Showing 1–50 of 80 results for author: Singhal, A

AI-assisted Script Management for Requirements Elicitation Interviews

Authors: Anmol Singhal, Paulo Carvalho, Travis Breaux

Abstract: Requirements elicitation interviews require interviewers to balance topic coverage, active listening, and adaptive probing while responding to stakeholders in real time. Although prior work has explored AI support for isolated interviewing tasks, such as script generation and follow-up question generation, little is known about how integrated support affects the interview and what requirements art… ▽ More Requirements elicitation interviews require interviewers to balance topic coverage, active listening, and adaptive probing while responding to stakeholders in real time. Although prior work has explored AI support for isolated interviewing tasks, such as script generation and follow-up question generation, little is known about how integrated support affects the interview and what requirements artifacts emerge. Furthermore, script management---which helps the interviewer track topic coverage in real time and decide when to probe further---remains underexplored. This paper presents an AI-assisted elicitation workflow that combines theory-guided script generation grounded in business goals with live support for topic coverage tracking and on-demand follow-up question generation. We evaluate the workflow in a between-subjects quasi-experimental study comparing a no-training, AI-assisted condition with a training, AI-unassisted condition. Based on a rubric derived from elicitation best practices, the AI-generated scripts score higher than training-only scripts (92.8 vs. 74.8 out of 100). AI-assisted interviews cover fewer topics (9.6 vs. 14.5), cover more scripted questions (86% vs. 69%), ask more follow-ups per topic (3.43 vs. 1.15), and produce more refined goal models (lowest-level goal fraction 0.653 vs. 0.598). Participants find script management useful, rating topic tracking as the most useful workflow feature (86% agreement). Collectively, these results show that the AI-assisted condition is associated with a different interview trajectory and different elicited requirements than a training-only condition, positioning AI-assisted workflows as elicitation scaffolds for future studies. △ Less

Submitted 2 August, 2026; originally announced August 2026.

Comments: 12 pages, 3 figures, 3 tables

Hallucination Detection in Large Language Models Using Diversion Decoding

Authors: Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Parag Modi, Ehab Al-Shaer

Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate L… ▽ More Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measure of the LLM's uncertainty. Our experimental results demonstrate that diversion decoding outperforms existing methods with significantly lower computational complexity, making it an efficient and robust solution for evaluating hallucination detection. △ Less

Submitted 19 August, 2026; v1 submitted 11 July, 2026; originally announced July 2026.

Journal ref: Data and Applications Security and Privacy XXXIX. DBSec 2025

Predictable GRPO: A Closed-Form Model of Training Dynamics

Authors: Rajat Ghosh, Datta Nimmaturi, Aryan Singhal, Vaishnavi Bhargava, Henry Wong, Johnu George, Debojyoti Dutta

Abstract: We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO update to a stochastically-forced damped oscillator whose mass, damping, and stiffness are fixed in closed form by the optimizer hyperparameters together with a single measured curvature scale -- momentum supplies the inerti… ▽ More We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO update to a stochastically-forced damped oscillator whose mass, damping, and stiffness are fixed in closed form by the optimizer hyperparameters together with a single measured curvature scale -- momentum supplies the inertia, off-policy lag erodes the damping, and the group size enters, to leading order, as a noise temperature. The reduction has three consequences. First, it subsumes the empirical single-exponential saturation law as its overdamped limit, recasting the fitted plateau, timescale, and size exponent as the fixed point, inverse stiffness, and curvature-scaling exponent of the underlying potential, and adding, through the retained inertial term, the slow-start phase the single exponential cannot represent. Second, it yields predictions tied to independently measurable quantities rather than fitted ones: group-size invariance of the deterministic trajectory with a $1/G$ stationary fluctuation, a sharp stability threshold in the refresh interval, and an overdamped-to-oscillatory transition. Third, it furnishes diagnostics that separate failure modes a reward curve alone conflates -- reward hacking, advantage degeneracy, policy concentration, and dynamical instability. Across three models and two group sizes, the closed-form trajectory fits training reward to $R^2 \geq 0.91$ and the mean trajectory is group-size invariant to leading order -- on both the reward curve and out-of-distribution transfer to eight math benchmarks -- while the within-group reward spread retains a residual $G$-dependence that the leading-order temperature picture does not capture. △ Less

Submitted 1 July, 2026; v1 submitted 29 June, 2026; originally announced June 2026.

Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance

Authors: Arush Singhal, Umang Soni

Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias. In this work, we identify a complementary optimization-level pathology: inter-class gradient interference within shared representations, where gradients from majority classes suppress minority-class learning. To analyze this phenomenon, we introduce a diagnostic f… ▽ More Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias. In this work, we identify a complementary optimization-level pathology: inter-class gradient interference within shared representations, where gradients from majority classes suppress minority-class learning. To analyze this phenomenon, we introduce a diagnostic framework based on layer-wise gradient flow analysis and a Gradient Conflict Matrix, which quantifies interference using cosine similarity between class-specific gradients. Using this framework, we study multi-branch convolutional architectures and propose a lightweight modification, Class-Specific Branch Attention (CSBA), that enables branch-specific channel reweighting to reduce gradient coupling. This mechanism promotes implicit feature decoupling across branches while preserving architectural simplicity. Empirically, CSBA improves minority-class performance, increasing the F1 score for the Physical-Damage class from 0.261 to 0.522 under severe imbalance, while maintaining comparable overall accuracy. Validation on CIFAR-10-LT confirms that this behavior generalizes across imbalanced visual recognition settings, with Macro-F1 improving from 0.595 to 0.655. More broadly, our findings highlight the importance of considering optimization dynamics alongside statistical methods when designing architectures for imbalanced learning. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: 14 pages, 4 figures, 13 tables

Report on the Designing Accountable Software Systems Workshop

Authors: Catherine Albiston, Travis Breaux, Kat Dearstyne, Jane Cleland-Huang, Serge Egelman, Joan Feigenbaum, Lu Feng, Max Lindquist, Stephen Miner, Ruzica Piskac, Sarah Santos, Jordan Schmerge, Anmol Singhal, Maria Smith, Daniel Weitzner, Christopher Yoo

Abstract: The Workshop on Designing Accountable Software Systems (DASS) was convened in November 2024 with support from the U.S. National Science Foundation to engage a wide range of current and future stakeholders from government, academia, and industry on the cross-disciplinary topic of accountability in software systems. Over two days, attendees engaged in a series of panels, invited talks, and breakout… ▽ More The Workshop on Designing Accountable Software Systems (DASS) was convened in November 2024 with support from the U.S. National Science Foundation to engage a wide range of current and future stakeholders from government, academia, and industry on the cross-disciplinary topic of accountability in software systems. Over two days, attendees engaged in a series of panels, invited talks, and breakout sessions covering: (1) the dimensions of accountability, including legal compliance as well as business and societal aspects and drivers; (2) a conceptual model of the various structures needed to realize accountability; (3) the sources of legal requirements that affect software; (4) the operationalization of legal requirements in software; (5) the requirements to preserve evidence needed to conduct investigations; and (6) a range of challenges and contextual factors beyond software that affect why some accountability structures succeed, while others fail. The workshop was conducted as a collaborative systematization of knowledge that culminated in several research directions. The findings include the importance of clarifying definitions and responsibilities within accountable organizations, which can affect whether those researching accountability are making assumptions that limit the generalizability of findings. Further research was also identified as needed to study the ways to improve the translation of accountability structures into the software design process while improving engagement with stakeholders, such as legislators, regulators, business executives and system developers. Finally, a key finding was the high demands that DASS-like research projects place on interdisciplinary teams: both in terms of team formation and sustainment, as well as, the specific demands of cross-disciplinary learning that covers both research methods, research dissemination, and career development. △ Less

Submitted 1 June, 2026; originally announced June 2026.

ACM Class: K.5

Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models

Authors: S M Tahmid Siddiqui, Akib Jawad Ononto, Anoop Singhal, Latifur Khan

Abstract: Large language models (LLMs) have seen widespread adoption across various domains, yet their reliability is frequently undermined by hallucinations - responses that are plausible-sounding but factually incorrect. In high-stakes domains, these errors can reduce trust and introduce real-world risk. To address this challenge, we present a parameter-efficient approach that uses soft prompts to mitigat… ▽ More Large language models (LLMs) have seen widespread adoption across various domains, yet their reliability is frequently undermined by hallucinations - responses that are plausible-sounding but factually incorrect. In high-stakes domains, these errors can reduce trust and introduce real-world risk. To address this challenge, we present a parameter-efficient approach that uses soft prompts to mitigate hallucinated content and promote responsible abstention in generative question-answering (QA) tasks. Our method, called Responsible Contrastive Soft Prompting (RCSP), uses a composite loss to train soft prompts that balance three goals: suppressing hallucinatory content, encouraging abstention under uncertainty, and preserving or improving factual recall. To achieve these goals, we incorporate contrastive loss, curriculum learning, and KL regularization into our training mechanism. We evaluate our approach on five diverse generative QA datasets using an LLM-as-a-Judge framework. Experimental results on the Gemma 3 (12B) and Llama 3.1 (8B) backbones demonstrate that RCSP effectively balances factual recall with hallucination suppression and abstention, yielding a generally superior F-score over standard reasoning and instruction-based prompting baselines. Notably, these improvements are achieved by training only a fraction of the parameters required by other tuning techniques. Our results demonstrate that soft prompts provide a modular and computationally efficient path toward improving LLM reliability. △ Less

Submitted 19 August, 2026; v1 submitted 30 May, 2026; originally announced June 2026.

Comments: 20 pages, 5 tables, 2 figures. Accepted for publication in DBSec 2026

Inverse Design of Metainterfaces for Static Friction Control: Beyond the Hertzian Limit

Authors: Jacopo Bilotto, Arnav Singhal, Joaquin Garcia-Suarez, Gaëtan Cortes, Lucas Fourel, Jean-François Molinari

Abstract: Programming the static friction of mechanical interfaces is critical for soft robotics, haptics, and precision gripping. Static friction is governed by the real contact area, and standard rough surfaces exhibit a linear area-load scaling inherent to classical Archard and Greenwood-Williamson models, severely restricting their functional range. Here, we propose a framework for the inverse design of… ▽ More Programming the static friction of mechanical interfaces is critical for soft robotics, haptics, and precision gripping. Static friction is governed by the real contact area, and standard rough surfaces exhibit a linear area-load scaling inherent to classical Archard and Greenwood-Williamson models, severely restricting their functional range. Here, we propose a framework for the inverse design of tribological metainterfaces engineered for programmable contact behaviors. By utilizing general axisymmetric asperities, we unlock nonlinear macroscopic responses unattainable by standard Hertzian contacts. To solve the inverse problem, we embed a fully differentiable contact mechanics engine within a neural network and a quadratic optimizer. We leverage regularized physical gradients to automatically discover non-standard topographies that reproduce complex target friction laws, with only a few asperities in unit cells. The predicted designs are strictly validated against high-fidelity Boundary Element Method (BEM) simulations. This framework bridges data-driven optimization and rigorous physics, offering a scale-invariant pathway for discovering functional tribological surfaces. △ Less

Submitted 19 May, 2026; v1 submitted 10 May, 2026; originally announced May 2026.

Comments: 19 pages, 8 figures

Phase-Based Bit Commitment Protocol

Authors: Janis Nötzel, Anshul Singhal, Peter van Loock

Abstract: With the rise of artificial intelligence and machine learning, a new wave of private information is being flushed into applications. This development raises privacy concerns, as private datasets can be stolen or abused for non-authorized purposes. Secure function computation aims to solve such problems by allowing a service provider to compute functions of datasets in the possession of a a data pr… ▽ More With the rise of artificial intelligence and machine learning, a new wave of private information is being flushed into applications. This development raises privacy concerns, as private datasets can be stolen or abused for non-authorized purposes. Secure function computation aims to solve such problems by allowing a service provider to compute functions of datasets in the possession of a a data provider without reading the data itself. A foundational primitive for such tasks is Bit Commitment (BC), which is known to be impossible to realize without added assumptions. Given the pressing nature of the topic, it is thus important to develop BC systems and prove their security under reasonable assumptions. In this work, we provide a novel quantum optical BC protocol that uses the added assumption that the network provider will secure transmission lines against eavesdropping. Under this added assumption, we prove security of our protocol in the honest but curious setting and discuss the hardness of Mayer's attack in the context of our protocol. △ Less

Submitted 18 February, 2026; originally announced February 2026.

Comments: 6 pages, one figure, accepted for presentation at IEEE ICC 2026

Stabilizing Transformer Training Through Consensus

Authors: Shyam Venkatasubramanian, Sean Moushegian, Michael Lin, Mir Park, Ankit Singhal, Connor Lee

Abstract: Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such overspecification by modifying the optimization procedure, fundamental architectural innovations to this end remain underexplored. In this work, we illustrate that th… ▽ More Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such overspecification by modifying the optimization procedure, fundamental architectural innovations to this end remain underexplored. In this work, we illustrate that the consensus mechanism, a drop-in replacement for attention, stabilizes transformer training across a wider effective range of learning rates. We formulate consensus as a graphical model and provide extensive empirical analysis demonstrating improved stability across learning rate sweeps on text, DNA, and protein modalities. We further propose a hybrid consensus-attention framework that preserves performance while improving stability. We provide theoretical analysis characterizing the properties of consensus. △ Less

Submitted 30 January, 2026; originally announced January 2026.

Primate-like perceptual decision making emerges through deep recurrent reinforcement learning

Authors: Nathan J. Wispinski, Scott A. Stone, Anthony Singhal, Patrick M. Pilarski, Craig S. Chapman

Abstract: Progress has led to a detailed understanding of the neural mechanisms that underlie decision making in primates. However, less is known about why such mechanisms are present in the first place. Theory suggests that primate decision making mechanisms, and their resultant behavioral abilities, emerged to maximize reward in the face of noisy, temporally evolving information. To test this theory, we t… ▽ More Progress has led to a detailed understanding of the neural mechanisms that underlie decision making in primates. However, less is known about why such mechanisms are present in the first place. Theory suggests that primate decision making mechanisms, and their resultant behavioral abilities, emerged to maximize reward in the face of noisy, temporally evolving information. To test this theory, we trained an end-to-end deep recurrent neural network using reinforcement learning on a noisy perceptual discrimination task. Networks learned several key abilities of primate-like decision making including trading off speed for accuracy, and flexibly changing their mind in the face of new information. Internal dynamics of these networks suggest that these abilities were supported by similar decision mechanisms as those observed in primate neurophysiological studies. These results provide experimental support for key pressures that gave rise to the primate ability to make flexible decisions. △ Less

Submitted 18 January, 2026; originally announced January 2026.

ARMARecon: An ARMA Convolutional Filter based Graph Neural Network for Neurodegenerative Dementias Classification

Authors: VSS Tejaswi Abburi, Ananya Singhal, Saurabh J. Shigwan, Nitin Kumar

Abstract: Early detection of neurodegenerative diseases such as Alzheimer's Disease (AD) and Frontotemporal Dementia (FTD) is essential for reducing the risk of progression to severe disease stages. As AD and FTD propagate along white-matter regions in a global, graph-dependent manner, graph-based neural networks are well suited to capture these patterns. Hence, we introduce ARMARecon, a unified graph learn… ▽ More Early detection of neurodegenerative diseases such as Alzheimer's Disease (AD) and Frontotemporal Dementia (FTD) is essential for reducing the risk of progression to severe disease stages. As AD and FTD propagate along white-matter regions in a global, graph-dependent manner, graph-based neural networks are well suited to capture these patterns. Hence, we introduce ARMARecon, a unified graph learning framework that integrates Autoregressive Moving Average (ARMA) graph filtering with a reconstruction-driven objective to enhance feature representation and improve classification accuracy. ARMARecon effectively models both local and global connectivity by leveraging 20-bin Fractional Anisotropy (FA) histogram features extracted from white-matter regions, while mitigating over-smoothing. Overall, ARMARecon achieves superior performance compared to state-of-the-art methods on the multi-site dMRI datasets ADNI and NIFD. △ Less

Submitted 17 January, 2026; originally announced January 2026.

Comments: Accepted at IEEE International Symposium on Biomedical Imaging (ISBI) 2026

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer

Authors: Raina Panda, Daniel Fein, Arpita Singhal, Mark Fiore, Maneesh Agrawala, Matyas Bohacek

Abstract: Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt engineering, all of which can be computationally expensive and may still entangle style with subject matter. In this paper, we introduce a training- and inference-light, interpretable method for representing and transferr… ▽ More Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt engineering, all of which can be computationally expensive and may still entangle style with subject matter. In this paper, we introduce a training- and inference-light, interpretable method for representing and transferring artistic style. Our approach leverages an art-specific Sparse Autoencoder (SAE) on top of latent embeddings of generative image models. Trained on artistic data, our SAE learns an emergent, largely disentangled set of stylistic and compositional concepts, corresponding to style-related elements pertaining brushwork, texture, and color palette, as well as semantic and structural concepts. We call it LouvreSAE and use it to construct style profiles: compact, decomposable steering vectors that enable style transfer without any model updates or optimization. Unlike prior concept-based style transfer methods, our method requires no fine-tuning, no LoRA training, and no additional inference passes, enabling direct steering of artistic styles from only a few reference images. We validate our method on ArtBench10, achieving or surpassing existing methods on style evaluations (VGG Style Loss and CLIP Score Style) while being 1.7-20x faster and, critically, interpretable. △ Less

Submitted 21 December, 2025; originally announced December 2025.

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost

Authors: Haojun Xia, Xiaoxia Wu, Jisen Li, Robert Wu, Junxiong Wang, Jue Wang, Chenxi Li, Aman Singhal, Alay Dilipbhai Shah, Alpay Ariyak, Donglin Zhuang, Zhongzhu Zhou, Ben Athiwaratkun, Zhen Zheng, Shuaiwen Leon Song

Abstract: The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for mixed-precision KV caching: Kitty. On the algorithm side, extensive experiments show that Dynamic Channel-wise Precision Boost -- which ranks Key-cache channels by sensi… ▽ More The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for mixed-precision KV caching: Kitty. On the algorithm side, extensive experiments show that Dynamic Channel-wise Precision Boost -- which ranks Key-cache channels by sensitivity and keeps only a small fraction at higher precision -- maintains near-zero loss in accuracy drop while approaching 2-bit memory. The main challenge is handling dynamic 4-bit channel boosts while keeping the page layout coalesced and the dequantization uniform, with no scattered reads or hard-coded masks. Kitty addresses these issues by decompose each mixed-precision Key page into two tensors with unified 2-bit precision. Based on this, Kitty provides a page-centric KV layout, Triton-compatible page dequantization kernels, and a lightweight runtime pipeline that preserves coalescing and avoids divergence. Across seven tasks and two model families (Qwen3, LLaMA3), Kitty cuts KV memory by nearly 8x with negligible accuracy loss, enabling up to 8x larger batches and 2.1x-4.1x higher throughput under the same memory budget. We release the full implementation of Kitty at https://github.com/Summer-Summer/Kitty. △ Less

Submitted 23 November, 2025; originally announced November 2025.

Ensemble Deep Learning Models for Early Detection of Meningitis in ICU: Multi-center Study

Authors: Han Ouyang, Ayush Singhal, Jesse Hamilton, Saeed Amal

Abstract: The stacking ensemble combining RF, LightGBM, and DNN performed well on internal test sets, exhibiting an NPV greater than 99.9% even with substantial class imbalance. While performance was lower on the external eICU cohort compared to the internal test sets, sensitivity remained robust. Therefore, the stacking ensemble may serve as a rule-out screening option for ERs and ICUs after additional pro… ▽ More The stacking ensemble combining RF, LightGBM, and DNN performed well on internal test sets, exhibiting an NPV greater than 99.9% even with substantial class imbalance. While performance was lower on the external eICU cohort compared to the internal test sets, sensitivity remained robust. Therefore, the stacking ensemble may serve as a rule-out screening option for ERs and ICUs after additional prospective multi-site validation studies for its efficacy in real-world. △ Less

Submitted 20 April, 2026; v1 submitted 16 October, 2025; originally announced October 2025.

From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding

Authors: Guangyu Sun, Archit Singhal, Burak Uzkent, Mubarak Shah, Chen Chen, Garin Kessler

Abstract: Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the model's context window. Existing solutions mitigate this issue by selecting a sparse set of frames, but such frame-wise selection discards essential temporal dynamic… ▽ More Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the model's context window. Existing solutions mitigate this issue by selecting a sparse set of frames, but such frame-wise selection discards essential temporal dynamics in long-form videos, leading to suboptimal reasoning about motion and event continuity. In this work, we systematically examine the role of temporal information and show that extending selection from isolated key frames to temporally coherent key clips improves video understanding. To maintain a fixed computational budget while accommodating the larger token footprint of clips, we introduce frame resolution as a controllable factor in frame selection, enabling a trade-off between spatial resolution and clip length. Building on this idea, we propose an adaptive clip length module that dynamically balances these factors to ensure a constant token count per video. Experiments on three long-form video benchmarks demonstrate that our training-free approach, F2C, outperforms uniform sampling by up to 8.1%, 5.6%, and 10.3% on Video-MME, LongVideoBench, and MLVU, respectively. These results highlight the importance of preserving temporal coherence in frame selection and provide a practical pathway for scaling VLMs to real-world video understanding applications. Project webpage is available at https://guangyusun.com/f2c . △ Less

Submitted 18 December, 2025; v1 submitted 2 October, 2025; originally announced October 2025.

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval

Authors: Pratik Shah, Rajat Ghosh, Aryan Singhal, Debojyoti Dutta

Abstract: General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities… ▽ More General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities, or natural language queries (for example, describing a task and retrieving the corresponding code). We present RANGER, a repository-level code retrieval agent designed to address both query types, filling a gap in recent works that have focused primarily on code-entity queries. We first present a tool that constructs a comprehensive knowledge graph of the entire repository, capturing hierarchical and cross-file dependencies down to the variable level, and augments graph nodes with textual descriptions and embeddings to bridge the gap between code and natural language. RANGER then operates on this graph through a dual-stage retrieval pipeline. Entity-based queries are answered through fast Cypher lookups, while natural language queries are handled by MCTS-guided graph exploration. We evaluate RANGER across four diverse benchmarks that represent core ASE tasks including code search, question answering, cross-file dependency retrieval, and repository-level code completion. On CodeSearchNet and RepoQA it outperforms retrieval baselines that use embeddings from strong models such as Qwen3-8B. On RepoBench, it achieves superior cross-file dependency retrieval over baselines, and on CrossCodeEval, pairing RANGER with BM25 delivers the highest exact match rate in code completion compared to other RAG methods. △ Less

Submitted 27 September, 2025; originally announced September 2025.

Comments: 24 pages, 4 figures

Analogy-Driven Financial Chain-of-Thought (AD-FCoT): A Prompting Approach for Financial Sentiment Analysis

Authors: Anmol Singhal Navya Singhal

Abstract: Financial news sentiment analysis is crucial for anticipating market movements. With the rise of AI techniques such as Large Language Models (LLMs), which demonstrate strong text understanding capabilities, there has been renewed interest in enhancing these systems. Existing methods, however, often struggle to capture the complex economic context of news and lack transparent reasoning, which under… ▽ More Financial news sentiment analysis is crucial for anticipating market movements. With the rise of AI techniques such as Large Language Models (LLMs), which demonstrate strong text understanding capabilities, there has been renewed interest in enhancing these systems. Existing methods, however, often struggle to capture the complex economic context of news and lack transparent reasoning, which undermines their reliability. We propose Analogy-Driven Financial Chain-of-Thought (AD-FCoT), a prompting framework that integrates analogical reasoning with chain-of-thought (CoT) prompting for sentiment prediction on historical financial news. AD-FCoT guides LLMs to draw parallels between new events and relevant historical scenarios with known outcomes, embedding these analogies into a structured, step-by-step reasoning chain. To our knowledge, this is among the first approaches to explicitly combine analogical examples with CoT reasoning in finance. Operating purely through prompting, AD-FCoT requires no additional training data or fine-tuning and leverages the model's internal financial knowledge to generate rationales that mirror human analytical reasoning. Experiments on thousands of news articles show that AD-FCoT outperforms strong baselines in sentiment classification accuracy and achieves substantially higher correlation with market returns. Its generated explanations also align with domain expertise, providing interpretable insights suitable for real-world financial analysis. △ Less

Submitted 15 September, 2025; originally announced September 2025.

Comments: IEEE AIxB 2025

BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning

Authors: Jinan Zhou, Rajat Ghosh, Vaishnavi Bhargava, Debojyoti Dutta, Aryan Singhal

Abstract: When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no model can simultaneously optimize for all three. We formally prove this trade-off and propose a principled framework named The BAR Theorem for LLM-application design. When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no model can simultaneously optimize for all three. We formally prove this trade-off and propose a principled framework named The BAR Theorem for LLM-application design. △ Less

Submitted 2 August, 2025; v1 submitted 30 July, 2025; originally announced July 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

From Legal Text to Tech Specs: Generative AI's Interpretation of Consent in Privacy Law

Authors: Aniket Kesari, Travis Breaux, Tom Norton, Sarah Santos, Anmol Singhal

Abstract: Privacy law and regulation have turned to "consent" as the legitimate basis for collecting and processing individuals' data. As governments have rushed to enshrine consent requirements in their privacy laws, such as the California Consumer Privacy Act (CCPA), significant challenges remain in understanding how these legal mandates are operationalized in software. The opaque nature of software devel… ▽ More Privacy law and regulation have turned to "consent" as the legitimate basis for collecting and processing individuals' data. As governments have rushed to enshrine consent requirements in their privacy laws, such as the California Consumer Privacy Act (CCPA), significant challenges remain in understanding how these legal mandates are operationalized in software. The opaque nature of software development processes further complicates this translation. To address this, we explore the use of Large Language Models (LLMs) in requirements engineering to bridge the gap between legal requirements and technical implementation. This study employs a three-step pipeline that involves using an LLM to classify software use cases for compliance, generating LLM modifications for non-compliant cases, and manually validating these changes against legal standards. Our preliminary findings highlight the potential of LLMs in automating compliance tasks, while also revealing limitations in their reasoning capabilities. By benchmarking LLMs against real-world use cases, this research provides insights into leveraging AI-driven solutions to enhance legal compliance of software. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Comments: 10 pages, 1 figure, 20th International Conference on Artificial Intelligence and Law (ICAIL 2025)

Requirements Elicitation Follow-Up Question Generation

Authors: Yuchen Shen, Anmol Singhal, Travis Breaux

Abstract: Interviews are a widely used technique in eliciting requirements to gather stakeholder needs, preferences, and expectations for a software system. Effective interviewing requires skilled interviewers to formulate appropriate interview questions in real time while facing multiple challenges, including lack of familiarity with the domain, excessive cognitive load, and information overload that hinde… ▽ More Interviews are a widely used technique in eliciting requirements to gather stakeholder needs, preferences, and expectations for a software system. Effective interviewing requires skilled interviewers to formulate appropriate interview questions in real time while facing multiple challenges, including lack of familiarity with the domain, excessive cognitive load, and information overload that hinders how humans process stakeholders' speech. Recently, large language models (LLMs) have exhibited state-of-the-art performance in multiple natural language processing tasks, including text summarization and entailment. To support interviewers, we investigate the application of GPT-4o to generate follow-up interview questions during requirements elicitation by building on a framework of common interviewer mistake types. In addition, we describe methods to generate questions based on interviewee speech. We report a controlled experiment to evaluate LLM-generated and human-authored questions with minimal guidance, and a second controlled experiment to evaluate the LLM-generated questions when generation is guided by interviewer mistake types. Our findings demonstrate that, for both experiments, the LLM-generated questions are no worse than the human-authored questions with respect to clarity, relevancy, and informativeness. In addition, LLM-generated questions outperform human-authored questions when guided by common mistakes types. This highlights the potential of using LLMs to help interviewers improve the quality and ease of requirements elicitation interviews in real time. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: 13 pages, 2 figures, accepted at the 33rd IEEE International Requirements Engineering 2025

Legal Requirements Translation from Law

Authors: Anmol Singhal, Travis Breaux

Abstract: Software systems must comply with legal regulations, which is a resource-intensive task, particularly for small organizations and startups lacking dedicated legal expertise. Extracting metadata from regulations to elicit legal requirements for software is a critical step to ensure compliance. However, it is a cumbersome task due to the length and complex nature of legal text. Although prior work h… ▽ More Software systems must comply with legal regulations, which is a resource-intensive task, particularly for small organizations and startups lacking dedicated legal expertise. Extracting metadata from regulations to elicit legal requirements for software is a critical step to ensure compliance. However, it is a cumbersome task due to the length and complex nature of legal text. Although prior work has pursued automated methods for extracting structural and semantic metadata from legal text, key limitations remain: they do not consider the interplay and interrelationships among attributes associated with these metadata types, and they rely on manual labeling or heuristic-driven machine learning, which does not generalize well to new documents. In this paper, we introduce an approach based on textual entailment and in-context learning for automatically generating a canonical representation of legal text, encodable and executable as Python code. Our representation is instantiated from a manually designed Python class structure that serves as a domain-specific metamodel, capturing both structural and semantic legal metadata and their interrelationships. This design choice reduces the need for large, manually labeled datasets and enhances applicability to unseen legislation. We evaluate our approach on 13 U.S. state data breach notification laws, demonstrating that our generated representations pass approximately 89.4% of test cases and achieve a precision and recall of 82.2 and 88.7, respectively. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: 13 pages, 7 figures, Accepted at the 33rd IEEE International Requirements Engineering 2025

Transferable Learning of Reaction Pathways from Geometric Priors

Authors: Juno Nam, Miguel Steiner, Max Misterka, Soojung Yang, Avni Singhal, Rafael Gómez-Bombarelli

Abstract: Identifying minimum-energy paths (MEPs) is crucial for understanding chemical reaction mechanisms but remains computationally demanding. We introduce MEPIN, a scalable machine-learning method for efficiently predicting MEPs from reactant and product configurations, without relying on transition-state geometries or pre-optimized reaction paths during training. The task is defined as predicting devi… ▽ More Identifying minimum-energy paths (MEPs) is crucial for understanding chemical reaction mechanisms but remains computationally demanding. We introduce MEPIN, a scalable machine-learning method for efficiently predicting MEPs from reactant and product configurations, without relying on transition-state geometries or pre-optimized reaction paths during training. The task is defined as predicting deviations from geometric interpolations along reaction coordinates. We address this task with a continuous reaction path model based on a symmetry-broken equivariant neural network that generates a flexible number of intermediate structures. The model is trained using an energy-based objective, with efficiency enhanced by incorporating geometric priors from geodesic interpolation as initial interpolations or pre-training objectives. Our approach generalizes across diverse chemical reactions and achieves accurate alignment with reference intrinsic reaction coordinates, as demonstrated on various small molecule reactions and [3+2] cycloadditions. Our method enables the exploration of large chemical reaction spaces with efficient, data-driven predictions of reaction pathways. △ Less

Submitted 21 April, 2025; originally announced April 2025.

Comments: 14 pages, 6 figures; Supporting Information in ancillary files

PatrolVision: Automated License Plate Recognition in the wild

Authors: Anmol Singhal Navya Singhal

Abstract: Adoption of AI driven techniques in public services remains low due to challenges related to accuracy and speed of information at population scale. Computer vision techniques for traffic monitoring have not gained much popularity despite their relative strength in areas such as autonomous driving. Despite large number of academic methods for Automatic License Plate Recognition (ALPR) systems, very… ▽ More Adoption of AI driven techniques in public services remains low due to challenges related to accuracy and speed of information at population scale. Computer vision techniques for traffic monitoring have not gained much popularity despite their relative strength in areas such as autonomous driving. Despite large number of academic methods for Automatic License Plate Recognition (ALPR) systems, very few provide an end to end solution for patrolling in the city. This paper presents a novel prototype for a low power GPU based patrolling system to be deployed in an urban environment on surveillance vehicles for automated vehicle detection, recognition and tracking. In this work, we propose a complete ALPR system for Singapore license plates having both single and double line creating our own YOLO based network. We focus on unconstrained capture scenarios as would be the case in real world application, where the license plate (LP) might be considerably distorted due to oblique views. In this work, we first detect the license plate from the full image using RFB-Net and rectify multiple distorted license plates in a single image. After that, the detected license plate image is fed to our network for character recognition. We evaluate the performance of our proposed system on a newly built dataset covering more than 16,000 images. The system was able to correctly detect license plates with 86\% precision and recognize characters of a license plate in 67\% of the test set, and 89\% accuracy with one incorrect character (partial match). We also test latency of our system and achieve 64FPS on Tesla P4 GPU △ Less

Submitted 14 April, 2025; originally announced April 2025.

Comments: Accepted in IEEE Southeast Con 2025. To be published in IEEEXplore

Semantic Search and Recommendation Algorithm

Authors: Aryan Duhan, Aryan Singhal, Shourya Sharma, Neeraj, Arti MK

Abstract: This paper introduces a new semantic search algorithm that uses Word2Vec and Annoy Index to improve the efficiency of information retrieval from large datasets. The proposed approach addresses the limitations of traditional search methods by offering enhanced speed, accuracy, and scalability. Testing on datasets up to 100GB demonstrates the method's effectiveness in processing vast amounts of data… ▽ More This paper introduces a new semantic search algorithm that uses Word2Vec and Annoy Index to improve the efficiency of information retrieval from large datasets. The proposed approach addresses the limitations of traditional search methods by offering enhanced speed, accuracy, and scalability. Testing on datasets up to 100GB demonstrates the method's effectiveness in processing vast amounts of data while maintaining high precision and performance. △ Less

Submitted 9 December, 2024; originally announced December 2024.

Comments: 6 pages, 5 Figures

DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA

Authors: Aman Patel, Arpita Singhal, Austin Wang, Anusri Pampari, Maya Kasowski, Anshul Kundaje

Abstract: Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn generalizable representations of diverse DNA elements, potentially enabling various genomic prediction, interpretation and design tasks. Despite their potential, existing benchmarks do not adequately ass… ▽ More Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn generalizable representations of diverse DNA elements, potentially enabling various genomic prediction, interpretation and design tasks. Despite their potential, existing benchmarks do not adequately assess the capabilities of DNALMs on key downstream applications involving an important class of non-coding DNA elements critical for regulating gene activity. In this study, we introduce DART-Eval, a suite of representative benchmarks specifically focused on regulatory DNA to evaluate model performance across zero-shot, probed, and fine-tuned scenarios against contemporary ab initio models as baselines. Our benchmarks target biologically meaningful downstream tasks such as functional sequence feature discovery, predicting cell-type specific regulatory activity, and counterfactual prediction of the impacts of genetic variants. We find that current DNALMs exhibit inconsistent performance and do not offer compelling gains over alternative baseline models for most tasks, while requiring significantly more computational resources. We discuss potentially promising modeling, data curation, and evaluation strategies for the next generation of DNALMs. Our code is available at https://github.com/kundajelab/DART-Eval. △ Less

Submitted 23 March, 2026; v1 submitted 6 December, 2024; originally announced December 2024.

Comments: NeurIPS Datasets and Benchmarks 2024

ThunderKittens: Simple, Fast, and Adorable AI Kernels

Authors: Benjamin F. Spector, Simran Arora, Aaryan Singhal, Daniel Y. Fu, Christopher Ré

Abstract: The challenge of mapping AI architectures to GPU hardware is creating a critical bottleneck in AI progress. Despite substantial efforts, hand-written custom kernels fail to meet their theoretical performance thresholds, even on well-established operations like linear attention. The diverse hardware capabilities of GPUs might suggest that we need a wide variety of techniques to achieve high perform… ▽ More The challenge of mapping AI architectures to GPU hardware is creating a critical bottleneck in AI progress. Despite substantial efforts, hand-written custom kernels fail to meet their theoretical performance thresholds, even on well-established operations like linear attention. The diverse hardware capabilities of GPUs might suggest that we need a wide variety of techniques to achieve high performance. However, our work explores whether a small number of key abstractions can drastically simplify the process. We present ThunderKittens (TK), a framework for writing performant AI kernels while remaining easy to use and maintain. Our abstractions map to the three levels of the GPU hierarchy: (1) at the warp-level, we provide 16x16 matrix tiles as basic data structures and PyTorch-like parallel compute operations over tiles, (2) at the thread-block level, we provide a template for overlapping asynchronous operations across parallel warps, and (3) at the grid-level, we provide support to help hide the block launch and tear-down, and memory costs. We show the value of TK by providing kernels that match or outperform prior kernels for a range of AI operations. We match CuBLAS and FlashAttention-3 on GEMM and attention inference performance and outperform the strongest baselines by $10-40\%$ on attention backwards, $8\times$ on state space models, and $14\times$ on linear attention. △ Less

Submitted 27 October, 2024; originally announced October 2024.

A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification

Authors: Aryan Singhal, Veronica Shao, Gary Sun, Ryan Ding, Jonathan Lu, Kevin Zhu

Abstract: The rise of digital misinformation has heightened interest in using multilingual Large Language Models (LLMs) for fact-checking. This study systematically evaluates translation bias and the effectiveness of LLMs for cross-lingual claim verification across 15 languages from five language families: Romance, Slavic, Turkic, Indo-Aryan, and Kartvelian. Using the XFACT dataset to assess their impact on… ▽ More The rise of digital misinformation has heightened interest in using multilingual Large Language Models (LLMs) for fact-checking. This study systematically evaluates translation bias and the effectiveness of LLMs for cross-lingual claim verification across 15 languages from five language families: Romance, Slavic, Turkic, Indo-Aryan, and Kartvelian. Using the XFACT dataset to assess their impact on accuracy and bias, we investigate two distinct translation methods: pre-translation and self-translation. We use mBERT's performance on the English dataset as a baseline to compare language-specific accuracies. Our findings reveal that low-resource languages exhibit significantly lower accuracy in direct inference due to underrepresentation in the training data. Furthermore, larger models demonstrate superior performance in self-translation, improving translation accuracy and reducing bias. These results highlight the need for balanced multilingual training, especially in low-resource languages, to promote equitable access to reliable fact-checking tools and minimize the risk of spreading misinformation in different linguistic contexts. △ Less

Submitted 14 October, 2024; originally announced October 2024.

Comments: Accepted to ATTRIB @ NeurIPS 2024

LoLCATs: On Low-Rank Linearizing of Large Language Models

Authors: Michael Zhang, Simran Arora, Rahul Chalamala, Alan Wu, Benjamin Spector, Aaryan Singhal, Krithik Ramesh, Christopher Ré

Abstract: Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However, linearizing LLMs often significantly degrades model quality, still requires training over billions of tokens, and remains limited to smaller 1.3B to 7B LLMs. W… ▽ More Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However, linearizing LLMs often significantly degrades model quality, still requires training over billions of tokens, and remains limited to smaller 1.3B to 7B LLMs. We thus propose Low-rank Linear Conversion via Attention Transfer (LoLCATs), a simple two-step method that improves LLM linearizing quality with orders of magnitudes less memory and compute. We base these steps on two findings. First, we can replace an LLM's softmax attentions with closely-approximating linear attentions, simply by training the linear attentions to match their softmax counterparts with an output MSE loss ("attention transfer"). Then, this enables adjusting for approximation errors and recovering LLM quality simply with low-rank adaptation (LoRA). LoLCATs significantly improves linearizing quality, training efficiency, and scalability. We significantly reduce the linearizing quality gap and produce state-of-the-art subquadratic LLMs from Llama 3 8B and Mistral 7B v0.1, leading to 20+ points of improvement on 5-shot MMLU. Furthermore, LoLCATs does so with only 0.2% of past methods' model parameters and 0.4% of their training tokens. Finally, we apply LoLCATs to create the first linearized 70B and 405B LLMs (50x larger than prior work). When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3.1 70B and 405B LLMs by 77.8% and 78.1% on 5-shot MMLU. △ Less

Submitted 5 March, 2025; v1 submitted 14 October, 2024; originally announced October 2024.

Comments: 58 pages, 25 figures, 26 tables, ICLR 2025

Symmetry-Constrained Generation of Diverse Low-Bandgap Molecules with Monte Carlo Tree Search

Authors: Akshay Subramanian, James Damewood, Juno Nam, Kevin P. Greenman, Avni P. Singhal, Rafael Gómez-Bombarelli

Abstract: Organic optoelectronic materials are a promising avenue for next-generation electronic devices due to their solution processability, mechanical flexibility, and tunable electronic properties. In particular, near-infrared (NIR) sensitive molecules have unique applications in night-vision equipment and biomedical imaging. Molecular engineering has played a crucial role in developing non-fullerene ac… ▽ More Organic optoelectronic materials are a promising avenue for next-generation electronic devices due to their solution processability, mechanical flexibility, and tunable electronic properties. In particular, near-infrared (NIR) sensitive molecules have unique applications in night-vision equipment and biomedical imaging. Molecular engineering has played a crucial role in developing non-fullerene acceptors (NFAs) such as the Y-series molecules, which have significantly improved the power conversion efficiency (PCE) of solar cells and enhanced spectral coverage in the NIR region. However, systematically designing molecules with targeted optoelectronic properties while ensuring synthetic accessibility remains a challenge. To address this, we leverage structural priors from domain-focused, patent-mined datasets of organic electronic molecules using a symmetry-aware fragment decomposition algorithm and a fragment-constrained Monte Carlo Tree Search (MCTS) generator. Our approach generates candidates that retain symmetry constraints from the patent dataset, while also exhibiting red-shifted absorption, as validated by TD-DFT calculations. △ Less

Submitted 12 December, 2024; v1 submitted 11 October, 2024; originally announced October 2024.

Data Poisoning and Leakage Analysis in Federated Learning

Authors: Wenqi Wei, Tiansheng Huang, Zachary Yahn, Anoop Singhal, Margaret Loper, Ling Liu

Abstract: Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em training data poisoning}. We first investigate training data privacy threat and present our observations on when and how training data may be leaked during the cou… ▽ More Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em training data poisoning}. We first investigate training data privacy threat and present our observations on when and how training data may be leaked during the course of federated training. One promising defense strategy is to perturb the raw gradient update by adding some controlled randomized noise prior to sharing during each round of federated learning. We discuss the importance of determining the proper amount of randomized noise and the proper location to add such noise for effective mitigation of gradient leakage threats against training data privacy. Then we will review and compare different training data poisoning threats and analyze why and when such data poisoning induced model Trojan attacks may lead to detrimental damage on the performance of the global model. We will categorize and compare representative poisoning attacks and the effectiveness of their mitigation techniques, delivering an in-depth understanding of the negative impact of data poisoning. Finally, we demonstrate the potential of dynamic model perturbation in simultaneously ensuring privacy protection, poisoning resilience, and model performance. The chapter concludes with a discussion on additional risk factors in federated learning, including the negative impact of skewness, data and algorithmic biases, as well as misinformation in training data. Powered by empirical evidence, our analytical study offers some transformative insights into effective privacy protection and security assurance strategies in attack-resilient federated learning. △ Less

Submitted 19 September, 2024; originally announced September 2024.

Comments: Chapter of Handbook of Trustworthy Federated Learning

A Comprehensive Survey on Synthetic Infrared Image synthesis

Authors: Avinash Upadhyay, Manoj sharma, Prerana Mukherjee, Amit Singhal, Brejesh Lall

Abstract: Synthetic infrared (IR) scene and target generation is an important computer vision problem as it allows the generation of realistic IR images and targets for training and testing of various applications, such as remote sensing, surveillance, and target recognition. It also helps reduce the cost and risk associated with collecting real-world IR data. This survey paper aims to provide a comprehensi… ▽ More Synthetic infrared (IR) scene and target generation is an important computer vision problem as it allows the generation of realistic IR images and targets for training and testing of various applications, such as remote sensing, surveillance, and target recognition. It also helps reduce the cost and risk associated with collecting real-world IR data. This survey paper aims to provide a comprehensive overview of the conventional mathematical modelling-based methods and deep learning-based methods used for generating synthetic IR scenes and targets. The paper discusses the importance of synthetic IR scene and target generation and briefly covers the mathematics of blackbody and grey body radiations, as well as IR image-capturing methods. The potential use cases of synthetic IR scenes and target generation are also described, highlighting the significance of these techniques in various fields. Additionally, the paper explores possible new ways of developing new techniques to enhance the efficiency and effectiveness of synthetic IR scenes and target generation while highlighting the need for further research to advance this field. △ Less

Submitted 14 August, 2024; v1 submitted 13 August, 2024; originally announced August 2024.

Comments: Submitted in Journal of Infrared Physics & Technology

Just read twice: closing the recall gap for recurrent language models

Authors: Simran Arora, Aman Timalsina, Aaryan Singhal, Benjamin Spector, Sabri Eyuboglu, Xinyi Zhao, Ashish Rao, Atri Rudra, Christopher Ré

Abstract: Recurrent large language models that compete with Transformers in language modeling perplexity are emerging at a rapid rate (e.g., Mamba, RWKV). Excitingly, these architectures use a constant amount of memory during inference. However, due to the limited memory, recurrent LMs cannot recall and use all the information in long contexts leading to brittle in-context learning (ICL) quality. A key chal… ▽ More Recurrent large language models that compete with Transformers in language modeling perplexity are emerging at a rapid rate (e.g., Mamba, RWKV). Excitingly, these architectures use a constant amount of memory during inference. However, due to the limited memory, recurrent LMs cannot recall and use all the information in long contexts leading to brittle in-context learning (ICL) quality. A key challenge for efficient LMs is selecting what information to store versus discard. In this work, we observe the order in which information is shown to the LM impacts the selection difficulty. To formalize this, we show that the hardness of information recall reduces to the hardness of a problem called set disjointness (SD), a quintessential problem in communication complexity that requires a streaming algorithm (e.g., recurrent model) to decide whether inputted sets are disjoint. We empirically and theoretically show that the recurrent memory required to solve SD changes with set order, i.e., whether the smaller set appears first in-context. Our analysis suggests, to mitigate the reliance on data order, we can put information in the right order in-context or process prompts non-causally. Towards that end, we propose: (1) JRT-Prompt, where context gets repeated multiple times in the prompt, effectively showing the model all data orders. This gives $11.0 \pm 1.3$ points of improvement, averaged across $16$ recurrent LMs and the $6$ ICL tasks, with $11.9\times$ higher throughput than FlashAttention-2 for generation prefill (length $32$k, batch size $16$, NVidia H100). We then propose (2) JRT-RNN, which uses non-causal prefix-linear-attention to process prompts and provides $99\%$ of Transformer quality at $360$M params., $30$B tokens and $96\%$ at $1.3$B params., $50$B tokens on average across the tasks, with $19.2\times$ higher throughput for prefill than FA2. △ Less

Submitted 7 July, 2024; originally announced July 2024.

Generating Clarification Questions for Disambiguating Contracts

Authors: Anmol Singhal, Chirag Jain, Preethu Rose Anish, Arkajyoti Chakraborty, Smita Ghaisas

Abstract: Enterprises frequently enter into commercial contracts that can serve as vital sources of project-specific requirements. Contractual clauses are obligatory, and the requirements derived from contracts can detail the downstream implementation activities that non-legal stakeholders, including requirement analysts, engineers, and delivery personnel, need to conduct. However, comprehending contracts i… ▽ More Enterprises frequently enter into commercial contracts that can serve as vital sources of project-specific requirements. Contractual clauses are obligatory, and the requirements derived from contracts can detail the downstream implementation activities that non-legal stakeholders, including requirement analysts, engineers, and delivery personnel, need to conduct. However, comprehending contracts is cognitively demanding and error-prone for such stakeholders due to the extensive use of Legalese and the inherent complexity of contract language. Furthermore, contracts often contain ambiguously worded clauses to ensure comprehensive coverage. In contrast, non-legal stakeholders require a detailed and unambiguous comprehension of contractual clauses to craft actionable requirements. In this work, we introduce a novel legal NLP task that involves generating clarification questions for contracts. These questions aim to identify contract ambiguities on a document level, thereby assisting non-legal stakeholders in obtaining the necessary details for eliciting requirements. This task is challenged by three core issues: (1) data availability, (2) the length and unstructured nature of contracts, and (3) the complexity of legal text. To address these issues, we propose ConRAP, a retrieval-augmented prompting framework for generating clarification questions to disambiguate contractual text. Experiments conducted on contracts sourced from the publicly available CUAD dataset show that ConRAP with ChatGPT can detect ambiguities with an F2 score of 0.87. 70% of the generated clarification questions are deemed useful by human evaluators. △ Less

Submitted 12 March, 2024; originally announced March 2024.

Comments: 9 pages, 3 figures, accepted to LREC-COLING 2024

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding, Xinyang Geng, Fred Alcober, Roy Frostig, Mark Omernick, Lexi Walker, Cosmin Paduraru, Christina Sorokin, Andrea Tacchetti, Colin Gaffney, Samira Daruki, Olcan Sercinoglu, Zach Gleicher, Juliette Love , et al. (1112 additional authors not shown)

Abstract: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February… ▽ More In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content. △ Less

Submitted 16 December, 2024; v1 submitted 8 March, 2024; originally announced March 2024.

Dealing with Data for RE: Mitigating Challenges while using NLP and Generative AI

Authors: Smita Ghaisas, Anmol Singhal

Abstract: Across the dynamic business landscape today, enterprises face an ever-increasing range of challenges. These include the constantly evolving regulatory environment, the growing demand for personalization within software applications, and the heightened emphasis on governance. In response to these multifaceted demands, large enterprises have been adopting automation that spans from the optimization… ▽ More Across the dynamic business landscape today, enterprises face an ever-increasing range of challenges. These include the constantly evolving regulatory environment, the growing demand for personalization within software applications, and the heightened emphasis on governance. In response to these multifaceted demands, large enterprises have been adopting automation that spans from the optimization of core business processes to the enhancement of customer experiences. Indeed, Artificial Intelligence (AI) has emerged as a pivotal element of modern software systems. In this context, data plays an indispensable role. AI-centric software systems based on supervised learning and operating at an industrial scale require large volumes of training data to perform effectively. Moreover, the incorporation of generative AI has led to a growing demand for adequate evaluation benchmarks. Our experience in this field has revealed that the requirement for large datasets for training and evaluation introduces a host of intricate challenges. This book chapter explores the evolving landscape of Software Engineering (SE) in general, and Requirements Engineering (RE) in particular, in this era marked by AI integration. We discuss challenges that arise while integrating Natural Language Processing (NLP) and generative AI into enterprise-critical software systems. The chapter provides practical insights, solutions, and examples to equip readers with the knowledge and tools necessary for effectively building solutions with NLP at their cores. We also reflect on how these text data-centric tasks sit together with the traditional RE process. We also highlight new RE tasks that may be necessary for handling the increasingly important text data-centricity involved in developing software systems. △ Less

Submitted 28 February, 2024; v1 submitted 26 February, 2024; originally announced February 2024.

Comments: 24 pages, 2 figures, to be published in NLP for Requirements Engineering Book

Domain-Independent Disperse and Pick method for Robotic Grasping

Authors: Prem Raj, Aniruddha Singhal, Vipul Sanap, L. Behera, Rajesh Sinha

Abstract: Picking unseen objects from clutter is a difficult problem because of the variability in objects (shape, size, and material) and occlusion due to clutter. As a result, it becomes difficult for grasping methods to segment the objects properly and they fail to singulate the object to be picked. This may result in grasp failure or picking of multiple objects together in a single attempt. A push-to-mo… ▽ More Picking unseen objects from clutter is a difficult problem because of the variability in objects (shape, size, and material) and occlusion due to clutter. As a result, it becomes difficult for grasping methods to segment the objects properly and they fail to singulate the object to be picked. This may result in grasp failure or picking of multiple objects together in a single attempt. A push-to-move action by the robot will be beneficial to disperse the objects in the workspace and thus assist the grasping and vision algorithm. We propose a disperse and pick method for domain-independent robotic grasping in a highly cluttered heap of objects. The novel contribution of our framework is the introduction of a heuristic clutter removal method that does not require deep learning and can work on unseen objects. At each iteration of the algorithm, the robot either performs a push-to-move action or a grasp action based on the estimated clutter profile. For grasp planning, we present an improved and adaptive version of a recent domain-independent grasping method. The efficacy of the integrated system is demonstrated in simulation as well as in the real-world. △ Less

Submitted 19 December, 2023; originally announced December 2023.

Comments: Published at 2022 International Joint Conference on Neural Networks (IJCNN)

Journal ref: 10.1109/IJCNN55064.2022.9892672

Gemini: A Family of Highly Capable Multimodal Models

Authors: Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazaridou, Orhan Firat, James Molloy, Michael Isard, Paul R. Barham, Tom Hennigan, Benjamin Lee , et al. (1326 additional authors not shown)

Abstract: This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultr… ▽ More This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI. △ Less

Submitted 9 May, 2025; v1 submitted 18 December, 2023; originally announced December 2023.

Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media

Authors: Jhuma Kabir Mim, Mourad Oussalah, Akash Singhal

Abstract: In today's age, social media reigns as the paramount communication platform, providing individuals with the avenue to express their conjectures, intellectual propositions, and reflections. Unfortunately, this freedom often comes with a downside as it facilitates the widespread proliferation of hate speech and offensive content, leaving a deleterious impact on our world. Thus, it becomes essential… ▽ More In today's age, social media reigns as the paramount communication platform, providing individuals with the avenue to express their conjectures, intellectual propositions, and reflections. Unfortunately, this freedom often comes with a downside as it facilitates the widespread proliferation of hate speech and offensive content, leaving a deleterious impact on our world. Thus, it becomes essential to discern and eradicate such offensive material from the realm of social media. This article delves into the comprehensive results and key revelations from the HASOC-2023 offensive language identification result. The primary emphasis is placed on the meticulous detection of hate speech within the linguistic domains of Bengali, Assamese, and Bodo, forming the framework for Task 4: Annihilate Hates. In this work, we used BERT models, including XML-Roberta, L3-cube, IndicBERT, BenglaBERT, and BanglaHateBERT. The research outcomes were promising and showed that XML-Roberta-lagre performed better than monolingual models in most cases. Our team 'TeamBD' achieved rank 3rd for Task 4 - Assamese, & 5th for Bengali. △ Less

Submitted 16 December, 2023; originally announced December 2023.

Comments: 9 pages, 1 figure, 5 tables

Towards Mitigating Perceived Unfairness in Contracts from a Non-Legal Stakeholder's Perspective

Authors: Anmol Singhal, Preethu Rose Anish, Shirish Karande, Smita Ghaisas

Abstract: Commercial contracts are known to be a valuable source for deriving project-specific requirements. However, contract negotiations mainly occur among the legal counsel of the parties involved. The participation of non-legal stakeholders, including requirement analysts, engineers, and solution architects, whose primary responsibility lies in ensuring the seamless implementation of contractual terms,… ▽ More Commercial contracts are known to be a valuable source for deriving project-specific requirements. However, contract negotiations mainly occur among the legal counsel of the parties involved. The participation of non-legal stakeholders, including requirement analysts, engineers, and solution architects, whose primary responsibility lies in ensuring the seamless implementation of contractual terms, is often indirect and inadequate. Consequently, a significant number of sentences in contractual clauses, though legally accurate, can appear unfair from an implementation perspective to non-legal stakeholders. This perception poses a problem since requirements indicated in the clauses are obligatory and can involve punitive measures and penalties if not implemented as committed in the contract. Therefore, the identification of potentially unfair clauses in contracts becomes crucial. In this work, we conduct an empirical study to analyze the perspectives of different stakeholders regarding contractual fairness. We then investigate the ability of Pre-trained Language Models (PLMs) to identify unfairness in contractual sentences by comparing chain of thought prompting and semi-supervised fine-tuning approaches. Using BERT-based fine-tuning, we achieved an accuracy of 84% on a dataset consisting of proprietary contracts. It outperformed chain of thought prompting using Vicuna-13B by a margin of 9%. △ Less

Submitted 3 December, 2023; originally announced December 2023.

Comments: 9 pages, 2 figures, to be published in Natural Legal Language Processing Workshop at EMNLP 2023

Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations

Authors: Sayak Mukherjee, Ramij R. Hossain, Sheik M. Mohiuddin, Yuan Liu, Wei Du, Veronica Adetola, Rohit A. Jinsiwale, Qiuhua Huang, Tianzhixi Yin, Ankit Singhal

Abstract: Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs). This paper (1) presents resilient control design in presence of adversarial cyber-events, and proposes a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issue… ▽ More Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs). This paper (1) presents resilient control design in presence of adversarial cyber-events, and proposes a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issues regarding data sharing in multi-party-owned networked grids, and (2) transfers learned controls from simulation to hardware-in-the-loop test-bed, thereby bridging the gap between simulation and real world. With these multi-prong objectives, first, we formulate a reinforcement learning (RL) training setup generating episodic trajectories with adversaries (attack signal) injected at the primary controllers of the grid forming (GFM) inverters where RL agents (or controllers) are being trained to mitigate the injected attacks. For networked microgrids, the horizontal Fed-RL method involving distinct independent environments is not appropriate, leading us to develop vertical variant Federated Soft Actor-Critic (FedSAC) algorithm to grasp the interconnected dynamics of networked microgrid. Next, utilizing OpenAI Gym interface, we built a custom simulation set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark test systems comprising 3 interconnected microgrids. Finally, the learned policies in simulation world are transferred to the real-time hardware-in-the-loop test-bed set-up developed using high-fidelity Hypersim platform. Experiments show that the simulator-trained RL controllers produce convincing results with the real-time test-bed set-up, validating the minimization of sim-to-real gap. △ Less

Submitted 20 November, 2023; originally announced November 2023.

Comments: 10 pages, 7 figures

Journal ref: IEEE Transactions on Smart Grid ( Volume: 16, Issue: 2, March 2025)

Real-time Control of Electric Autonomous Mobility-on-Demand Systems via Graph Reinforcement Learning

Authors: Aaryan Singhal, Daniele Gammelli, Justin Luke, Karthik Gopalakrishnan, Dominik Helmreich, Marco Pavone

Abstract: Operators of Electric Autonomous Mobility-on-Demand (E-AMoD) fleets need to make several real-time decisions such as matching available vehicles to ride requests, rebalancing idle vehicles to areas of high demand, and charging vehicles to ensure sufficient range. While this problem can be posed as a linear program that optimizes flows over a space-charge-time graph, the size of the resulting optim… ▽ More Operators of Electric Autonomous Mobility-on-Demand (E-AMoD) fleets need to make several real-time decisions such as matching available vehicles to ride requests, rebalancing idle vehicles to areas of high demand, and charging vehicles to ensure sufficient range. While this problem can be posed as a linear program that optimizes flows over a space-charge-time graph, the size of the resulting optimization problem does not allow for real-time implementation in realistic settings. In this work, we present the E-AMoD control problem through the lens of reinforcement learning and propose a graph network-based framework to achieve drastically improved scalability and superior performance over heuristics. Specifically, we adopt a bi-level formulation where we (1) leverage a graph network-based RL agent to specify a desired next state in the space-charge graph, and (2) solve more tractable linear programs to best achieve the desired state while ensuring feasibility. Experiments using real-world data from San Francisco and New York City show that our approach achieves up to 89% of the profits of the theoretically-optimal solution while achieving more than a 100x speedup in computational time. We further highlight promising zero-shot transfer capabilities of our learned policy on tasks such as inter-city generalization and service area expansion, thus showing the utility, scalability, and flexibility of our framework. Finally, our approach outperforms the best domain-specific heuristics with comparable runtimes, with an increase in profits by up to 3.2x. △ Less

Submitted 3 April, 2024; v1 submitted 9 November, 2023; originally announced November 2023.

Comments: 9 pages, revised SF travel data, includes additional experimental results, content and clarification revisions per reviewer feedback, and typo fixes

Journal ref: 2024 European Control Conference (ECC), pp. 1407-1414, 2024

Multidimensional well-being of US households at a fine spatial scale using fused household surveys: fusionACS

Authors: Kevin Ummel, Miguel Poblete-Cazenave, Karthik Akkiraju, Nick Graetz, Hero Ashman, Cora Kingdon, Steven Herrera Tenorio, Aaryaman "Sunny" Singhal, Daniel Aldana Cohen, Narasimha D. Rao

Abstract: Social science often relies on surveys of households and individuals. Dozens of such surveys are regularly administered by the U.S. government. However, they field independent, unconnected samples with specialized questions, limiting research questions to those that can be answered by a single survey. The fusionACS project seeks to integrate data from multiple U.S. household surveys by statistical… ▽ More Social science often relies on surveys of households and individuals. Dozens of such surveys are regularly administered by the U.S. government. However, they field independent, unconnected samples with specialized questions, limiting research questions to those that can be answered by a single survey. The fusionACS project seeks to integrate data from multiple U.S. household surveys by statistically "fusing" variables from "donor" surveys onto American Community Survey (ACS) microdata. This results in an integrated microdataset of household attributes and well-being dimensions that can be analyzed to address research questions in ways that are not currently possible. The presented data comprise the fusion onto the ACS of select donor variables from the Residential Energy Consumption Survey (RECS) of 2015, the National Household Transportation Survey (NHTS) of 2017, the American Housing Survey (AHS) of 2019, and the Consumer Expenditure Survey - Interview (CEI) for the years 2015-2019. The underlying statistical techniques are included in an open-source $R$ package, fusionModel, that provides generic tools for the creation, analysis, and validation of fused microdata. △ Less

Submitted 15 September, 2023; originally announced September 2023.

Comments: 35 pages, 6 figures

Towards FATE in AI for Social Media and Healthcare: A Systematic Review

Authors: Aditya Singhal, Hasnaat Tanveer, Vijay Mago

Abstract: As artificial intelligence (AI) systems become more prevalent, ensuring fairness in their design becomes increasingly important. This survey focuses on the subdomains of social media and healthcare, examining the concepts of fairness, accountability, transparency, and ethics (FATE) within the context of AI. We explore existing research on FATE in AI, highlighting the benefits and limitations of cu… ▽ More As artificial intelligence (AI) systems become more prevalent, ensuring fairness in their design becomes increasingly important. This survey focuses on the subdomains of social media and healthcare, examining the concepts of fairness, accountability, transparency, and ethics (FATE) within the context of AI. We explore existing research on FATE in AI, highlighting the benefits and limitations of current solutions, and provide future research directions. We found that statistical and intersectional fairness can support fairness in healthcare on social media platforms, and transparency in AI is essential for accountability. While solutions like simulation, data analytics, and automated systems are widely used, their effectiveness can vary, and keeping up-to-date with the latest research is crucial. △ Less

Submitted 5 June, 2023; originally announced June 2023.

NODDLE: Node2vec based deep learning model for link prediction

Authors: Kazi Zainab Khanam, Aditya Singhal, Vijay Mago

Abstract: Computing the probability of an edge's existence in a graph network is known as link prediction. While traditional methods calculate the similarity between two given nodes in a static network, recent research has focused on evaluating networks that evolve dynamically. Although deep learning techniques and network representation learning algorithms, such as node2vec, show remarkable improvements in… ▽ More Computing the probability of an edge's existence in a graph network is known as link prediction. While traditional methods calculate the similarity between two given nodes in a static network, recent research has focused on evaluating networks that evolve dynamically. Although deep learning techniques and network representation learning algorithms, such as node2vec, show remarkable improvements in prediction accuracy, the Stochastic Gradient Descent (SGD) method of node2vec tends to fall into a mediocre local optimum value due to a shortage of prior network information, resulting in failure to capture the global structure of the network. To tackle this problem, we propose NODDLE (integration of NOde2vec anD Deep Learning mEthod), a deep learning model which incorporates the features extracted by node2vec and feeds them into a four layer hidden neural network. NODDLE takes advantage of adaptive learning optimizers such as Adam, Adamax, Adadelta, and Adagrad to improve the performance of link prediction. Experimental results show that this method yields better results than the traditional methods on various social network datasets. △ Less

Submitted 25 May, 2023; originally announced May 2023.

Journal ref: In: Big Data Technologies and Applications. BDTA BDTA 2022 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 480. Springer, Cham

Analysis of h-index for research awards

Authors: Aashay Singhal, Kamalakar Karlapalem

Abstract: In order to advance academic research, it is important to assess and evaluate the academic influence of researchers and the findings they produce. Citation metrics are universally used methods to evaluate researchers. Amongst the several variations of citation metrics, the h-index proposed by Hirsch has become the leading measure. Recent work shows that h-index is not an effective measure to deter… ▽ More In order to advance academic research, it is important to assess and evaluate the academic influence of researchers and the findings they produce. Citation metrics are universally used methods to evaluate researchers. Amongst the several variations of citation metrics, the h-index proposed by Hirsch has become the leading measure. Recent work shows that h-index is not an effective measure to determine scientific impact - due to changing authorship patterns. This can be mitigated by using h-index of a paper to compute h- index of an author. We show that using fractional allocation of h-index gives better results. In this work, we reapply two indices based on the h-index of a single paper. The indices are referred to as: hp-index and hp-frac-index. We run large-scale experiments in three different fields with about a million publications and 3,000 authors. We also compare h-index of a paper with nine h-index like metrics. Our experiments show that hp-frac-index provides a unique ranking when compared to h-index. It also performs better than h-index in providing higher ranks to the awarded researcher. △ Less

Submitted 17 May, 2023; v1 submitted 5 May, 2023; originally announced May 2023.

Wobble control of a pendulum actuated spherical robot

Authors: Animesh Singhal, Sahil Modi, Abhishek Gupta, Leena Vachhani

Abstract: Spherical robots can conduct surveillance in hostile, cluttered environments without being damaged, as their protective shell can safely house sensors such as cameras. However, lateral oscillations, also known as wobble, occur when these sphere-shaped robots operate at low speeds, leading to shaky camera feedback. These oscillations in a pendulum-actuated spherical robot are caused by the coupling… ▽ More Spherical robots can conduct surveillance in hostile, cluttered environments without being damaged, as their protective shell can safely house sensors such as cameras. However, lateral oscillations, also known as wobble, occur when these sphere-shaped robots operate at low speeds, leading to shaky camera feedback. These oscillations in a pendulum-actuated spherical robot are caused by the coupling between the forward and steering motions due to nonholonomic constraints. Designing a controller to limit wobbling in these robots is challenging due to their underactuated nature. We propose a model-based controller to navigate a pendulum-actuated spherical robot using wobble-free turning maneuvers consisting of circular arcs and straight lines. The model is developed using Lagrange-D'Alembert equations and accounts for the coupled forward and steering motions. The model is further analyzed to derive expressions for radius of curvature, precession rate, wobble amplitude, and wobble frequency during circular motions. Finally, we design an input-output feedback linearization-based controller to control the robot's heading direction and wobble. Overall, the proposed controller enables a teleoperator to command a specific forward velocity and pendulum angle as per the desired turning radius while limiting the robot's lateral oscillations to enhance the quality of camera feedback. △ Less

Submitted 16 January, 2023; originally announced January 2023.

Comments: The length of the research paper is 20 pages, and it contains 15 graphs or illustrations

Pendulum Actuated Spherical Robot: Dynamic Modeling & Analysis for Wobble & Precession

Authors: Animesh Singhal, Sahil Modi, Abhishek Gupta, Leena Vachhani, Omkar A. Ghag

Abstract: A spherical robot has many practical advantages as the entire electronics are protected within a hull and can be carried easily by any Unmanned Aerial Vehicle (UAV). However, its use is limited due to finding mounts for sensors. Pendulum actuated spherical robot provides space for mounting sensors at the yoke. We study the non-linear dynamics of a pendulum-actuated spherical robot to analyze the d… ▽ More A spherical robot has many practical advantages as the entire electronics are protected within a hull and can be carried easily by any Unmanned Aerial Vehicle (UAV). However, its use is limited due to finding mounts for sensors. Pendulum actuated spherical robot provides space for mounting sensors at the yoke. We study the non-linear dynamics of a pendulum-actuated spherical robot to analyze the dynamics of internal assembly (yoke) for mounting sensors. For such robots, we provide a coupled dynamic model that takes care of the relationship between forward and sideways motion. We further demonstrate the effects of wobbling and precession captured by our model when the bot is controlled to execute a turning maneuver while moving with a moderate forward velocity, a practical situation encountered by spherical robots moving in an indoor setting. A simulation setup based on the developed model provides visualization of the spherical robot motion. △ Less

Submitted 14 January, 2023; originally announced January 2023.

Comments: The paper has been accepted to the 22nd IFAC International Symposium on Automatic Control in Aerospace (ACA) 2022. It consists of 6 pages and 15 figures

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning

Authors: Sayak Mukherjee, Ramij R. Hossain, Yuan Liu, Wei Du, Veronica Adetola, Sheik M. Mohiuddin, Qiuhua Huang, Tianzhixi Yin, Ankit Singhal

Abstract: This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids. We formulate a resilient reinforcement learning (RL) training setup which (a) generates episodic trajectories injecting adversarial actions at primary control reference signals of the grid forming (GFM) inverters and (b) trains the RL agents (or controllers) to… ▽ More This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids. We formulate a resilient reinforcement learning (RL) training setup which (a) generates episodic trajectories injecting adversarial actions at primary control reference signals of the grid forming (GFM) inverters and (b) trains the RL agents (or controllers) to alleviate the impact of the injected adversaries. To circumvent data-sharing issues and concerns for proprietary privacy in multi-party-owned networked grids, we bring in the aspects of federated machine learning and propose a novel Fed-RL algorithm to train the RL agents. To this end, the conventional horizontal Fed-RL approaches using decoupled independent environments fail to capture the coupled dynamics in a networked microgrid, which leads us to propose a multi-agent vertically federated variation of actor-critic algorithms, namely federated soft actor-critic (FedSAC) algorithm. We created a customized simulation setup encapsulating microgrid dynamics in the GridLAB-D/HELICS co-simulation platform compatible with the OpenAI Gym interface for training RL agents. Finally, the proposed methodology is validated with numerical examples of modified IEEE 123-bus benchmark test systems consisting of three coupled microgrids. △ Less

Submitted 17 December, 2022; originally announced December 2022.

Comments: 13 pages, 5 figures

Journal ref: 2023 IEEE Power & Energy Society General Meeting (PESGM)

Task Transfer and Domain Adaptation for Zero-Shot Question Answering

Authors: Xiang Pan, Alex Sheng, David Shimshoni, Aditya Singhal, Sara Rosenthal, Avirup Sil

Abstract: Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available. To address this, we use supervised pretraining on source-domain data to reduce sample complexity on domain-specific downstream tasks. We evaluate zero-shot perf… ▽ More Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available. To address this, we use supervised pretraining on source-domain data to reduce sample complexity on domain-specific downstream tasks. We evaluate zero-shot performance on domain-specific reading comprehension tasks by combining task transfer with domain adaptation to fine-tune a pretrained model with no labelled data from the target task. Our approach outperforms Domain-Adaptive Pretraining on downstream domain-specific reading comprehension tasks in 3 out of 4 domains. △ Less

Submitted 14 June, 2022; originally announced June 2022.

Comments: NAACL 2022 Deep Learning for Low-Resource NLP Workshop Paper

MSC Class: 68T50 ACM Class: I.2.7