb{N}$. The player who sets the lowest price captures the entire demand; if multiple players tie for the lowest price, they split the demand equally. We study the Bertrand paradox, where classica… ▽ More We study the discrete Bertrand pricing game with a non-increasing demand function. The game has $n \ge 2$ players who simultaneously choose prices from the set $\{1/k, 2/k, \ldots, 1\}$, where $k\in\mathbb{N}$. The player who sets the lowest price captures the entire demand; if multiple players tie for the lowest price, they split the demand equally. We study the Bertrand paradox, where classical theory predicts low prices, yet real markets often sustain high prices. To understand this gap, we analyze a repeated-game model in which firms set prices using no-regret learners. Our goal is to characterize the equilibrium outcomes that can arise under different no-regret learning guarantees. We are particularly interested in questions such as whether no-external-regret learners can converge to undesirable high-price outcomes, and how stronger guarantees such as no-swap regret shape the emergence of competitive low-price behavior. We address these and related questions through a theoretical analysis, complemented by experiments that support the theory and reveal surprising phenomena for no-swap regret learners. △ Less

Submitted 28 May, 2026; v1 submitted 25 February, 2026; originally announced February 2026.

Comments: 36 pages, 34 figures

Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback

Authors: Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff

Abstract: In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning algorithm tha… ▽ More In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning algorithm that guarantees last-iterate convergence to the Nash equilibrium with high probability. We establish a convergence rate of $\tilde{O}(T^{-1/4})$ up to polynomial factors in problem parameters. Crucially, our proposed algorithm is computationally efficient, requiring only an efficient linear optimization oracle over the players' compact action sets. The algorithm is obtained by combining techniques from experimental design and the classic Follow-The-Regularized-Leader (FTRL) framework, with a carefully chosen regularizer function tailored to the geometry of the action set of each learner. △ Less

Submitted 10 August, 2026; v1 submitted 24 February, 2026; originally announced February 2026.

Comments: 19 pages, accepted at AISTATS 2026. Affiliation update only; no changes to technical content

Min-Sum Uniform Coverage Problem by Autonomous Mobile Robots

Authors: Animesh Maiti, Abhinav Chakraborty, Bibhuti Das, Subhash Bhagat, Krishnendu Mukhopadhyaya

Abstract: We study the \textit{min-sum uniform coverage} problem for a swarm of $n$ mobile robots on a given finite line segment and on a circle having finite positive radius, where the circle is given as an input. The robots must coordinate their movements to reach a uniformly spaced configuration that minimizes the total distance traveled by all robots. The robots are autonomous, anonymous, identical, and… ▽ More We study the \textit{min-sum uniform coverage} problem for a swarm of $n$ mobile robots on a given finite line segment and on a circle having finite positive radius, where the circle is given as an input. The robots must coordinate their movements to reach a uniformly spaced configuration that minimizes the total distance traveled by all robots. The robots are autonomous, anonymous, identical, and homogeneous, and operate under the \textit{Look-Compute-Move} (LCM) model with \textit{non-rigid} motion controlled by a fair asynchronous scheduler. They are oblivious and silent, possessing neither persistent memory nor a means of explicit communication. In the \textbf{line-segment setting}, the \textit{min-sum uniform coverage} problem requires placing the robots at uniformly spaced points along the segment so as to minimize the total distance traveled by all robots. In the \textbf{circle setting} for this problem, the robots have to arrange themselves uniformly around the given circle to form a regular $n$-gon. There is no fixed orientation or designated starting vertex, and the goal is to minimize the total distance traveled by all the robots. We present a deterministic distributed algorithm that achieves uniform coverage in the line-segment setting with minimum total movement cost. For the circle setting, we characterize all initial configurations for which the \textit{min-sum uniform coverage} problem is deterministically unsolvable under the considered robot model. For all the other remaining configurations, we provide a deterministic distributed algorithm that achieves uniform coverage while minimizing the total distance traveled. These results characterize the deterministic solvability of min-sum coverage for oblivious robots and achieve optimal cost whenever solvable. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret

Authors: Shinji Ito, Haipeng Luo, Arnab Maiti, Taira Tsuchiya, Yue Wu

Abstract: Learning to play zero-sum games is a fundamental problem in game theory and machine learning. While significant progress has been made in minimizing external regret in the self-play settings or with full-information feedback, real-world applications often force learners to play against unknown, arbitrary opponents and restrict learners to bandit feedback where only the payoff of the realized actio… ▽ More Learning to play zero-sum games is a fundamental problem in game theory and machine learning. While significant progress has been made in minimizing external regret in the self-play settings or with full-information feedback, real-world applications often force learners to play against unknown, arbitrary opponents and restrict learners to bandit feedback where only the payoff of the realized action is observable. In such challenging settings, it is well-known that $Ω(\sqrt{T})$ external regret is unavoidable (where T is the number of rounds). To overcome this barrier, we investigate adversarial learning in zero-sum games under bandit feedback, aiming to minimize the deficit against the maximin pure strategy -- a metric we term Pure-Strategy Maximin Regret. We analyze this problem under two bandit feedback models: uninformed (only the realized reward is revealed) and informed (both the reward and the opponent's action are revealed). For uninformed bandit learning of normal-form games, we show that the Tsallis-INF algorithm achieves $O(c \log T)$ instance-dependent regret with a game-dependent parameter $c$. Crucially, we prove an information-theoretic lower bound showing that the dependence on c is necessary. To overcome this hardness, we turn to the informed setting and introduce Maximin-UCB, which obtains another regret bound of the form $O(c' \log T)$ for a different game-dependent parameter $c'$ that could potentially be much smaller than $c$. Finally, we generalize both results to bilinear games over an arbitrary, large action set, proposing Tsallis-FTRL-SPM and Maximin-LinUCB for the uninformed and informed setting respectively and establishing similar game-dependent logarithmic regret bounds. △ Less

Submitted 5 February, 2026; originally announced February 2026.

MSC Class: 91A26 (Primary) 68T05; 68Q32 (Secondary) ACM Class: F.2.0; I.2.6; G.3

Towards Worst-Case Guarantees with Scale-Aware Interpretability

Authors: Lauren Greenspan, David Berman, Aryeh Brill, Ro Jefferson, Artemy Kolchinsky, Jennifer Lin, Andrew Mack, Anindita Maiti, Fernando E. Rosas, Alexander Stapleton, Lucas Teixeira, Dmitry Vaintrob

Abstract: Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, explicitly tracking how features compose across resolutions and guaranteeing bounds on the influence of fine-grained structure that is discarded as irrelevant noise. We posit that the renormalisation framework from physics… ▽ More Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, explicitly tracking how features compose across resolutions and guaranteeing bounds on the influence of fine-grained structure that is discarded as irrelevant noise. We posit that the renormalisation framework from physics can meet this need by offering technical tools that can overcome limitations of current methods. Moreover, relevant work from adjacent fields has now matured to a point where scattered research threads can be synthesized into practical, theory-informed tools. To combine these threads in an AI safety context, we propose a unifying research agenda -- \emph{scale-aware interpretability} -- to develop formal machinery and interpretability tools that have robustness and faithfulness properties supported by statistical physics. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art

Authors: Khoi Trinh, Scott Seidenberger, Joseph Spracklen, Raveen Wijewickrama, Bimal Viswanath, Murtuza Jadliwala, Anindya Maiti

Abstract: The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts to generate unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered bona fide intellectual property, given th… ▽ More The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts to generate unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered bona fide intellectual property, given that humans and AI tools may be able to infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our study aims to assess (i) how accurately humans can infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting combined human and AI prompts with the help of a large language model. Although previous research has explored AI-driven prompt inference and protection strategies, our work is the first to incorporate a human subject study and examine collaborative human-AI prompt inference in depth. Our findings indicate that while prompts inferred by humans and prompts inferred through a combined human and AI effort can generate images with a moderate level of similarity, they are not as successful as using the original prompt. Moreover, combining human- and AI-inferred prompts using our suggested merging techniques did not improve performance over purely human-inferred prompts. △ Less

Submitted 24 January, 2026; originally announced January 2026.

Comments: To appear in EvoMUSART 2026

Estimating Causal Effects in Gaussian Linear SCMs with Finite Data

Authors: Aurghya Maiti, Prateek Jain

Abstract: Estimating causal effects from observational data remains a fundamental challenge in causal inference, especially in the presence of latent confounders. This paper focuses on estimating causal effects in Gaussian Linear Structural Causal Models (GL-SCMs), which are widely used due to their analytical tractability. However, parameter estimation in GL-SCMs is often infeasible with finite data, prima… ▽ More Estimating causal effects from observational data remains a fundamental challenge in causal inference, especially in the presence of latent confounders. This paper focuses on estimating causal effects in Gaussian Linear Structural Causal Models (GL-SCMs), which are widely used due to their analytical tractability. However, parameter estimation in GL-SCMs is often infeasible with finite data, primarily due to overparameterization. To address this, we introduce the class of Centralized Gaussian Linear SCMs (CGL-SCMs), a simplified yet expressive subclass where exogenous variables follow standardized distributions. We show that CGL-SCMs are equally expressive in terms of causal effect identifiability from observational distributions and present a novel EM-based estimation algorithm that can learn CGL-SCM parameters and estimate identifiable causal effects from finite observational samples. Our theoretical analysis is validated through experiments on synthetic data and benchmark causal graphs, demonstrating that the learned models accurately recover causal distributions. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: Accepted at the Workshop on Scaling Up Intervention Models at the 42nd International Conference on Machine Learning (ICML 2025)

NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data

Authors: Agniva Maiti, Manya Pandey, Murari Mandal

Abstract: The vast majority of the world's languages, particularly creoles like Nagamese, remain severely under-resourced in Natural Language Processing (NLP), creating a significant barrier to their representation in digital technology. This paper introduces NagaNLP, a comprehensive open-source toolkit for Nagamese, bootstrapped through a novel methodology that relies on LLM-driven but human-validated synt… ▽ More The vast majority of the world's languages, particularly creoles like Nagamese, remain severely under-resourced in Natural Language Processing (NLP), creating a significant barrier to their representation in digital technology. This paper introduces NagaNLP, a comprehensive open-source toolkit for Nagamese, bootstrapped through a novel methodology that relies on LLM-driven but human-validated synthetic data generation. We detail a multi-stage pipeline where an expert-guided LLM (Gemini) generates a candidate corpus, which is then refined and annotated by native speakers. This synthetic-hybrid approach yielded a 10K pair conversational dataset and a high-quality annotated corpus for foundational tasks. To assess the effectiveness of our methodology, we trained both discriminative and generative models. Our fine-tuned XLM-RoBERTa-base model establishes a new benchmark for Nagamese, achieving a 93.81\% accuracy (0.90 F1-Macro) on Part-of-Speech tagging and a 0.75 F1-Macro on Named Entity Recognition, massively outperforming strong zero-shot baselines. Furthermore, we fine-tuned a Llama-3.2-3B Instruct model, named NagaLLaMA, which demonstrates superior performance on conversational tasks, achieving a Perplexity of 3.85, an order of magnitude improvement over its few-shot counterpart (96.76). We release the NagaNLP toolkit, including all datasets, models, and code, providing a foundational resource for a previously underserved language and a reproducible framework for reducing data scarcity in other low-resource contexts. △ Less

Submitted 13 December, 2025; originally announced December 2025.

Semantic Reconstruction of Adversarial Plagiarism: A Context-Aware Framework for Detecting and Restoring "Tortured Phrases" in Scientific Literature

Authors: Agniva Maiti, Prajwal Panth, Suresh Chandra Satapathy

Abstract: The integrity and reliability of scientific literature is facing a serious threat by adversarial text generation techniques, specifically from the use of automated paraphrasing tools to mask plagiarism. These tools generate "tortured phrases", statistically improbable synonyms (e.g. "counterfeit consciousness" for "artificial intelligence"), that preserve the local grammar while obscuring the orig… ▽ More The integrity and reliability of scientific literature is facing a serious threat by adversarial text generation techniques, specifically from the use of automated paraphrasing tools to mask plagiarism. These tools generate "tortured phrases", statistically improbable synonyms (e.g. "counterfeit consciousness" for "artificial intelligence"), that preserve the local grammar while obscuring the original source. Most existing detection methods depend heavily on static blocklists or general-domain language models, which suffer from high false-negative rates for novel obfuscations and cannot determine the source of the plagiarized content. In this paper, we propose Semantic Reconstruction of Adversarial Plagiarism (SRAP), a framework designed not only to detect these anomalies but to mathematically recover the original terminology. We use a two-stage architecture: (1) statistical anomaly detection with a domain-specific masked language model (SciBERT) using token-level pseudo-perplexity, and (2) source-based semantic reconstruction using dense vector retrieval (FAISS) and sentence-level alignment (SBERT). Experiments on a parallel corpus of adversarial scientific text show that while zero-shot baselines fail completely (0.00 percent restoration accuracy), our retrieval-augmented approach achieves 23.67 percent restoration accuracy, significantly outperforming baseline methods. We also show that static decision boundaries are necessary for robust detection in jargon-heavy scientific text, since dynamic thresholding fails under high variance. SRAP enables forensic analysis by linking obfuscated expressions back to their most probable source documents. △ Less

Submitted 11 December, 2025; originally announced December 2025.

Comments: 10 pages, 5 figures; unpublished manuscript; submitted to arXiv for dissemination

ACM Class: I.2.7; H.3.3; I.5.1

Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup

Authors: Aniruddha Maiti, Satya Nimmagadda, Kartha Veerya Jammuladinne, Niladri Sengupta, Ananya Jana

Abstract: In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's output and generates a response. This continues for a fixed number of steps. We used Mistral Nemo Base 2407 and Llama 2 13B hf. We observed that most conversat… ▽ More In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's output and generates a response. This continues for a fixed number of steps. We used Mistral Nemo Base 2407 and Llama 2 13B hf. We observed that most conversations start coherently but later fall into repetition. In many runs, a short phrase appears and repeats across turns. Once repetition begins, both models tend to produce similar output rather than introducing a new direction in the conversation. This leads to a loop where the same or similar text is produced repeatedly. We describe this behavior as a form of convergence. It occurs even though the models are large, trained separately, and not given any prompt instructions. To study this behavior, we apply lexical and embedding-based metrics to measure how far the conversation drifts from the initial seed and how similar the outputs of the two models becomes as the conversation progresses. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Comments: accepted to LLM 2025

Quantum-Classical Separation in Bounded-Resource Tasks Arising from Measurement Contextuality

Authors: Shashwat Kumar, Eliott Rosenberg, Alejandro Grajales Dau, Rodrigo Cortinas, Dmitri Maslov, Richard Oliver, Adam Zalcman, Matthew Neeley, Alice Pagano, Aaron Szasz, Ilya Drozdov, Zlatko Minev, Craig Gidney, Noureldin Yosri, Stijn J. de Graaf, Aniket Maiti, Dmitry Abanin, Rajeev Acharya, Laleh Aghababaie Beni, Georg Aigeldinger, Ross Alcaraz, Sayra Alcaraz, Trond I. Andersen, Markus Ansmann, Frank Arute , et al. (258 additional authors not shown)

Abstract: The prevailing view is that quantum phenomena can be harnessed to tackle certain problems beyond the reach of classical approaches. Quantifying this capability as a quantum-classical separation and demonstrating it on current quantum processors has remained elusive. Using a superconducting qubit processor, we show that quantum contextuality enables certain tasks to be performed with success probab… ▽ More The prevailing view is that quantum phenomena can be harnessed to tackle certain problems beyond the reach of classical approaches. Quantifying this capability as a quantum-classical separation and demonstrating it on current quantum processors has remained elusive. Using a superconducting qubit processor, we show that quantum contextuality enables certain tasks to be performed with success probabilities beyond classical limits. With a few qubits, we illustrate quantum contextuality with the magic square game, as well as quantify it through a Kochen--Specker--Bell inequality violation. To examine many-body contextuality, we implement the N-player GHZ game and separately solve a 2D hidden linear function problem, exceeding classical success rate in both. Our work proposes novel ways to benchmark quantum processors using contextuality-based algorithms. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Fermions and Supersymmetry in Neural Network Field Theories

Authors: Samuel Frank, James Halverson, Anindita Maiti, Fabian Ruehle

Abstract: We introduce fermionic neural network field theories via Grassmann-valued neural networks. Free theories are obtained by a generalization of the Central Limit Theorem to Grassmann variables. This enables the realization of the free Dirac spinor at infinite width and a four fermion interaction at finite width. Yukawa couplings are introduced by breaking the statistical independence of the output we… ▽ More We introduce fermionic neural network field theories via Grassmann-valued neural networks. Free theories are obtained by a generalization of the Central Limit Theorem to Grassmann variables. This enables the realization of the free Dirac spinor at infinite width and a four fermion interaction at finite width. Yukawa couplings are introduced by breaking the statistical independence of the output weights for the fermionic and bosonic fields. A large class of interacting supersymmetric quantum mechanics and field theory models are introduced by super-affine transformations on the input that realize a superspace formalism. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: 34 pages + appendices

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Authors: Shinji Ito, Kevin Jamieson, Haipeng Luo, Arnab Maiti, Taira Tsuchiya

Abstract: We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual losses at each state-action pair. While prior work in this setting has focused exclusively on worst-case analysis, we initiate the study of best-of-both-worlds… ▽ More We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual losses at each state-action pair. While prior work in this setting has focused exclusively on worst-case analysis, we initiate the study of best-of-both-worlds (BOBW) algorithms that achieve low regret in both stochastic and adversarial environments. We propose the first BOBW algorithms for episodic tabular MDPs with aggregate bandit feedback. In the case of known transitions, our algorithms achieve $O(\log T)$ regret in stochastic settings and ${O}(\sqrt{T})$ regret in adversarial ones. Importantly, we also establish matching lower bounds, showing the optimality of our algorithms in this setting. We further extend our approach to unknown-transition settings by incorporating confidence-based techniques. Our results rely on a combination of FTRL over occupancy measures, self-bounding techniques, and new loss estimators inspired by recent advances in online shortest path problems. Along the way, we also provide the first individual-gap-dependent lower bounds and demonstrate near-optimal BOBW algorithms for shortest path problems with bandit feedback. △ Less

Submitted 27 October, 2025; v1 submitted 19 October, 2025; originally announced October 2025.

Comments: 49 pages

On the Universal Near Optimality of Hedge in Combinatorial Settings

Authors: Zhiyuan Fan, Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff, Gabriele Farina

Abstract: In this paper, we study the classical Hedge algorithm in combinatorial settings. In each round, the learner selects a vector $\boldsymbol{x}_t$ from a set $X \subseteq \{0,1\}^d$, observes a full loss vector $\boldsymbol{y}_t \in \mathbb{R}^d$, and incurs a loss $\langle \boldsymbol{x}_t, \boldsymbol{y}_t \rangle \in [-1,1]$. This setting captures several important problems, including extensive-fo… ▽ More In this paper, we study the classical Hedge algorithm in combinatorial settings. In each round, the learner selects a vector $\boldsymbol{x}_t$ from a set $X \subseteq \{0,1\}^d$, observes a full loss vector $\boldsymbol{y}_t \in \mathbb{R}^d$, and incurs a loss $\langle \boldsymbol{x}_t, \boldsymbol{y}_t \rangle \in [-1,1]$. This setting captures several important problems, including extensive-form games, resource allocation, $m$-sets, online multitask learning, and shortest-path problems on directed acyclic graphs (DAGs). It is well known that Hedge achieves a regret of $O\big(\sqrt{T \log |X|}\big)$ after $T$ rounds of interaction. In this paper, we ask whether Hedge is optimal across all combinatorial settings. To that end, we show that for any $X \subseteq \{0,1\}^d$, Hedge is near-optimal--specifically, up to a $\sqrt{\log d}$ factor--by establishing a lower bound of $Ω\big(\sqrt{T \log(|X|)/\log d}\big)$ that holds for any algorithm. We then identify a natural class of combinatorial sets--namely, $m$-sets with $\log d \leq m \leq \sqrt{d}$--for which this lower bound is tight, and for which Hedge is provably suboptimal by a factor of exactly $\sqrt{\log d}$. At the same time, we show that Hedge is optimal for online multitask learning, a generalization of the classical $K$-experts problem. Finally, we leverage the near-optimality of Hedge to establish the existence of a near-optimal regularizer for online shortest-path problems in DAGs--a setting that subsumes a broad range of combinatorial domains. Specifically, we show that the classical Online Mirror Descent (OMD) algorithm, when instantiated with the dilated entropy regularizer, is iterate-equivalent to Hedge, and therefore inherits its near-optimal regret guarantees for DAGs. △ Less

Submitted 23 October, 2025; v1 submitted 19 October, 2025; originally announced October 2025.

Comments: 28 pages, 1 Figure

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals

Authors: Junyan Liu, Arnab Maiti, Artin Tajdini, Kevin Jamieson, Lillian J. Ratliff

Abstract: We initiate the study of a repeated principal-agent problem over a finite horizon $T$, where a principal sequentially interacts with $K\geq 2$ types of agents arriving in an adversarial order. At each round, the principal strategically chooses one of the $N$ arms to incentivize for an arriving agent of unknown type. The agent then chooses an arm based on its own utility and the provided incentive,… ▽ More We initiate the study of a repeated principal-agent problem over a finite horizon $T$, where a principal sequentially interacts with $K\geq 2$ types of agents arriving in an adversarial order. At each round, the principal strategically chooses one of the $N$ arms to incentivize for an arriving agent of unknown type. The agent then chooses an arm based on its own utility and the provided incentive, and the principal receives a corresponding reward. The objective is to minimize regret against the best incentive in hindsight. Without prior knowledge of agent behavior, we show that the problem becomes intractable, leading to linear regret. We analyze two key settings where sublinear regret is achievable. In the first setting, the principal knows the arm each agent type would select greedily for any given incentive. Under this setting, we propose an algorithm that achieves a regret bound of $O(\min\{\sqrt{KT\log N},K\sqrt{T}\})$ and provide a matching lower bound up to a $\log K$ factor. In the second setting, an agent's response varies smoothly with the incentive and is governed by a Lipschitz constant $L\geq 1$. Under this setting, we show that there is an algorithm with a regret bound of $\tilde{O}((LN)^{1/3}T^{2/3})$ and establish a matching lower bound up to logarithmic factors. Finally, we extend our algorithmic results for both settings by allowing the principal to incentivize multiple arms simultaneously in each round. △ Less

Submitted 1 August, 2025; v1 submitted 29 May, 2025; originally announced May 2025.

Comments: To appear at ICML 2025

Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

Authors: Debdeep Sanyal, Agniva Maiti, Umakanta Maharana, Dhruv Kumar, Ankur Mali, C. Lee Giles, Murari Mandal

Abstract: Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer promise as tools to simulate such complex pedagogical environments, current simulation frameworks are limited in two key respects: (1) they often reduce students to… ▽ More Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Models (LLMs) offer promise as tools to simulate such complex pedagogical environments, current simulation frameworks are limited in two key respects: (1) they often reduce students to static knowledge profiles, and (2) they lack adaptive mechanisms for modeling teachers who evolve their strategies in response to student feedback. To address these gaps, \textbf{we introduce a novel simulation framework that integrates LLM-based heterogeneous student agents with a self-optimizing teacher agent}. The teacher agent's pedagogical policy is dynamically evolved using a genetic algorithm, allowing it to discover and refine effective teaching strategies based on the aggregate performance of diverse learners. In addition, \textbf{we propose Persona-RAG}, a Retrieval Augmented Generation module that enables student agents to retrieve knowledge tailored to their individual learning styles. Persona-RAG preserves the retrieval accuracy of standard RAG baselines while enhancing personalization, an essential factor in modeling realistic educational scenarios. Through extensive experiments, we demonstrate how our framework supports the emergence of distinct and interpretable teaching patterns when interacting with varied student populations. Our results highlight the potential of LLM-driven simulations to inform adaptive teaching practices and provide a testbed for training human educators in controlled, data-driven environments. △ Less

Submitted 25 May, 2025; originally announced May 2025.

Comments: 38 Pages

EtherBee: A Global Dataset of Ethereum Node Performance Measurements Coupled with Honeypot Interactions and Full Network Sessions

Authors: Scott Seidenberger, Anindya Maiti

Abstract: We introduce EtherBee, a global dataset integrating detailed Ethereum node metrics, network traffic metadata, and honeypot interaction logs collected from ten geographically diverse vantage points over three months. By correlating node data with granular network sessions and security events, EtherBee provides unique insights into benign and malicious activity, node stability, and network-level thr… ▽ More We introduce EtherBee, a global dataset integrating detailed Ethereum node metrics, network traffic metadata, and honeypot interaction logs collected from ten geographically diverse vantage points over three months. By correlating node data with granular network sessions and security events, EtherBee provides unique insights into benign and malicious activity, node stability, and network-level threats in the Ethereum peer-to-peer network. A case study shows how client-based optimizations can unintentionally concentrate the network geographically, impacting resilience and censorship resistance. We publicly release EtherBee to promote further investigations into performance, reliability, and security in decentralized networks. △ Less

Submitted 23 May, 2025; originally announced May 2025.

A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks

Authors: Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

Abstract: With AI-generated content becoming ubiquitous across the web, social media, and other digital platforms, it is vital to examine how such content are inspired and generated. The creation of AI-generated images often involves refining the input prompt iteratively to achieve desired visual outcomes. This study focuses on the relatively underexplored concept of image regeneration using AI, in which a… ▽ More With AI-generated content becoming ubiquitous across the web, social media, and other digital platforms, it is vital to examine how such content are inspired and generated. The creation of AI-generated images often involves refining the input prompt iteratively to achieve desired visual outcomes. This study focuses on the relatively underexplored concept of image regeneration using AI, in which a human operator attempts to closely recreate a specific target image by iteratively refining their prompt. Image regeneration is distinct from normal image generation, which lacks any predefined visual reference. A separate challenge lies in determining whether existing image similarity metrics (ISMs) can provide reliable, objective feedback in iterative workflows, given that we do not fully understand if subjective human judgments of similarity align with these metrics. Consequently, we must first validate their alignment with human perception before assessing their potential as a feedback mechanism in the iterative prompt refinement process. To address these research gaps, we present a structured user study evaluating how iterative prompt refinement affects the similarity of regenerated images relative to their targets, while also examining whether ISMs capture the same improvements perceived by human observers. Our findings suggest that incremental prompt adjustments substantially improve alignment, verified through both subjective evaluations and quantitative measures, underscoring the broader potential of iterative workflows to enhance generative AI content creation across various application domains. △ Less

Submitted 28 April, 2025; originally announced April 2025.

Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries

Authors: Arnab Maiti, Zhiyuan Fan, Kevin Jamieson, Lillian J. Ratliff, Gabriele Farina

Abstract: In this paper, we study the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary. Given a DAG $G = (V, E)$ with a source node $v_{\mathsf{s}}$ and a sink node $v_{\mathsf{t}}$, let $X \subseteq \{0,1\}^{|E|}$ denote the set of all paths from $v_{\mathsf{s}}$ to $v_{\mathsf{t}}$. At each round $t$, we select a path $\mathbf{x}_t \in X$ a… ▽ More In this paper, we study the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary. Given a DAG $G = (V, E)$ with a source node $v_{\mathsf{s}}$ and a sink node $v_{\mathsf{t}}$, let $X \subseteq \{0,1\}^{|E|}$ denote the set of all paths from $v_{\mathsf{s}}$ to $v_{\mathsf{t}}$. At each round $t$, we select a path $\mathbf{x}_t \in X$ and receive bandit feedback on our loss $\langle \mathbf{x}_t, \mathbf{y}_t \rangle \in [-1,1]$, where $\mathbf{y}_t$ is an adversarially chosen loss vector. Our goal is to minimize regret with respect to the best path in hindsight over $T$ rounds. We propose the first computationally efficient algorithm to achieve a near-minimax optimal regret bound of $\tilde O(\sqrt{|E|T\log |X|})$ with high probability against any adaptive adversary, where $\tilde O(\cdot)$ hides logarithmic factors in the number of edges $|E|$. Our algorithm leverages a novel loss estimator and a centroid-based decomposition in a nontrivial manner to attain this regret bound. As an application, we show that our algorithm for DAGs provides state-of-the-art efficient algorithms for $m$-sets, extensive-form games, the Colonel Blotto game, shortest walks in directed graphs, hypercubes, and multi-task multi-armed bandits, achieving improved high-probability regret guarantees in all these settings. △ Less

Submitted 1 April, 2025; originally announced April 2025.

Comments: 48 pages, 8 figures

Exploring the Energy Landscape of RBMs: Reciprocal Space Insights into Bosons, Hierarchical Learning and Symmetry Breaking

Authors: J. Quetzalcóatl Toledo-Marin, Anindita Maiti, Geoffrey C. Fox, Roger G. Melko

Abstract: Deep generative models have become ubiquitous due to their ability to learn and sample from complex distributions. Despite the proliferation of various frameworks, the relationships among these models remain largely unexplored, a gap that hinders the development of a unified theory of AI learning. We address two central challenges: clarifying the connections between different deep generative model… ▽ More Deep generative models have become ubiquitous due to their ability to learn and sample from complex distributions. Despite the proliferation of various frameworks, the relationships among these models remain largely unexplored, a gap that hinders the development of a unified theory of AI learning. We address two central challenges: clarifying the connections between different deep generative models and deepening our understanding of their learning mechanisms. We focus on Restricted Boltzmann Machines (RBMs), known for their universal approximation capabilities for discrete distributions. By introducing a reciprocal space formulation, we reveal a connection between RBMs, diffusion processes, and coupled Bosons. We show that at initialization, the RBM operates at a saddle point, where the local curvature is determined by the singular values, whose distribution follows the Marcenko-Pastur law and exhibits rotational symmetry. During training, this rotational symmetry is broken due to hierarchical learning, where different degrees of freedom progressively capture features at multiple levels of abstraction. This leads to a symmetry breaking in the energy landscape, reminiscent of Landau theory. This symmetry breaking in the energy landscape is characterized by the singular values and the weight matrix eigenvector matrix. We derive the corresponding free energy in a mean-field approximation. We show that in the limit of infinite size RBM, the reciprocal variables are Gaussian distributed. Our findings indicate that in this regime, there will be some modes for which the diffusion process will not converge to the Boltzmann distribution. To illustrate our results, we trained replicas of RBMs with different hidden layer sizes using the MNIST dataset. Our findings bridge the gap between disparate generative frameworks and also shed light on the processes underpinning learning in generative models. △ Less

Submitted 22 October, 2025; v1 submitted 27 March, 2025; originally announced March 2025.

Comments: 19pp, 8figs, research article

Journal ref: 2025 Mach. Learn.: Sci. Technol. 6 035030

Comparative Analysis of OpenAI GPT-4o and DeepSeek R1 for Scientific Text Categorization Using Prompt Engineering

Authors: Aniruddha Maiti, Samuel Adewumi, Temesgen Alemayehu Tikure, Zichun Wang, Niladri Sengupta, Anastasiia Sukhanova, Ananya Jana

Abstract: This study examines how large language models categorize sentences from scientific papers using prompt engineering. We use two advanced web-based models, GPT-4o (by OpenAI) and DeepSeek R1, to classify sentences into predefined relationship categories. DeepSeek R1 has been tested on benchmark datasets in its technical report. However, its performance in scientific text categorization remains unexp… ▽ More This study examines how large language models categorize sentences from scientific papers using prompt engineering. We use two advanced web-based models, GPT-4o (by OpenAI) and DeepSeek R1, to classify sentences into predefined relationship categories. DeepSeek R1 has been tested on benchmark datasets in its technical report. However, its performance in scientific text categorization remains unexplored. To address this gap, we introduce a new evaluation method designed specifically for this task. We also compile a dataset of cleaned scientific papers from diverse domains. This dataset provides a platform for comparing the two models. Using this dataset, we analyze their effectiveness and consistency in categorization. △ Less

Submitted 3 March, 2025; originally announced March 2025.

Comments: Accepted to ASEE North Central Section 2025

MagnetDB: A Longitudinal Torrent Discovery Dataset with IMDb-Matched Movies and TV Shows

Authors: Scott Seidenberger, Noah Pursell, Anindya Maiti

Abstract: BitTorrent remains a prominent channel for illicit distribution of copyrighted material, yet the supply side of such content remains understudied. We introduce MagnetDB, a longitudinal dataset of torrents discovered through the BitTorrent DHT between 2018 and 2024, containing more than 28.6 million torrents and metadata of more than 950 million files. While our primary focus is on enabling researc… ▽ More BitTorrent remains a prominent channel for illicit distribution of copyrighted material, yet the supply side of such content remains understudied. We introduce MagnetDB, a longitudinal dataset of torrents discovered through the BitTorrent DHT between 2018 and 2024, containing more than 28.6 million torrents and metadata of more than 950 million files. While our primary focus is on enabling research based on the supply of pirated movies and TV shows, the dataset also encompasses other legitimate and illegitimate torrents. By applying IMDb-matching and annotation to movie and TV show torrents, MagnetDB facilitates detailed analyses of pirated content evolution in the BitTorrent network. Researchers can leverage MagnetDB to examine distribution trends, subcultural practices, and the gift economy within piracy ecosystems. Through its scale and temporal scope, MagnetDB presents a unique opportunity for investigating the broader dynamics of BitTorrent and advancing empirical knowledge on digital piracy. △ Less

Submitted 15 January, 2025; originally announced January 2025.

ScooterLab: A Programmable and Participatory Sensing Research Testbed using Micromobility Vehicles

Authors: Ubaidullah Khan, Raveen Wijewickrama, Buddhi Ashan M. K., A. H. M. Nazmus Sakib, Khoi Trinh, Christina Duthie, Nima Najafian, Ahmer Patel, R. N. Molina, Anindya Maiti, Sushil K. Prasad, Greg P. Griffin, Murtuza Jadliwala

Abstract: Micromobility vehicles, such as e-scooters, are increasingly popular in urban communities but present significant challenges in terms of road safety, user privacy, infrastructure planning, and civil engineering. Addressing these critical issues requires a large-scale and easily accessible research infrastructure to collect diverse mobility and contextual data from micromobility users in realistic… ▽ More Micromobility vehicles, such as e-scooters, are increasingly popular in urban communities but present significant challenges in terms of road safety, user privacy, infrastructure planning, and civil engineering. Addressing these critical issues requires a large-scale and easily accessible research infrastructure to collect diverse mobility and contextual data from micromobility users in realistic settings. To this end, we present ScooterLab, a community research testbed comprising a fleet of customizable battery-powered micromobility vehicles retrofitted with advanced sensing, communication, and control capabilities. ScooterLab enables interdisciplinary research at the intersection of computing, mobility, and urban planning by providing researchers with tools to design and deploy customized sensing experiments and access curated datasets. The testbed will enable advances in machine learning, privacy, and urban transportation research while promoting sustainable mobility. △ Less

Submitted 10 January, 2025; originally announced January 2025.

Initial Evidence of Elevated Reconnaissance Attacks Against Nodes in P2P Overlay Networks

Authors: Scott Seidenberger, Anindya Maiti

Abstract: We hypothesize that peer-to-peer (P2P) overlay network nodes can be attractive to attackers due to their visibility, sustained uptime, and resource potential. Towards validating this hypothesis, we investigate the state of active reconnaissance attacks on Ethereum P2P network nodes by deploying a series of honeypots alongside actual Ethereum nodes across globally distributed vantage points. We fin… ▽ More We hypothesize that peer-to-peer (P2P) overlay network nodes can be attractive to attackers due to their visibility, sustained uptime, and resource potential. Towards validating this hypothesis, we investigate the state of active reconnaissance attacks on Ethereum P2P network nodes by deploying a series of honeypots alongside actual Ethereum nodes across globally distributed vantage points. We find that Ethereum nodes experience not only increased attacks, but also specific types of attacks targeting particular ports and services. Furthermore, we find evidence that the threat assessment on our nodes is applicable to the wider P2P network by having performed port scans on other reachable peers. Our findings provide insights into potential mitigation strategies to improve the security of the P2P networking layer. △ Less

Submitted 27 November, 2024; v1 submitted 21 November, 2024; originally announced November 2024.

NinjaDoH: A Censorship-Resistant Moving Target DoH Server Using Hyperscalers and IPNS

Authors: Scott Seidenberger, Marc Beret, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

Abstract: We introduce NinjaDoH, a novel DNS over HTTPS (DoH) protocol that leverages the InterPlanetary Name System (IPNS), along with public cloud infrastructure, to create a censorship-resistant moving target DoH service. NinjaDoH is specifically designed to evade traditional censorship methods that involve blocking DoH servers by IP addresses or domains by continually altering the server's network ident… ▽ More We introduce NinjaDoH, a novel DNS over HTTPS (DoH) protocol that leverages the InterPlanetary Name System (IPNS), along with public cloud infrastructure, to create a censorship-resistant moving target DoH service. NinjaDoH is specifically designed to evade traditional censorship methods that involve blocking DoH servers by IP addresses or domains by continually altering the server's network identifiers, significantly increasing the complexity of effectively censoring NinjaDoH traffic without disruption of other web traffic. We also present an analysis that quantifies the DNS query latency and financial costs of running our implementation of this protocol as a service. Further tests assess the ability of NinjaDoH to elude detection mechanisms, including both commercial firewall products and advanced machine learning-based detection systems. The results broadly support NinjaDoH's efficacy as a robust, moving target DNS solution that can ensure continuous and secure internet access in environments with heavy DNS-based censorship. △ Less

Submitted 4 November, 2024; originally announced November 2024.

Promptly Yours? A Human Subject Study on Prompt Inference in AI-Generated Art

Authors: Khoi Trinh, Joseph Spracklen, Raveen Wijewickrama, Bimal Viswanath, Murtuza Jadliwala, Anindya Maiti

Abstract: The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts for generating unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered as secure intellectual property, given… ▽ More The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts for generating unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered as secure intellectual property, given that humans and AI tools may be able to approximately infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our survey aims to assess (i) how accurately can humans infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting human-AI combined prompts with the help of a large language model. Although previous research has explored the use of AI and machine learning to infer (and also protect against) prompt inference, we are the first to include humans in the loop. Our findings indicate that while humans and human-AI collaborations can infer prompts and generate similar images with high accuracy, they are not as successful as using the original prompt. △ Less

Submitted 10 October, 2024; originally announced October 2024.

Why You've Got Mail: Evaluating Inbox Privacy Implications of Email Marketing Practices in Online Apps and Services

Authors: Scott Seidenberger, Oluwasijibomi Ajisegiri, Noah Pursell, Fazil Raja, Anindya Maiti

Abstract: This study explores the widespread perception that personal data, such as email addresses, may be shared or sold without informed user consent, investigating whether these concerns are reflected in actual practices of popular online services and apps. Over the course of a year, we collected and analyzed the source, volume, frequency, and content of emails received by users after signing up for the… ▽ More This study explores the widespread perception that personal data, such as email addresses, may be shared or sold without informed user consent, investigating whether these concerns are reflected in actual practices of popular online services and apps. Over the course of a year, we collected and analyzed the source, volume, frequency, and content of emails received by users after signing up for the 150 most popular online services and apps across various sectors. By examining patterns in email communications, we aim to identify consistent strategies used across industries, including potential signs of third-party data sharing. This analysis provides a critical evaluation of how email marketing tactics may intersect with data-sharing practices, with important implications for consumer privacy and regulatory oversight. Our study findings, conducted post-CCPA and GDPR, indicate that while no unknown third-party spam email was detected, internal and authorized third-party email marketing practices were pervasive, with companies frequently sending promotional and CRM emails despite opt-out preferences. The framework established in this work is designed to be scalable, allowing for continuous monitoring, and can be extended to include a more diverse set of apps and services for broader analysis, ultimately contributing to transparency in email address privacy practices. △ Less

Submitted 18 February, 2025; v1 submitted 10 October, 2024; originally announced October 2024.

Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities

Authors: Md Tauseef Alam, Raju Halder, Abyayananda Maiti

Abstract: The large-scale deployment of Solidity smart contracts on the Ethereum mainnet has increasingly attracted financially-motivated attackers in recent years. A few now-infamous attacks in Ethereum's history includes DAO attack in 2016 (50 million dollars lost), Parity Wallet hack in 2017 (146 million dollars locked), Beautychain's token BEC in 2018 (900 million dollars market value fell to 0), and NF… ▽ More The large-scale deployment of Solidity smart contracts on the Ethereum mainnet has increasingly attracted financially-motivated attackers in recent years. A few now-infamous attacks in Ethereum's history includes DAO attack in 2016 (50 million dollars lost), Parity Wallet hack in 2017 (146 million dollars locked), Beautychain's token BEC in 2018 (900 million dollars market value fell to 0), and NFT gaming blockchain breach in 2022 ($600 million in Ether stolen). This paper presents a comprehensive investigation of the use of large language models (LLMs) and their capabilities in detecting OWASP Top Ten vulnerabilities in Solidity. We introduce a novel, class-balanced, structured, and labeled dataset named VulSmart, which we use to benchmark and compare the performance of open-source LLMs such as CodeLlama, Llama2, CodeT5 and Falcon, alongside closed-source models like GPT-3.5 Turbo and GPT-4o Mini. Our proposed SmartVD framework is rigorously tested against these models through extensive automated and manual evaluations, utilizing BLEU and ROUGE metrics to assess the effectiveness of vulnerability detection in smart contracts. We also explore three distinct prompting strategies-zero-shot, few-shot, and chain-of-thought-to evaluate the multi-class classification and generative capabilities of the SmartVD framework. Our findings reveal that SmartVD outperforms its open-source counterparts and even exceeds the performance of closed-source base models like GPT-3.5 and GPT-4 Mini. After fine-tuning, the closed-source models, GPT-3.5 Turbo and GPT-4o Mini, achieved remarkable performance with 99% accuracy in detecting vulnerabilities, 94% in identifying their types, and 98% in determining severity. Notably, SmartVD performs best with the `chain-of-thought' prompting technique, whereas the fine-tuned closed-source models excel with the `zero-shot' prompting approach. △ Less

Submitted 26 October, 2024; v1 submitted 15 September, 2024; originally announced September 2024.

Optimal Neural Network Approximation for High-Dimensional Continuous Functions

Authors: Ayan Maiti, Michelle Michelle, Haizhao Yang

Abstract: Recently, the authors of \cite{SYZ22} developed a neural network with width $36d(2d + 1)$ and depth $11$, which utilizes a special activation function called the elementary universal activation function, to achieve the super approximation property for functions in $C([a,b]^d)$. That is, the constructed network only requires a fixed number of neurons (and thus parameters) to approximate a $d$-varia… ▽ More Recently, the authors of \cite{SYZ22} developed a neural network with width $36d(2d + 1)$ and depth $11$, which utilizes a special activation function called the elementary universal activation function, to achieve the super approximation property for functions in $C([a,b]^d)$. That is, the constructed network only requires a fixed number of neurons (and thus parameters) to approximate a $d$-variate continuous function on a $d$-dimensional hypercube with arbitrary accuracy. More specifically, only $\mathcal{O}(d^2)$ neurons or parameters are used. One natural question is whether we can reduce the number of these neurons or parameters in such a network. By leveraging a variant of the Kolmogorov Superposition Theorem, \textcolor{black}{we show that there is a composition of networks generated by the elementary universal activation function with at most $10889d + 10887$ nonzero parameters such that this super approximation property is attained. The composed network consists of repeated evaluations of two neural networks: one with width $36(2d+1)$ and the other with width 36, both having 5 layers.} Furthermore, we present a family of continuous functions that requires at least width $d$, and thus at least $d$ neurons or parameters, to achieve arbitrary accuracy in its approximation. This suggests that the number of nonzero parameters is optimal in the sense that it grows linearly with the input dimension $d$, unlike some approximation methods where parameters may grow exponentially with $d$. △ Less

Submitted 13 June, 2025; v1 submitted 3 September, 2024; originally announced September 2024.

Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs

Authors: Sanjay Bhargav Dharavath, Tanmoy Dam, Supriyo Chakraborty, Prithwiraj Roy, Aniruddha Maiti

Abstract: The field of autonomous vehicles (AVs) predominantly leverages multi-modal integration of LiDAR and camera data to achieve better performance compared to using a single modality. However, the fusion process encounters challenges in detecting distant objects due to the disparity between the high resolution of cameras and the sparse data from LiDAR. Insufficient integration of global perspectives wi… ▽ More The field of autonomous vehicles (AVs) predominantly leverages multi-modal integration of LiDAR and camera data to achieve better performance compared to using a single modality. However, the fusion process encounters challenges in detecting distant objects due to the disparity between the high resolution of cameras and the sparse data from LiDAR. Insufficient integration of global perspectives with local-level details results in sub-optimal fusion performance.To address this issue, we have developed an innovative two-stage fusion process called Quantum Inverse Contextual Vision Transformers (Q-ICVT). This approach leverages adiabatic computing in quantum concepts to create a novel reversible vision transformer known as the Global Adiabatic Transformer (GAT). GAT aggregates sparse LiDAR features with semantic features in dense images for cross-modal integration in a global form. Additionally, the Sparse Expert of Local Fusion (SELF) module maps the sparse LiDAR 3D proposals and encodes position information of the raw point cloud onto the dense camera feature space using a gating point fusion approach. Our experiments show that Q-ICVT achieves an mAPH of 82.54 for L2 difficulties on the Waymo dataset, improving by 1.88% over current state-of-the-art fusion methods. We also analyze GAT and SELF in ablation studies to highlight the impact of Q-ICVT. Our code is available at https://github.com/sanjay-810/Qicvt Q-ICVT △ Less

Submitted 20 August, 2024; originally announced August 2024.

Comments: The paper has been accepted as a short paper at CIKM '24

Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offs

Authors: Maryam Abbasihafshejani, Anindya Maiti, Murtuza Jadliwala

Abstract: Federated machine learning enables model training across multiple clients while maintaining data privacy. Vertical Federated Learning (VFL) specifically deals with instances where the clients have different feature sets of the same samples. As federated learning models aim to improve efficiency and adaptability, innovative neural network architectures like Spiking Neural Networks (SNNs) are being… ▽ More Federated machine learning enables model training across multiple clients while maintaining data privacy. Vertical Federated Learning (VFL) specifically deals with instances where the clients have different feature sets of the same samples. As federated learning models aim to improve efficiency and adaptability, innovative neural network architectures like Spiking Neural Networks (SNNs) are being leveraged to enable fast and accurate processing at the edge. SNNs, known for their efficiency over Artificial Neural Networks (ANNs), have not been analyzed for their applicability in VFL, thus far. In this paper, we investigate the benefits and trade-offs of using SNN models in a vertical federated learning setting. We implement two different federated learning architectures -- with model splitting and without model splitting -- that have different privacy and performance implications. We evaluate the setup using CIFAR-10 and CIFAR-100 benchmark datasets along with SNN implementations of VGG9 and ResNET classification models. Comparative evaluations demonstrate that the accuracy of SNN models is comparable to that of traditional ANNs for VFL applications, albeit significantly more energy efficient. △ Less

Submitted 13 August, 2024; v1 submitted 24 July, 2024; originally announced July 2024.

We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs

Authors: Joseph Spracklen, Raveen Wijewickrama, A H M Nazmus Sakib, Anindya Maiti, Bimal Viswanath, Murtuza Jadliwala

Abstract: The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-generating Large Language Models (LLMs), has created a new type of threat to the software supply chain: package hallucinations. These hallucinations, which arise from fact-conflicting errors when generating code using LLMs, re… ▽ More The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-generating Large Language Models (LLMs), has created a new type of threat to the software supply chain: package hallucinations. These hallucinations, which arise from fact-conflicting errors when generating code using LLMs, represent a novel form of package confusion attack that poses a critical threat to the integrity of the software supply chain. This paper conducts a rigorous and comprehensive evaluation of package hallucinations across different programming languages, settings, and parameters, exploring how a diverse set of models and configurations affect the likelihood of generating erroneous package recommendations and identifying the root causes of this phenomenon. Using 16 popular LLMs for code generation and two unique prompt datasets, we generate 576,000 code samples in two programming languages that we analyze for package hallucinations. Our findings reveal that that the average percentage of hallucinated packages is at least 5.2% for commercial models and 21.7% for open-source models, including a staggering 205,474 unique examples of hallucinated package names, further underscoring the severity and pervasiveness of this threat. To overcome this problem, we implement several hallucination mitigation strategies and show that they are able to significantly reduce the number of package hallucinations while maintaining code quality. Our experiments and findings highlight package hallucinations as a persistent and systemic phenomenon while using state-of-the-art LLMs for code generation, and a significant challenge which deserves the research community's urgent attention. △ Less

Submitted 2 March, 2025; v1 submitted 11 June, 2024; originally announced June 2024.

Comments: To appear in the 2025 USENIX Security Symposium. 22 pages, 14 figures, 8 tables. Edited from original version for submission to a different conference. No change to original results or findings

Causal Contextual Bandits with Adaptive Context

Authors: Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth Barman

Abstract: We study a variant of causal contextual bandits where the context is chosen based on an initial intervention chosen by the learner. At the beginning of each round, the learner selects an initial action, depending on which a stochastic context is revealed by the environment. Following this, the learner then selects a final action and receives a reward. Given $T$ rounds of interactions with the envi… ▽ More We study a variant of causal contextual bandits where the context is chosen based on an initial intervention chosen by the learner. At the beginning of each round, the learner selects an initial action, depending on which a stochastic context is revealed by the environment. Following this, the learner then selects a final action and receives a reward. Given $T$ rounds of interactions with the environment, the objective of the learner is to learn a policy (of selecting the initial and the final action) with maximum expected reward. In this paper we study the specific situation where every action corresponds to intervening on a node in some known causal graph. We extend prior work from the deterministic context setting to obtain simple regret minimization guarantees. This is achieved through an instance-dependent causal parameter, $λ$, which characterizes our upper bound. Furthermore, we prove that our simple regret is essentially tight for a large class of instances. A key feature of our work is that we use convex optimization to address the bandit exploration problem. We also conduct experiments to validate our theoretical results, and release our code at our project GitHub repository: https://github.com/adaptiveContextualCausalBandits/aCCB. △ Less

Submitted 2 June, 2024; v1 submitted 28 May, 2024; originally announced May 2024.

Comments: Reinforcement Learning Conference (RLC) 2024, 10 pages (31 pages including appendix), 8 plots. arXiv admin note: text overlap with arXiv:2111.00886

Generating Print-Ready Personalized AI Art Products from Minimal User Inputs

Authors: Noah Pursell, Anindya Maiti

Abstract: We present a novel framework to advance generative artificial intelligence (AI) applications in the realm of printed art products, specifically addressing large-format products that require high-resolution artworks. The framework consists of a pipeline that addresses two major challenges in the domain: the high complexity of generating effective prompts, and the low native resolution of images pro… ▽ More We present a novel framework to advance generative artificial intelligence (AI) applications in the realm of printed art products, specifically addressing large-format products that require high-resolution artworks. The framework consists of a pipeline that addresses two major challenges in the domain: the high complexity of generating effective prompts, and the low native resolution of images produced by diffusion models. By integrating AI-enhanced prompt generations with AI-powered upscaling techniques, our framework can efficiently produce high-quality, diverse artistic images suitable for many new commercial use cases. Our work represents a significant step towards democratizing high-quality AI art, opening new avenues for consumers, artists, designers, and businesses. △ Less

Submitted 28 March, 2024; originally announced May 2024.

Bayesian RG Flow in Neural Network Field Theories

Authors: Jessica N. Howard, Marc S. Klinger, Anindita Maiti, Alexander G. Stapleton

Abstract: The Neural Network Field Theory correspondence (NNFT) is a mapping from neural network (NN) architectures into the space of statistical field theories (SFTs). The Bayesian renormalization group (BRG) is an information-theoretic coarse graining scheme that generalizes the principles of the exact renormalization group (ERG) to arbitrarily parameterized probability distributions, including those of N… ▽ More The Neural Network Field Theory correspondence (NNFT) is a mapping from neural network (NN) architectures into the space of statistical field theories (SFTs). The Bayesian renormalization group (BRG) is an information-theoretic coarse graining scheme that generalizes the principles of the exact renormalization group (ERG) to arbitrarily parameterized probability distributions, including those of NNs. In BRG, coarse graining is performed in parameter space with respect to an information-theoretic distinguishability scale set by the Fisher information metric. In this paper, we unify NNFT and BRG to form a powerful new framework for exploring the space of NNs and SFTs, which we coin BRG-NNFT. With BRG-NNFT, NN training dynamics can be interpreted as inducing a flow in the space of SFTs from the information-theoretic `IR' $\rightarrow$ `UV'. Conversely, applying an information-shell coarse graining to the trained network's parameters induces a flow in the space of SFTs from the information-theoretic `UV' $\rightarrow$ `IR'. When the information-theoretic cutoff scale coincides with a standard momentum scale, BRG is equivalent to ERG. We demonstrate the BRG-NNFT correspondence on two analytically tractable examples. First, we construct BRG flows for trained, infinite-width NNs, of arbitrary depth, with generic activation functions. As a special case, we then restrict to architectures with a single infinitely-wide layer, scalar outputs, and generalized cos-net activations. In this case, we show that BRG coarse-graining corresponds exactly to the momentum-shell ERG flow of a free scalar SFT. Our analytic results are corroborated by a numerical experiment in which an ensemble of asymptotically wide NNs are trained and subsequently renormalized using an information-shell BRG scheme. △ Less

Submitted 5 February, 2025; v1 submitted 27 May, 2024; originally announced May 2024.

Comments: 41 pages, 9 figures, 2 tables; clarified parts of text, fixed typos, added a pedagogical Bayesian inference example to section 2.1

Journal ref: SciPost Phys. Core 8, 027 (2025)

Asymptotic theory of in-context learning by linear attention

Authors: Yue M. Lu, Mary I. Letey, Jacob A. Zavatone-Veth, Anindita Maiti, Cengiz Pehlevan

Abstract: Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a cornerstone of Transformers' success, yet questions about the necessary sample complexity, pretraining task diversity, and context length for successful ICL remain unr… ▽ More Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a cornerstone of Transformers' success, yet questions about the necessary sample complexity, pretraining task diversity, and context length for successful ICL remain unresolved. Here, we provide a precise answer to these questions in an exactly solvable model of ICL of a linear regression task by linear attention. We derive sharp asymptotics for the learning curve in a phenomenologically-rich scaling regime where the token dimension is taken to infinity; the context length and pretraining task diversity scale proportionally with the token dimension; and the number of pretraining examples scales quadratically. We demonstrate a double-descent learning curve with increasing pretraining examples, and uncover a phase transition in the model's behavior between low and high task diversity regimes: In the low diversity regime, the model tends toward memorization of training tasks, whereas in the high diversity regime, it achieves genuine in-context learning and generalization beyond the scope of pretrained tasks. These theoretical insights are empirically validated through experiments with both linear attention and full nonlinear Transformer architectures. △ Less

Submitted 1 October, 2025; v1 submitted 19 May, 2024; originally announced May 2024.

Comments: 15 pages (main doc), 6 figures, and supplementary information (22 pages)

Report number: 10.1073/pnas.2502599122

Journal ref: Proc. Natl. Acad. Sci. U.S.A. 122 (28) e2502599122 (2025)

Wilsonian Renormalization of Neural Network Gaussian Processes

Authors: Jessica N. Howard, Ro Jefferson, Anindita Maiti, Zohar Ringel

Abstract: Separating relevant and irrelevant information is key to any modeling process or scientific inquiry. Theoretical physics offers a powerful tool for achieving this in the form of the renormalization group (RG). Here we demonstrate a practical approach to performing Wilsonian RG in the context of Gaussian Process (GP) Regression. We systematically integrate out the unlearnable modes of the GP kernel… ▽ More Separating relevant and irrelevant information is key to any modeling process or scientific inquiry. Theoretical physics offers a powerful tool for achieving this in the form of the renormalization group (RG). Here we demonstrate a practical approach to performing Wilsonian RG in the context of Gaussian Process (GP) Regression. We systematically integrate out the unlearnable modes of the GP kernel, thereby obtaining an RG flow of the GP in which the data sets the IR scale. In simple cases, this results in a universal flow of the ridge parameter, which becomes input-dependent in the richer scenario in which non-Gaussianities are included. In addition to being analytically tractable, this approach goes beyond structural analogies between RG and neural networks by providing a natural connection between RG flow and learnable vs. unlearnable modes. Studying such flows may improve our understanding of feature learning in deep neural networks, and enable us to identify potential universality classes in these models. △ Less

Submitted 13 May, 2025; v1 submitted 9 May, 2024; originally announced May 2024.

Comments: Accepted by Machine Learning: Science and Technology; 45 pages, 6 figures; expanded neural scaling law results with empirical experiments, clarified intermediate derivation steps, added references, added appendices

NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry

Authors: Yash Khandelwal, Mayur Arvind, Sriram Kumar, Ashish Gupta, Sachin Kumar Danisetty, Piyush Bagad, Anish Madan, Mayank Lunayach, Aditya Annavajjala, Abhishek Maiti, Sansiddh Jain, Aman Dalmia, Namrata Deka, Jerome White, Jigar Doshi, Angjoo Kanazawa, Rahul Panicker, Alpan Raval, Srinivas Rana, Makarand Tapaswi

Abstract: Malnutrition among newborns is a top public health concern in developing countries. Identification and subsequent growth monitoring are key to successful interventions. However, this is challenging in rural communities where health systems tend to be inaccessible and under-equipped, with poor adherence to protocol. Our goal is to equip health workers and public health systems with a solution for c… ▽ More Malnutrition among newborns is a top public health concern in developing countries. Identification and subsequent growth monitoring are key to successful interventions. However, this is challenging in rural communities where health systems tend to be inaccessible and under-equipped, with poor adherence to protocol. Our goal is to equip health workers and public health systems with a solution for contactless newborn anthropometry in the community. We propose NurtureNet, a multi-task model that fuses visual information (a video taken with a low-cost smartphone) with tabular inputs to regress multiple anthropometry estimates including weight, length, head circumference, and chest circumference. We show that visual proxy tasks of segmentation and keypoint prediction further improve performance. We establish the efficacy of the model through several experiments and achieve a relative error of 3.9% and mean absolute error of 114.3 g for weight estimation. Model compression to 15 MB also allows offline deployment to low-cost smartphones. △ Less

Submitted 8 May, 2024; originally announced May 2024.

Comments: Accepted at CVPM Workshop at CVPR 2024

Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks

Authors: Kavita Kumari, Murtuza Jadliwala, Sumit Kumar Jha, Anindya Maiti

Abstract: Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have only analyzed MIA in a single "what if" interaction scenario between an adversary and the target ML model; thus, it does not discern the factors impacting the capab… ▽ More Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have only analyzed MIA in a single "what if" interaction scenario between an adversary and the target ML model; thus, it does not discern the factors impacting the capabilities of an adversary in launching MIA in repeated interaction settings. Additionally, these works rely on assumptions about the adversary's knowledge of the target model's structure and, thus, do not guarantee the optimality of the predefined threshold required to distinguish the members from non-members. In this paper, we delve into the domain of explanation-based threshold attacks, where the adversary endeavors to carry out MIA attacks by leveraging the variance of explanations through iterative interactions with the system comprising of the target ML model and its corresponding explanation method. We model such interactions by employing a continuous-time stochastic signaling game framework. In our framework, an adversary plays a stopping game, interacting with the system (having imperfect information about the type of an adversary, i.e., honest or malicious) to obtain explanation variance information and computing an optimal threshold to determine the membership of a datapoint accurately. First, we propose a sound mathematical formulation to prove that such an optimal threshold exists, which can be used to launch MIA. Then, we characterize the conditions under which a unique Markov perfect equilibrium (or steady state) exists in this dynamic system. By means of a comprehensive set of simulations of the proposed game model, we assess different factors that can impact the capability of an adversary to launch MIA in such repeated interaction settings. △ Less

Submitted 10 April, 2024; originally announced April 2024.

Comments: arXiv admin note: text overlap with arXiv:2202.02659

Boosting Digital Safeguards: Blending Cryptography and Steganography

Authors: Anamitra Maiti, Subham Laha, Rishav Upadhaya, Soumyajit Biswas, Vikas Chaudhary, Biplab Kar, Nikhil Kumar, Jaydip Sen

Abstract: In today's digital age, the internet is essential for communication and the sharing of information, creating a critical need for sophisticated data security measures to prevent unauthorized access and exploitation. Cryptography encrypts messages into a cipher text that is incomprehensible to unauthorized readers, thus safeguarding data during its transmission. Steganography, on the other hand, ori… ▽ More In today's digital age, the internet is essential for communication and the sharing of information, creating a critical need for sophisticated data security measures to prevent unauthorized access and exploitation. Cryptography encrypts messages into a cipher text that is incomprehensible to unauthorized readers, thus safeguarding data during its transmission. Steganography, on the other hand, originates from the Greek term for "covered writing" and involves the art of hiding data within another medium, thereby facilitating covert communication by making the message invisible. This proposed approach takes advantage of the latest advancements in Artificial Intelligence (AI) and Deep Learning (DL), especially through the application of Generative Adversarial Networks (GANs), to improve upon traditional steganographic methods. By embedding encrypted data within another medium, our method ensures that the communication remains hidden from prying eyes. The application of GANs enables a smart, secure system that utilizes the inherent sensitivity of neural networks to slight alterations in data, enhancing the protection against detection. By merging the encryption techniques of cryptography with the hiding capabilities of steganography, and augmenting these with the strengths of AI, we introduce a comprehensive security system designed to maintain both the privacy and integrity of information. This system is crafted not just to prevent unauthorized access or modification of data, but also to keep the existence of the data hidden. This fusion of technologies tackles the core challenges of data security in the current era of open digital communication, presenting an advanced solution with the potential to transform the landscape of information security. △ Less

Submitted 11 April, 2024; v1 submitted 8 April, 2024; originally announced April 2024.

Comments: This report pertains to the Capstone Project done by Group 3 of the Fall batch of 2023 students at Praxis Tech School, Kolkata, India. The reports consists of 36 pages and it includes 11 figures and 5 tables