Showing 1–50 of 79 results for author: Verma, N

Arc Gradient Descent: A Mathematically Derived Reformulation of Gradient Descent with Phase-Aware, User-Controlled Step Dynamics

Authors: Nikhil Verma, Joonas Linnosmaa, Leonardo Espinosa-Leal, Napat Vajragupta

Abstract: The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow,… ▽ More The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow, curved valley, across dimensions ranging from 2D to 1000D and an extreme case of 50,000D. Two configurations were evaluated to eliminate learning-rate bias: (i) both using ArcGD's effective learning rate and (ii) both using Adam's default learning rate. ArcGD consistently outperformed Adam under the first setting and, although slower under the second, achieved superior final solutions in most cases. In the second evaluation, ArcGD is evaluated against state-of-the-art optimizers (Adam, AdamW, Lion, SGD) on the CIFAR-10 image classification dataset across 8 diverse MLP architectures ranging from 1 to 5 hidden layers. ArcGD achieved the highest average test accuracy (50.7%) at 20,000 iterations, outperforming AdamW (46.6%), Adam (46.8%), SGD (49.6%), and Lion (43.4%), winning or tying on 6 of 8 architectures. Notably, while Adam and AdamW showed strong early convergence at 5,000 iterations, but regressed with extended training, whereas ArcGD continued improving, demonstrating generalization and resistance to overfitting without requiring early stopping tuning. Strong performance on geometric stress tests and standard deep-learning benchmarks indicates broad applicability, highlighting the need for further exploration. Moreover, it is also shown that a limiting variant of ArcGD can be interpreted as a sign-based momentum-like update, highlighting conceptual connections between the inherent mechanisms of ArcGD and the Lion optimiser. △ Less

Submitted 20 December, 2025; v1 submitted 7 December, 2025; originally announced December 2025.

Comments: 80 pages, 6 tables, 2 figures, 5 appendices, proof-of-concept

Stacked Ensemble of Fine-Tuned CNNs for Knee Osteoarthritis Severity Grading

Authors: Adarsh Gupta, Japleen Kaur, Tanvi Doshi, Teena Sharma, Nishchal K. Verma, Shantaram Vasikarla

Abstract: Knee Osteoarthritis (KOA) is a musculoskeletal condition that can cause significant limitations and impairments in daily activities, especially among older individuals. To evaluate the severity of KOA, typically, X-ray images of the affected knee are analyzed, and a grade is assigned based on the Kellgren-Lawrence (KL) grading system, which classifies KOA severity into five levels, ranging from 0… ▽ More Knee Osteoarthritis (KOA) is a musculoskeletal condition that can cause significant limitations and impairments in daily activities, especially among older individuals. To evaluate the severity of KOA, typically, X-ray images of the affected knee are analyzed, and a grade is assigned based on the Kellgren-Lawrence (KL) grading system, which classifies KOA severity into five levels, ranging from 0 to 4. This approach requires a high level of expertise and time and is susceptible to subjective interpretation, thereby introducing potential diagnostic inaccuracies. To address this problem a stacked ensemble model of fine-tuned Convolutional Neural Networks (CNNs) was developed for two classification tasks: a binary classifier for detecting the presence of KOA, and a multiclass classifier for precise grading across the KL spectrum. The proposed stacked ensemble model consists of a diverse set of pre-trained architectures, including MobileNetV2, You Only Look Once (YOLOv8), and DenseNet201 as base learners and Categorical Boosting (CatBoost) as the meta-learner. This proposed model had a balanced test accuracy of 73% in multiclass classification and 87.5% in binary classification, which is higher than previous works in extant literature. △ Less

Submitted 27 November, 2025; originally announced November 2025.

Comments: Accepted and Presented at IEEE UEMCON, IBM T.J. Watson Research Center, New York, USA, 2024

Quality-Aware Translation Tagging in Multilingual RAG system

Authors: Hoyeon Moon, Byeolhee Kim, Nikhil Verma

Abstract: Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translation quality degrades response generation performance. Existing approaches either assume sufficient translation quality or utilize the rewriting method, which introduces factual distortion and hallucinations. To mitigate th… ▽ More Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translation quality degrades response generation performance. Existing approaches either assume sufficient translation quality or utilize the rewriting method, which introduces factual distortion and hallucinations. To mitigate these problems, we propose Quality-Aware Translation Tagging in mRAG (QTT-RAG), which explicitly evaluates translation quality along three dimensions-semantic equivalence, grammatical accuracy, and naturalness&fluency-and attach these scores as metadata without altering the original content. We evaluate QTT-RAG against CrossRAG and DKM-RAG as baselines in two open-domain QA benchmarks (XORQA, MKQA) using six instruction-tuned LLMs ranging from 2.4B to 14B parameters, covering two low-resource languages (Korean and Finnish) and one high-resource language (Chinese). QTT-RAG outperforms the baselines by preserving factual integrity while enabling generator models to make informed decisions based on translation reliability. This approach allows for effective usage of cross-lingual documents in low-resource settings with limited native language documents, offering a practical and robust solution across multilingual domains. △ Less

Submitted 27 October, 2025; originally announced October 2025.

Comments: EMNLP 2025 MRL Workshop

SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning

Authors: Nikhil Verma, Manasa Bharadwaj, Wonjun Jang, Harmanpreet Singh, Yixiao Wang, Homa Fashandi, Chul Lee

Abstract: Large Language Models (LLMs) have redefined complex task automation with exceptional generalization capabilities. Despite these advancements, state-of-the-art methods rely on single-strategy prompting, missing the synergy of diverse reasoning approaches. No single strategy excels universally, highlighting the need for frameworks that fuse strategies to maximize performance and ensure robustness. W… ▽ More Large Language Models (LLMs) have redefined complex task automation with exceptional generalization capabilities. Despite these advancements, state-of-the-art methods rely on single-strategy prompting, missing the synergy of diverse reasoning approaches. No single strategy excels universally, highlighting the need for frameworks that fuse strategies to maximize performance and ensure robustness. We introduce the Select, Mix, and ReinvenT (SMaRT) framework, an innovative strategy fusion approach designed to overcome this constraint by creating balanced and efficient solutions through the seamless integration of diverse reasoning strategies. Unlike existing methods, which employ LLMs merely as evaluators, SMaRT uses them as intelligent integrators, unlocking the "best of all worlds" across tasks. Extensive empirical evaluations across benchmarks in reasoning, planning, and sequential decision-making highlight the robustness and adaptability of SMaRT. The framework consistently outperforms state-of-the-art baselines in solution quality, constraint adherence, and performance metrics. This work redefines LLM-driven decision-making by pioneering a new paradigm in cross-strategy calibration, unlocking superior outcomes for reasoning systems and advancing the boundaries of self-refining methodologies. △ Less

Submitted 20 October, 2025; originally announced October 2025.

t-SNE Exaggerates Clusters, Provably

Authors: Noah Bergam, Szymon Snoeck, Nakul Verma

Abstract: Central to the widespread use of t-distributed stochastic neighbor embedding (t-SNE) is the conviction that it produces visualizations whose structure roughly matches that of the input. To the contrary, we prove that (1) the strength of the input clustering, and (2) the extremity of outlier points, cannot be reliably inferred from the t-SNE output. We demonstrate the prevalence of these failure mo… ▽ More Central to the widespread use of t-distributed stochastic neighbor embedding (t-SNE) is the conviction that it produces visualizations whose structure roughly matches that of the input. To the contrary, we prove that (1) the strength of the input clustering, and (2) the extremity of outlier points, cannot be reliably inferred from the t-SNE output. We demonstrate the prevalence of these failure modes in practice as well. △ Less

Submitted 8 October, 2025; originally announced October 2025.

Compressibility Barriers to Neighborhood-Preserving Data Visualizations

Authors: Szymon Snoeck, Noah Bergam, Nakul Verma

Abstract: To what extent is it possible to visualize high-dimensional datasets in a two- or three-dimensional space? We reframe this question in terms of embedding $n$-vertex graphs (representing the neighborhood structure of the input points) into metric spaces of low doubling dimension $d$, in such a way that maintains the separation between neighbors and non-neighbors. This seemingly lax embedding requir… ▽ More To what extent is it possible to visualize high-dimensional datasets in a two- or three-dimensional space? We reframe this question in terms of embedding $n$-vertex graphs (representing the neighborhood structure of the input points) into metric spaces of low doubling dimension $d$, in such a way that maintains the separation between neighbors and non-neighbors. This seemingly lax embedding requirement is surprisingly difficult to satisfy. Our investigation shows that an overwhelming fraction of graphs require $d = Ω(\log n)$. Even when considering sparse regular graphs, the situation does not improve, as an overwhelming fraction of such graphs requires $d= Ω(\log n / \log\log n)$. The landscape changes dramatically when embedding into normed spaces. In particular, all but a vanishing fraction of graphs demand $d=Θ(n)$. Finally, we study the implications of these results for visualizing data with intrinsic cluster structure. We find that graphs produced from a planted partition model with $k$ clusters on $n$ points typically require $d=Ω(\log n)$, even when the cluster structure is salient. These results challenge the aspiration that constant-dimensional visualizations can faithfully preserve neighborhood structure. △ Less

Submitted 9 August, 2025; originally announced August 2025.

Optimizing Day-Ahead Energy Trading with Proximal Policy Optimization and Blockchain

Authors: Navneet Verma, Ying Xie

Abstract: The increasing penetration of renewable energy sources in day-ahead energy markets introduces challenges in balancing supply and demand, ensuring grid resilience, and maintaining trust in decentralized trading systems. This paper proposes a novel framework that integrates the Proximal Policy Optimization (PPO) algorithm, a state-of-the-art reinforcement learning method, with blockchain technology… ▽ More The increasing penetration of renewable energy sources in day-ahead energy markets introduces challenges in balancing supply and demand, ensuring grid resilience, and maintaining trust in decentralized trading systems. This paper proposes a novel framework that integrates the Proximal Policy Optimization (PPO) algorithm, a state-of-the-art reinforcement learning method, with blockchain technology to optimize automated trading strategies for prosumers in day-ahead energy markets. We introduce a comprehensive framework that employs RL agent for multi-objective energy optimization and blockchain for tamper-proof data and transaction management. Simulations using real-world data from the Electricity Reliability Council of Texas (ERCOT) demonstrate the effectiveness of our approach. The RL agent achieves demand-supply balancing within 2\% and maintains near-optimal supply costs for the majority of the operating hours. Moreover, it generates robust battery storage policies capable of handling variability in solar and wind generation. All decisions are recorded on an Algorand-based blockchain, ensuring transparency, auditability, and security - key enablers for trustworthy multi-agent energy trading. Our contributions include a novel system architecture, curriculum learning for robust agent development, and actionable policy insights for practical deployment. △ Less

Submitted 7 December, 2025; v1 submitted 3 August, 2025; originally announced August 2025.

GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems

Authors: Jisoo Lee, Raeyoung Chang, Dongwook Kwon, Harmanpreet Singh, Nikhil Verma

Abstract: Multi-agent systems built on language models have shown strong performance on collaborative reasoning tasks. However, existing evaluations focus only on the correctness of the final output, overlooking how inefficient communication and poor coordination contribute to redundant reasoning and higher computational costs. We introduce GEMMAS, a graph-based evaluation framework that analyzes the intern… ▽ More Multi-agent systems built on language models have shown strong performance on collaborative reasoning tasks. However, existing evaluations focus only on the correctness of the final output, overlooking how inefficient communication and poor coordination contribute to redundant reasoning and higher computational costs. We introduce GEMMAS, a graph-based evaluation framework that analyzes the internal collaboration process by modeling agent interactions as a directed acyclic graph. To capture collaboration quality, we propose two process-level metrics: Information Diversity Score (IDS) to measure semantic variation in inter-agent messages, and Unnecessary Path Ratio (UPR) to quantify redundant reasoning paths. We evaluate GEMMAS across five benchmarks and highlight results on GSM8K, where systems with only a 2.1% difference in accuracy differ by 12.8% in IDS and 80% in UPR, revealing substantial variation in internal collaboration. These findings demonstrate that outcome-only metrics are insufficient for evaluating multi-agent performance and highlight the importance of process-level diagnostics in designing more interpretable and resource-efficient collaborative AI systems. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Comments: 4 figures, 1 algorithm, 2 tables, 6 pages, under review at EMNLP Industry track 2025

DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging

Authors: Neha Verma, Kenton Murray, Kevin Duh

Abstract: Model compression offers a promising path to reducing the cost and inaccessibility of large pre-trained models, without significantly compromising their impressive performance. Large Transformer models, including large language models (LLMs), often contain computational redundancy, which can serve as a target for new model compression methods. In this work, we specifically target neuron-level redu… ▽ More Model compression offers a promising path to reducing the cost and inaccessibility of large pre-trained models, without significantly compromising their impressive performance. Large Transformer models, including large language models (LLMs), often contain computational redundancy, which can serve as a target for new model compression methods. In this work, we specifically target neuron-level redundancies in model layers by combining groups of similar neurons into fewer neurons. We frame this width reduction as a Discrete Optimal Transport problem, and propose DOTResize, a novel Transformer compression method that uses optimal transport theory to transform and compress model weights. To ensure applicability within the Transformer architecture, we motivate and incorporate entropic regularization and matrix factorization into the transportation maps produced by our method. Unlike pruning-based approaches which discard neurons based on importance measures, DOTResize re-projects the entire neuron width, allowing the retention and redistribution of useful signal across the reduced layer. Empirical results show that compared to simple or state-of-the-art neuron width-pruning techniques, DOTResize can outperform these methods across multiple LLM families and sizes, while achieving measurable reductions in real-world computational cost. △ Less

Submitted 6 July, 2025; originally announced July 2025.

OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections

Authors: Manasa Bharadwaj, Nikhil Verma, Kevin Ferreira

Abstract: Efforts to improve Large Language Model (LLM) agent performance on complex tasks have largely focused on fine-tuning and iterative self-correction. However, these approaches often lack generalizable mechanisms for longterm learning and remain inefficient in dynamic environments. We introduce OmniReflect, a hierarchical, reflection-driven framework that constructs a constitution, a compact set of g… ▽ More Efforts to improve Large Language Model (LLM) agent performance on complex tasks have largely focused on fine-tuning and iterative self-correction. However, these approaches often lack generalizable mechanisms for longterm learning and remain inefficient in dynamic environments. We introduce OmniReflect, a hierarchical, reflection-driven framework that constructs a constitution, a compact set of guiding principles distilled from task experiences, to enhance the effectiveness and efficiency of an LLM agent. OmniReflect operates in two modes: Self-sustaining, where a single agent periodically curates its own reflections during task execution, and Co-operative, where a Meta-advisor derives a constitution from a small calibration set to guide another agent. To construct these constitutional principles, we employ Neural, Symbolic, and NeuroSymbolic techniques, offering a balance between contextual adaptability and computational efficiency. Empirical results averaged across models show major improvements in task success, with absolute gains of +10.3% on ALFWorld, +23.8% on BabyAI, and +8.3% on PDDL in the Self-sustaining mode. Similar gains are seen in the Co-operative mode, where a lightweight Qwen3-4B ReAct agent outperforms all Reflexion baselines on BabyAI. These findings highlight the robustness and effectiveness of OmniReflect across environments and backbones. △ Less

Submitted 20 June, 2025; originally announced June 2025.

Cross-Attention Speculative Decoding

Authors: Wei Zhong, Manasa Bharadwaj, Yixiao Wang, Nikhil Verma, Yipeng Ji, Chul Lee

Abstract: Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on tightly coupled, self-attention-based Transformer decoders, often augmented with auxiliary pooling or fusion layers. This coupling makes them increasingly complex and… ▽ More Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on tightly coupled, self-attention-based Transformer decoders, often augmented with auxiliary pooling or fusion layers. This coupling makes them increasingly complex and harder to generalize across different models. We present Budget EAGLE (Beagle), the first, to our knowledge, cross-attention-based Transformer decoder SD model that achieves performance on par with leading self-attention SD models (EAGLE-v2) while eliminating the need for pooling or auxiliary components, simplifying the architecture, improving training efficiency, and maintaining stable memory usage during training-time simulation. To enable effective training of this novel architecture, we propose Two-Stage Block-Attention Training, a new method that achieves training stability and convergence efficiency in block-level attention scenarios. Extensive experiments across multiple LLMs and datasets show that Beagle achieves competitive inference speedups and higher training efficiency than EAGLE-v2, offering a strong alternative for architectures in speculative decoding. △ Less

Submitted 21 September, 2025; v1 submitted 30 May, 2025; originally announced May 2025.

How to keep pushing ML accelerator performance? Know your rooflines!

Authors: Marian Verhelst, Luca Benini, Naveen Verma

Abstract: The rapidly growing importance of Machine Learning (ML) applications, coupled with their ever-increasing model size and inference energy footprint, has created a strong need for specialized ML hardware architectures. Numerous ML accelerators have been explored and implemented, primarily to increase task-level throughput per unit area and reduce task-level energy consumption. This paper surveys key… ▽ More The rapidly growing importance of Machine Learning (ML) applications, coupled with their ever-increasing model size and inference energy footprint, has created a strong need for specialized ML hardware architectures. Numerous ML accelerators have been explored and implemented, primarily to increase task-level throughput per unit area and reduce task-level energy consumption. This paper surveys key trends toward these objectives for more efficient ML accelerators and provides a unifying framework to understand how compute and memory technologies/architectures interact to enhance system-level efficiency and performance. To achieve this, the paper introduces an enhanced version of the roofline model and applies it to ML accelerators as an effective tool for understanding where various execution regimes fall within roofline bounds and how to maximize performance and efficiency under the rooline. Key concepts are illustrated with examples from state-of-the-art designs, with a view towards open research opportunities to further advance accelerator performance. △ Less

Submitted 23 May, 2025; v1 submitted 22 May, 2025; originally announced May 2025.

Comments: in IEEE Journal of Solid-State Circuits, 2025

CB-cPIR: Code-Based Computational Private Information Retrieval

Authors: Camilla Hollanti, Neehar Verma

Abstract: A private information retrieval (PIR) scheme is a protocol that allows a user to retrieve a file from a database without revealing the identity of the desired file to a curious database. Given a distributed data storage system, efficient PIR can be achieved by making assumptions about the colluding capabilities of the storage servers holding the database. If these assumptions turn out to be incorr… ▽ More A private information retrieval (PIR) scheme is a protocol that allows a user to retrieve a file from a database without revealing the identity of the desired file to a curious database. Given a distributed data storage system, efficient PIR can be achieved by making assumptions about the colluding capabilities of the storage servers holding the database. If these assumptions turn out to be incorrect, privacy is lost. In this work, we focus on the worst-case assumption: full collusion or, equivalently, viewing the storage system virtually as a single honest-but-curious server. We present CB-cPIR, a single-server code-based computational private information retrieval (cPIR) scheme that derives security from code-based cryptography. Specifically, the queries are protected by the hardness of decoding a random linear code. The scheme is heavily inspired by the pioneering code-based cPIR scheme proposed by Holzbaur, Hollanti, and Wachter-Zeh in [Holzbaur et al., "Computational Code-Based Single-Server Private Information Retrieval", 2020 IEEE ISIT] and fixes the vulnerabilities of the original scheme arising from highly probable rank differences in submatrices of the user's query. Recently, a new vulnerability was observed in [Lage, Bartz, "On the Security of a Code-Based PIR Scheme"], a simple modification to the scheme now fixes this vulnerability. For further validation of our scheme, we draw comparisons to the state-of-the-art lattice-based cPIR schemes. △ Less

Submitted 7 August, 2025; v1 submitted 6 May, 2025; originally announced May 2025.

Comments: This paper builds on the work done in arXiv: 2402.02871v1 (IEEE ISIT24) and arXiv: 2001.07049 (IEEE ISIT20) Remark 6. briefly outlines a fix to a new attack, this paper will soon be updated to reflect the changes to the scheme

The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context

Authors: Nikhil Verma, Manasa Bharadwaj

Abstract: Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages. Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism general… ▽ More Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages. Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalize to multilingual settings. To address this, we conduct a systematic analysis of distributional shifts in the embedding space of LLMs before and after alignment, uncovering its impact on model behavior across diverse languages. We leverage the alignment-induced separation in safety space as a quantitative tool to measure how alignment enforces safety constraints. Our study evaluates seven LLMs using balanced toxicity datasets and parallel text-detoxification benchmarks, revealing substantial disparities in the latent representation space between high-resource and low-resource languages. These findings underscore the need for language-specific fine-tuning to ensure fair, reliable and robust multilingual alignment. Our insights provide a foundation for developing truly safe multilingual LLMs, emphasizing the urgency of addressing alignment gaps in underrepresented languages. △ Less

Submitted 3 April, 2025; originally announced April 2025.

Comments: 14 pages, 11 Figures, 2 Tables, currently under review at ACL 2025

LogicLearner: A Tool for the Guided Practice of Propositional Logic Proofs

Authors: Amogh Inamdar, Uzay Macar, Michel Vazirani, Michael Tarnow, Zarina Mustapha, Natalia Dittren, Sam Sadeh, Nakul Verma, Ansaf Salleb-Aouissi

Abstract: The study of propositional logic -- fundamental to the theory of computing -- is a cornerstone of the undergraduate computer science curriculum. Learning to solve logical proofs requires repeated guided practice, but undergraduate students often lack access to on-demand tutoring in a judgment-free environment. In this work, we highlight the need for guided practice tools in undergraduate mathemati… ▽ More The study of propositional logic -- fundamental to the theory of computing -- is a cornerstone of the undergraduate computer science curriculum. Learning to solve logical proofs requires repeated guided practice, but undergraduate students often lack access to on-demand tutoring in a judgment-free environment. In this work, we highlight the need for guided practice tools in undergraduate mathematics education and outline the desiderata of an effective practice tool. We accordingly develop LogicLearner, a web application for guided logic proof practice. LogicLearner consists of an interface to attempt logic proofs step-by-step and an automated proof solver to generate solutions on the fly, allowing users to request guidance as needed. We pilot LogicLearner as a practice tool in two semesters of an undergraduate discrete mathematics course and receive strongly positive feedback for usability and pedagogical value in student surveys. To the best of our knowledge, LogicLearner is the only learning tool that provides an end-to-end practice environment for logic proofs with immediate, judgment-free feedback. △ Less

Submitted 24 March, 2025; originally announced March 2025.

Comments: 32 pages, 27 figures, open-source codebase linked in paper

Diverse Inference and Verification for Advanced Reasoning

Authors: Iddo Drori, Gaston Longhitano, Mao Mao, Seunghwan Hyun, Yuke Zhang, Sungjun Park, Zachary Meeks, Xin-Yu Zhang, Ben Segev, Howard Yong, Nakul Verma, Avi Shporer, Alon Amit, Madeleine Udell

Abstract: Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding, yet find challenging advanced tasks such as International Mathematical Olympiad (IMO) combinatorics problems, Abstraction and Reasoning Corpus (ARC) puzzles, and Humanity's Last Exam (HLE) questions. We use a diverse inference approach that combines multiple models and methods at test tim… ▽ More Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding, yet find challenging advanced tasks such as International Mathematical Olympiad (IMO) combinatorics problems, Abstraction and Reasoning Corpus (ARC) puzzles, and Humanity's Last Exam (HLE) questions. We use a diverse inference approach that combines multiple models and methods at test time. We find that verifying mathematics and code problems, and rejection sampling on other problems is simple and effective. We automatically verify correctness of solutions to IMO problems by Lean, and ARC puzzles by code, and find that best-of-N effectively answers HLE questions. Our approach increases answer accuracy on IMO combinatorics problems from 33.3% to 77.8%, accuracy on HLE questions from 8% to 37%, and solves 80% of ARC puzzles that 948 humans could not and 26.5% of ARC puzzles that o3 high compute does not. Test-time simulations, reinforcement learning, and meta-learning with inference feedback improve generalization by adapting agent graph representations and varying prompts, code, and datasets. Our approach is reliable, robust, and scalable, and in the spirit of reproducible research, we will make it publicly available upon publication. △ Less

Submitted 14 February, 2025; originally announced February 2025.

Comments: 165 pages

Merging Feed-Forward Sublayers for Compressed Transformers

Authors: Neha Verma, Kenton Murray, Kevin Duh

Abstract: With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the memory constraints of different hardware. In this work, we present a novel approach to model compression by merging similar parameter groups within a model, ra… ▽ More With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the memory constraints of different hardware. In this work, we present a novel approach to model compression by merging similar parameter groups within a model, rather than pruning away less important parameters. Specifically, we select, align, and merge separate feed-forward sublayers in Transformer models, and test our method on language modeling, image classification, and machine translation. With our method, we demonstrate performance comparable to the original models while combining more than a third of model feed-forward sublayers, and demonstrate improved performance over a strong layer-pruning baseline. For instance, we can remove over 21% of total parameters from a Vision Transformer, while maintaining 99% of its original performance. Additionally, we observe that some groups of feed-forward sublayers exhibit high activation similarity, which may help explain their surprising mergeability. △ Less

Submitted 28 March, 2025; v1 submitted 10 January, 2025; originally announced January 2025.

Deep Autoregressive Models as Causal Inference Engines

Authors: Daniel Jiwoong Im, Kevin Zhang, Nakul Verma, Kyunghyun Cho

Abstract: Existing causal inference (CI) models are often restricted to data with low-dimensional confounders and singleton actions. We propose an autoregressive (AR) CI framework capable of handling complex confounders and sequential actions commonly found in modern applications. Our approach accomplishes this using {\em sequencification}, which transforms data from an underlying causal diagram into a sequ… ▽ More Existing causal inference (CI) models are often restricted to data with low-dimensional confounders and singleton actions. We propose an autoregressive (AR) CI framework capable of handling complex confounders and sequential actions commonly found in modern applications. Our approach accomplishes this using {\em sequencification}, which transforms data from an underlying causal diagram into a sequence of tokens. Sequencification not only accommodates training with data generated from a large class of DAGs, but also extends existing CI capabilities to estimate multiple causal quantities using a {\em single} model. We can directly compute probabilities from interventional distributions, simplifying inference and improving outcome prediction accuracy. We demonstrate that an AR model adapted for CI is efficient and effective in various complex applications such as navigating mazes, playing chess endgames, and evaluating the impact of certain keywords on paper acceptance rates, where we consider causal queries beyond standard reinforcement learning-type questions. △ Less

Submitted 4 July, 2025; v1 submitted 27 September, 2024; originally announced September 2024.

VisioPhysioENet: Visual Physiological Engagement Detection Network

Authors: Alakhsimar Singh, Kanav Goyal, Nischay Verma, Puneet Kumar, Xiaobai Li, Amritpal Singh

Abstract: This paper presents VisioPhysioENet, a novel multimodal system that leverages visual and physiological signals to detect learner engagement. It employs a two-level approach for extracting both visual and physiological features. For visual feature extraction, Dlib is used to detect facial landmarks, while OpenCV provides additional estimations. The face recognition library, built on Dlib, is used t… ▽ More This paper presents VisioPhysioENet, a novel multimodal system that leverages visual and physiological signals to detect learner engagement. It employs a two-level approach for extracting both visual and physiological features. For visual feature extraction, Dlib is used to detect facial landmarks, while OpenCV provides additional estimations. The face recognition library, built on Dlib, is used to identify the facial region of interest specifically for physiological signal extraction. Physiological signals are then extracted using the plane-orthogonal-toskin method to assess cardiovascular activity. These features are integrated using advanced machine learning classifiers, enhancing the detection of various levels of engagement. We thoroughly tested VisioPhysioENet on the DAiSEE dataset. It achieved an accuracy of 63.09%. This shows it can better identify different levels of engagement compared to many existing methods. It performed 8.6% better than the only other model that uses both physiological and visual features. △ Less

Submitted 20 August, 2025; v1 submitted 24 September, 2024; originally announced September 2024.

Comments: 35 Pages, 4 figures, 5 Tables

Large Language Models for Page Stream Segmentation

Authors: Hunter Heidenreich, Ratish Dalvi, Rohith Mukku, Nikhil Verma, Neven Pičuljan

Abstract: Page Stream Segmentation (PSS) is an essential prerequisite for automated document processing at scale. However, research progress has been limited by the absence of realistic public benchmarks. This paper works towards addressing this gap by introducing TABME++, an enhanced benchmark featuring commercial Optical Character Recognition (OCR) annotations. We evaluate the performance of large languag… ▽ More Page Stream Segmentation (PSS) is an essential prerequisite for automated document processing at scale. However, research progress has been limited by the absence of realistic public benchmarks. This paper works towards addressing this gap by introducing TABME++, an enhanced benchmark featuring commercial Optical Character Recognition (OCR) annotations. We evaluate the performance of large language models (LLMs) on PSS, focusing on decoder-based models fine-tuned with parameter-efficient methods. Our results show that decoder-based LLMs outperform smaller multimodal encoders. Through a review of existing PSS research and datasets, we identify key challenges and advancements in the field. Our findings highlight the key importance of robust OCR, providing valuable insights for the development of more effective document processing systems. △ Less

Submitted 21 August, 2024; originally announced August 2024.

Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models

Authors: Omer Belhasin, Idan Kligvasser, George Leifman, Regev Cohen, Erin Rainaldi, Li-Fang Cheng, Nishant Verma, Paul Varghese, Ehud Rivlin, Michael Elad

Abstract: Analyzing the cardiovascular system condition via Electrocardiography (ECG) is a common and highly effective approach, and it has been practiced and perfected over many decades. ECG sensing is non-invasive and relatively easy to acquire, and yet it is still cumbersome for holter monitoring tests that may span over hours and even days. A possible alternative in this context is Photoplethysmography… ▽ More Analyzing the cardiovascular system condition via Electrocardiography (ECG) is a common and highly effective approach, and it has been practiced and perfected over many decades. ECG sensing is non-invasive and relatively easy to acquire, and yet it is still cumbersome for holter monitoring tests that may span over hours and even days. A possible alternative in this context is Photoplethysmography (PPG): An optically-based signal that measures blood volume fluctuations, as typically sensed by conventional ``wearable devices''. While PPG presents clear advantages in acquisition, convenience, and cost-effectiveness, ECG provides more comprehensive information, allowing for a more precise detection of heart conditions. This implies that a conversion from PPG to ECG, as recently discussed in the literature, inherently involves an unavoidable level of uncertainty. In this paper we introduce a novel methodology for addressing the PPG-2-ECG conversion, and offer an enhanced classification of cardiovascular conditions using the given PPG, all while taking into account the uncertainties arising from the conversion process. We provide a mathematical justification for our proposed computational approach, and present empirical studies demonstrating its superior performance compared to state-of-the-art baseline methods. △ Less

Submitted 20 April, 2025; v1 submitted 19 May, 2024; originally announced May 2024.

GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification

Authors: Ali Pesaranghader, Nikhil Verma, Manasa Bharadwaj

Abstract: Harmful and offensive communication or content is detrimental to social bonding and the mental state of users on social media platforms. Text detoxification is a crucial task in natural language processing (NLP), where the goal is removing profanity and toxicity from text while preserving its content. Supervised and unsupervised learning are common approaches for designing text detoxification solu… ▽ More Harmful and offensive communication or content is detrimental to social bonding and the mental state of users on social media platforms. Text detoxification is a crucial task in natural language processing (NLP), where the goal is removing profanity and toxicity from text while preserving its content. Supervised and unsupervised learning are common approaches for designing text detoxification solutions. However, these methods necessitate fine-tuning, leading to computational overhead. In this paper, we propose GPT-DETOX as a framework for prompt-based in-context learning for text detoxification using GPT-3.5 Turbo. We utilize zero-shot and few-shot prompting techniques for detoxifying input sentences. To generate few-shot prompts, we propose two methods: word-matching example selection (WMES) and context-matching example selection (CMES). We additionally take into account ensemble in-context learning (EICL) where the ensemble is shaped by base prompts from zero-shot and all few-shot settings. We use ParaDetox and APPDIA as benchmark detoxification datasets. Our experimental results show that the zero-shot solution achieves promising performance, while our best few-shot setting outperforms the state-of-the-art models on ParaDetox and shows comparable results on APPDIA. Our EICL solutions obtain the greatest performance, adding at least 10% improvement, against both datasets. △ Less

Submitted 3 April, 2024; originally announced April 2024.

Comments: 7 pages, 8 tables. Published in: 2023 International Conference on Machine Learning and Applications (ICMLA)

Merging Text Transformer Models from Different Initializations

Authors: Neha Verma, Maha Elbayad

Abstract: Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer architecture, despite its dominant popularity in the language domain. Therefore, in this work, we investigate the extent to which separate Transformer minima learn simi… ▽ More Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer architecture, despite its dominant popularity in the language domain. Therefore, in this work, we investigate the extent to which separate Transformer minima learn similar features, and propose a model merging technique to investigate the relationship between these minima in the loss landscape. The specifics of the architecture, like its residual connections, multi-headed attention, and discrete, sequential input, require specific interventions in order to compute model permutations that remain within the same functional equivalence class. In merging these models with our method, we consistently find lower loss barriers between minima compared to model averaging, across models trained on a masked-language modeling task or fine-tuned on a language understanding benchmark. Our results show that the minima of these models are less sharp and isolated than previously understood, and provide a basis for future work on merging separately trained Transformer models. △ Less

Submitted 16 December, 2024; v1 submitted 1 March, 2024; originally announced March 2024.

Comments: TMLR, November 2024

On Designing Features for Condition Monitoring of Rotating Machines

Authors: Seetaram Maurya, Nishchal K. Verma

Abstract: Various methods for designing input features have been proposed for fault recognition in rotating machines using one-dimensional raw sensor data. The available methods are complex, rely on empirical approaches, and may differ depending on the condition monitoring data used. Therefore, this article proposes a novel algorithm to design input features that unifies the feature extraction process for d… ▽ More Various methods for designing input features have been proposed for fault recognition in rotating machines using one-dimensional raw sensor data. The available methods are complex, rely on empirical approaches, and may differ depending on the condition monitoring data used. Therefore, this article proposes a novel algorithm to design input features that unifies the feature extraction process for different time-series sensor data. This new insight for designing/extracting input features is obtained through the lens of histogram theory. The proposed algorithm extracts discriminative input features, which are suitable for a simple classifier to deep neural network-based classifiers. The designed input features are given as input to the classifier with end-to-end training in a single framework for machine conditions recognition. The proposed scheme has been validated through three real-time datasets: a) acoustic dataset, b) CWRU vibration dataset, and c) IMS vibration dataset. The real-time results and comparative study show the effectiveness of the proposed scheme for the prediction of the machine's health states. △ Less

Submitted 15 February, 2024; originally announced February 2024.

Code-Based Single-Server Private Information Retrieval: Circumventing the Sub-Query Attack

Authors: Neehar Verma, Camilla Hollanti

Abstract: Private information retrieval from a single server is considered, utilizing random linear codes. Presented is a modified version of the first code-based single-server computational PIR scheme proposed by Holzbaur, Hollanti, and Wachter-Zeh in [Holzbaur et al., "Computational Code-Based Single-Server Private Information Retrieval", 2020 IEEE ISIT]. The original scheme was broken in [Bordage et al.,… ▽ More Private information retrieval from a single server is considered, utilizing random linear codes. Presented is a modified version of the first code-based single-server computational PIR scheme proposed by Holzbaur, Hollanti, and Wachter-Zeh in [Holzbaur et al., "Computational Code-Based Single-Server Private Information Retrieval", 2020 IEEE ISIT]. The original scheme was broken in [Bordage et al., "On the privacy of a code-based single-server computational PIR scheme", Cryptogr. Comm., 2021] by an attack arising from highly probable rank differences in sub-matrices of the user's query. Here, this attack is now circumvented by ensuring that the sub-matrices have negligible rank difference. Furthermore, the rank difference cannot be attributed to the desired file index, thereby ensuring the privacy of the scheme. In the case of retrieving multiple files, the rate of the modified scheme is largely unaffected and at par with the original scheme. △ Less

Submitted 5 February, 2024; originally announced February 2024.

Comments: The scheme proposed in this work is a modified version of the scheme in arXiv:2001.07049 (IEEE ISIT 2020) and provides a mend against the attack discovered in arXiv:2004.00509 (Cryptography and Communications, 2021)

Image Reconstruction using Enhanced Vision Transformer

Authors: Nikhil Verma, Deepkamal Kaur, Lydia Chau

Abstract: Removing noise from images is a challenging and fundamental problem in the field of computer vision. Images captured by modern cameras are inevitably degraded by noise which limits the accuracy of any quantitative measurements on those images. In this project, we propose a novel image reconstruction framework which can be used for tasks such as image denoising, deblurring or inpainting. The model… ▽ More Removing noise from images is a challenging and fundamental problem in the field of computer vision. Images captured by modern cameras are inevitably degraded by noise which limits the accuracy of any quantitative measurements on those images. In this project, we propose a novel image reconstruction framework which can be used for tasks such as image denoising, deblurring or inpainting. The model proposed in this project is based on Vision Transformer (ViT) that takes 2D images as input and outputs embeddings which can be used for reconstructing denoised images. We incorporate four additional optimization techniques in the framework to improve the model reconstruction capability, namely Locality Sensitive Attention (LSA), Shifted Patch Tokenization (SPT), Rotary Position Embeddings (RoPE) and adversarial loss function inspired from Generative Adversarial Networks (GANs). LSA, SPT and RoPE enable the transformer to learn from the dataset more efficiently, while the adversarial loss function enhances the resolution of the reconstructed images. Based on our experiments, the proposed architecture outperforms the benchmark U-Net model by more than 3.5\% structural similarity (SSIM) for the reconstruction tasks of image denoising and inpainting. The proposed enhancements further show an improvement of \textasciitilde5\% SSIM over the benchmark for both tasks. △ Less

Submitted 10 July, 2023; originally announced July 2023.

Diffusion idea exploration for art generation

Authors: Nikhil Verma

Abstract: Cross-Modal learning tasks have picked up pace in recent times. With plethora of applications in diverse areas, generation of novel content using multiple modalities of data has remained a challenging problem. To address the same, various generative modelling techniques have been proposed for specific tasks. Novel and creative image generation is one important aspect for industrial application whi… ▽ More Cross-Modal learning tasks have picked up pace in recent times. With plethora of applications in diverse areas, generation of novel content using multiple modalities of data has remained a challenging problem. To address the same, various generative modelling techniques have been proposed for specific tasks. Novel and creative image generation is one important aspect for industrial application which could help as an arm for novel content generation. Techniques proposed previously used Generative Adversarial Network(GAN), autoregressive models and Variational Autoencoders (VAE) for accomplishing similar tasks. These approaches are limited in their capability to produce images guided by either text instructions or rough sketch images decreasing the overall performance of image generator. We used state of the art diffusion models to generate creative art by primarily leveraging text with additional support of rough sketches. Diffusion starts with a pattern of random dots and slowly converts that pattern into a design image using the guiding information fed into the model. Diffusion models have recently outperformed other generative models in image generation tasks using cross modal data as guiding information. The initial experiments for this task of novel image generation demonstrated promising qualitative results. △ Less

Submitted 10 July, 2023; originally announced July 2023.

Comments: Report Submitted for degree completion of Master of Science in Applied Computing at University of Toronto

Contrastive Loss is All You Need to Recover Analogies as Parallel Lines

Authors: Narutatsu Ri, Fei-Tzin Lee, Nakul Verma

Abstract: While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure. We find that an elementary contrastive-style method employed over distributional information performs competitively with popular word embedding models on analogy recovery tasks, while… ▽ More While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure. We find that an elementary contrastive-style method employed over distributional information performs competitively with popular word embedding models on analogy recovery tasks, while achieving dramatic speedups in training time. Further, we demonstrate that a contrastive loss is sufficient to create these parallel structures in word embeddings, and establish a precise relationship between the co-occurrence statistics and the geometric structure of the resulting word embeddings. △ Less

Submitted 13 June, 2023; originally announced June 2023.

A Novel Vision Transformer with Residual in Self-attention for Biomedical Image Classification

Authors: Arun K. Sharma, Nishchal K. Verma

Abstract: Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced nature of dataset. This article presents the novel framework of multi-head self-attention for vision transformer (ViT) which makes capable of capturing the spe… ▽ More Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced nature of dataset. This article presents the novel framework of multi-head self-attention for vision transformer (ViT) which makes capable of capturing the specific image features for classification and analysis. The proposed method uses the concept of residual connection for accumulating the best attention output in each block of multi-head attention. The proposed framework has been evaluated on two small datasets: (i) blood cell classification dataset and (ii) brain tumor detection using brain MRI images. The results show the significant improvement over traditional ViT and other convolution based state-of-the-art classification models. △ Less

Submitted 5 June, 2023; v1 submitted 2 June, 2023; originally announced June 2023.

Journal ref: Pattern Recognition, Volume 172, Part B, April 2026, 112497

Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer

Authors: Elizabeth Salesky, Neha Verma, Philipp Koehn, Matt Post

Abstract: We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a variety of language and script coverage, demonstrating improved performance compared to subword embeddings. We explore various properties of pixel representations such as parameter sharing within and across scripts to better… ▽ More We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a variety of language and script coverage, demonstrating improved performance compared to subword embeddings. We explore various properties of pixel representations such as parameter sharing within and across scripts to better understand where they lead to positive transfer. We observe that these properties not only enable seamless cross-lingual transfer to unseen scripts, but make pixel representations more data-efficient than alternatives such as vocabulary expansion. We hope this work contributes to more extensible multilingual models for all languages and scripts. △ Less

Submitted 24 October, 2023; v1 submitted 23 May, 2023; originally announced May 2023.

Comments: EMNLP 2023

Exploring Representational Disparities Between Multilingual and Bilingual Translation Models

Authors: Neha Verma, Kenton Murray, Kevin Duh

Abstract: Multilingual machine translation has proven immensely useful for both parameter efficiency and overall performance across many language pairs via complete multilingual parameter sharing. However, some language pairs in multilingual models can see worse performance than in bilingual models, especially in the one-to-many translation setting. Motivated by their empirical differences, we examine the g… ▽ More Multilingual machine translation has proven immensely useful for both parameter efficiency and overall performance across many language pairs via complete multilingual parameter sharing. However, some language pairs in multilingual models can see worse performance than in bilingual models, especially in the one-to-many translation setting. Motivated by their empirical differences, we examine the geometric differences in representations from bilingual models versus those from one-to-many multilingual models. Specifically, we compute the isotropy of these representations using intrinsic dimensionality and IsoScore, in order to measure how the representations utilize the dimensions in their underlying vector space. Using the same evaluation data in both models, we find that for a given language pair, its multilingual model decoder representations are consistently less isotropic and occupy fewer dimensions than comparable bilingual model decoder representations. Additionally, we show that much of the anisotropy in multilingual decoder representations can be attributed to modeling language-specific information, therefore limiting remaining representational capacity. △ Less

Submitted 26 March, 2024; v1 submitted 23 May, 2023; originally announced May 2023.

Comments: LREC-COLING 2024

Dish detection in food platters: A framework for automated diet logging and nutrition management

Authors: Mansi Goel, Shashank Dargar, Shounak Ghatak, Nidhi Verma, Pratik Chauhan, Anushka Gupta, Nikhila Vishnumolakala, Hareesh Amuru, Ekta Gambhir, Ronak Chhajed, Meenal Jain, Astha Jain, Samiksha Garg, Nitesh Narwade, Nikhilesh Verhwani, Abhuday Tiwari, Kirti Vashishtha, Ganesh Bagler

Abstract: Diet is central to the epidemic of lifestyle disorders. Accurate and effortless diet logging is one of the significant bottlenecks for effective diet management and calorie restriction. Dish detection from food platters is a challenging problem due to a visually complex food layout. We present an end-to-end computational framework for diet management, from data compilation, annotation, and state-o… ▽ More Diet is central to the epidemic of lifestyle disorders. Accurate and effortless diet logging is one of the significant bottlenecks for effective diet management and calorie restriction. Dish detection from food platters is a challenging problem due to a visually complex food layout. We present an end-to-end computational framework for diet management, from data compilation, annotation, and state-of-the-art model identification to its mobile app implementation. As a case study, we implement the framework in the context of Indian food platters known for their complex presentation that poses a challenge for the automated detection of dishes. Starting with the 61 most popular Indian dishes, we identify the state-of-the-art model through a comparative analysis of deep-learning-based object detection architectures. Rooted in a meticulous compilation of 68,005 platter images with 134,814 manual dish annotations, we first compare ten architectures for multi-label classification to identify ResNet152 (mAP=84.51%) as the best model. YOLOv8x (mAP=87.70%) emerged as the best model architecture for dish detection among the eight deep-learning models implemented after a thorough performance evaluation. By comparing with the state-of-the-art model for the IndianFood10 dataset, we demonstrate the superior object detection performance of YOLOv8x for this subset and establish Resnet152 as the best architecture for multi-label classification. The models thus trained on richly annotated data can be extended to include dishes from across global cuisines. The proposed framework is demonstrated through a proof-of-concept mobile application with diverse applications for diet logging, food recommendation systems, nutritional interventions, and mitigation of lifestyle disorders. △ Less

Submitted 12 May, 2023; originally announced May 2023.

Comments: 11 pages, 5 figures, 5 tables. Submitted to the 8th International Conference on Computer Vision & Image Processing (CVIP-2023)

ACM Class: I.4.9; I.5.4; J.3

eViper: A Scalable Platform for Untethered Modular Soft Robots

Authors: Hsin Cheng, Zhiwu Zheng, Prakhar Kumar, Wali Afridi, Ben Kim, Sigurd Wagner, Naveen Verma, James C. Sturm, Minjie Chen

Abstract: Soft robots present unique capabilities, but have been limited by the lack of scalable technologies for construction and the complexity of algorithms for efficient control and motion, which depend on soft-body dynamics, high-dimensional actuation patterns, and external/on-board forces. This paper presents scalable methods and platforms to study the impact of weight distribution and actuation patte… ▽ More Soft robots present unique capabilities, but have been limited by the lack of scalable technologies for construction and the complexity of algorithms for efficient control and motion, which depend on soft-body dynamics, high-dimensional actuation patterns, and external/on-board forces. This paper presents scalable methods and platforms to study the impact of weight distribution and actuation patterns on fully untethered modular soft robots. An extendable Vibrating Intelligent Piezo-Electric Robot (eViper), together with an open-source Simulation Framework for Electroactive Robotic Sheet (SFERS) implemented in PyBullet, was developed as a platform to study the sophisticated weight-locomotion interaction. By integrating the power electronics, sensors, actuators, and batteries on-board, the eViper platform enables rapid design iteration and evaluation of different weight distribution and control strategies for the actuator arrays, supporting both physics-based modeling and data-driven modeling via on-board automatic data-acquisition capabilities. We show that SFERS can provide useful guidelines for optimizing the weight distribution and actuation patterns of the eViper to achieve the maximum speed or minimum cost-of-transportation (COT). △ Less

Submitted 14 November, 2023; v1 submitted 2 March, 2023; originally announced March 2023.

Comments: 8 pages, 21 figures, accepted by IROS 2023

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces

Authors: Kelly Marchisio, Neha Verma, Kevin Duh, Philipp Koehn

Abstract: The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of "isomorphism." We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into t… ▽ More The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of "isomorphism." We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the Skip-gram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec. △ Less

Submitted 4 July, 2023; v1 submitted 10 October, 2022; originally announced October 2022.

Comments: Updated EMNLP2022 Camera Ready (citation correction, removed references to dimensionality reduction [was not used here].)

Improving Model Training via Self-learned Label Representations

Authors: Xiao Yu, Nakul Verma

Abstract: Modern neural network architectures have shown remarkable success in several large-scale classification and prediction tasks. Part of the success of these architectures is their flexibility to transform the data from the raw input representations (e.g. pixels for vision tasks, or text for natural language processing tasks) to one-hot output encoding. While much of the work has focused on studying… ▽ More Modern neural network architectures have shown remarkable success in several large-scale classification and prediction tasks. Part of the success of these architectures is their flexibility to transform the data from the raw input representations (e.g. pixels for vision tasks, or text for natural language processing tasks) to one-hot output encoding. While much of the work has focused on studying how the input gets transformed to the one-hot encoding, very little work has examined the effectiveness of these one-hot labels. In this work, we demonstrate that more sophisticated label representations are better for classification than the usual one-hot encoding. We propose Learning with Adaptive Labels (LwAL) algorithm, which simultaneously learns the label representation while training for the classification task. These learned labels can significantly cut down on the training time (usually by more than 50%) while often achieving better test accuracies. Our algorithm introduces negligible additional parameters and has a minimal computational overhead. Along with improved training times, our learned labels are semantically meaningful and can reveal hierarchical relationships that may be present in the data. △ Less

Submitted 9 September, 2022; originally announced September 2022.

Wirelessly-Controlled Untethered Piezoelectric Planar Soft Robot Capable of Bidirectional Crawling and Rotation

Authors: Zhiwu Zheng, Hsin Cheng, Prakhar Kumar, Sigurd Wagner, Minjie Chen, Naveen Verma, James C. Sturm

Abstract: Electrostatic actuators provide a promising approach to creating soft robotic sheets, due to their flexible form factor, modular integration, and fast response speed. However, their control requires kilo-Volt signals and understanding of complex dynamics resulting from force interactions by on-board and environmental effects. In this work, we demonstrate an untethered planar five-actuator piezoele… ▽ More Electrostatic actuators provide a promising approach to creating soft robotic sheets, due to their flexible form factor, modular integration, and fast response speed. However, their control requires kilo-Volt signals and understanding of complex dynamics resulting from force interactions by on-board and environmental effects. In this work, we demonstrate an untethered planar five-actuator piezoelectric robot powered by batteries and on-board high-voltage circuitry, and controlled through a wireless link. The scalable fabrication approach is based on bonding different functional layers on top of each other (steel foil substrate, actuators, flexible electronics). The robot exhibits a range of controllable motions, including bidirectional crawling (up to ~0.6 cm/s), turning, and in-place rotation (at ~1 degree/s). High-speed videos and control experiments show that the richness of the motion results from the interaction of an asymmetric mass distribution in the robot and the associated dependence of the dynamics on the driving frequency of the piezoelectrics. The robot's speed can reach 6 cm/s with specific payload distribution. △ Less

Submitted 19 January, 2023; v1 submitted 1 July, 2022; originally announced July 2022.

Comments: Accepted to the 2023 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref: 2023 IEEE International Conference on Robotics and Automation (ICRA), 641-647

Model-Based Control of Planar Piezoelectric Inchworm Soft Robot for Crawling in Constrained Environments

Authors: Zhiwu Zheng, Prakhar Kumar, Yenan Chen, Hsin Cheng, Sigurd Wagner, Minjie Chen, Naveen Verma, James C. Sturm

Abstract: Soft robots have drawn significant attention recently for their ability to achieve rich shapes when interacting with complex environments. However, their elasticity and flexibility compared to rigid robots also pose significant challenges for precise and robust shape control in real-time. Motivated by their potential to operate in highly-constrained environments, as in search-and-rescue operations… ▽ More Soft robots have drawn significant attention recently for their ability to achieve rich shapes when interacting with complex environments. However, their elasticity and flexibility compared to rigid robots also pose significant challenges for precise and robust shape control in real-time. Motivated by their potential to operate in highly-constrained environments, as in search-and-rescue operations, this work addresses these challenges of soft robots by developing a model-based full-shape controller, validated and demonstrated by experiments. A five-actuator planar soft robot was constructed with planar piezoelectric layers bonded to a steel foil substrate, enabling inchworm-like motion. The controller uses a soft-body continuous model for shape planning and control, given target shapes and/or environmental constraints, such as crawling under overhead barriers or "roof" safety lines. An approach to background model calibrations is developed to address deviations of actual robot shape due to material parameter variations and drift. Full experimental shape control and optimal movement under a roof safety line are demonstrated, where the robot maximizes its speed within the overhead constraint. The mean-squared error between the measured and target shapes improves from ~0.05 cm$^{2}$ without calibration to ~0.01 cm$^{2}$ with calibration. Simulation-based validation is also performed with various different roof shapes. △ Less

Submitted 28 March, 2022; originally announced March 2022.

Comments: Accepted to the 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft). Project website: https://piezorobotcontroller.github.io/ Summary video: https://youtu.be/Md-Uo-pUaIs

Journal ref: 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), 693-698

Scalable Simulation and Demonstration of Jumping Piezoelectric 2-D Soft Robots

Authors: Zhiwu Zheng, Prakhar Kumar, Yenan Chen, Hsin Cheng, Sigurd Wagner, Minjie Chen, Naveen Verma, James C. Sturm

Abstract: Soft robots have drawn great interest due to their ability to take on a rich range of shapes and motions, compared to traditional rigid robots. However, the motions, and underlying statics and dynamics, pose significant challenges to forming well-generalized and robust models necessary for robot design and control. In this work, we demonstrate a five-actuator soft robot capable of complex motions… ▽ More Soft robots have drawn great interest due to their ability to take on a rich range of shapes and motions, compared to traditional rigid robots. However, the motions, and underlying statics and dynamics, pose significant challenges to forming well-generalized and robust models necessary for robot design and control. In this work, we demonstrate a five-actuator soft robot capable of complex motions and develop a scalable simulation framework that reliably predicts robot motions. The simulation framework is validated by comparing its predictions to experimental results, based on a robot constructed from piezoelectric layers bonded to a steel-foil substrate. The simulation framework exploits the physics engine PyBullet, and employs discrete rigid-link elements connected by motors to model the actuators. We perform static and AC analyses to validate a single-unit actuator cantilever setup and observe close agreement between simulation and experiments for both the cases. The analyses are extended to the five-actuator robot, where simulations accurately predict the static and AC robot motions, including shapes for applied DC voltage inputs, nearly-static "inchworm" motion, and jumping (in vertical as well as vertical and horizontal directions). These motions exhibit complex non-linear behavior, with forward robot motion reaching ~1 cm/s. Our open-source code can be found at: https://github.com/zhiwuz/sfers. △ Less

Submitted 27 February, 2022; originally announced February 2022.

Comments: Accepted to the International Conference on Robotics and Automation (ICRA) 2022. Video: https://youtu.be/nHcH3V7rCrk

Journal ref: 2022 International Conference on Robotics and Automation (ICRA), 2022, pp. 5199-5204

A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level

Authors: Iddo Drori, Sarah Zhang, Reece Shuttleworth, Leonard Tang, Albert Lu, Elizabeth Ke, Kevin Liu, Linda Chen, Sunny Tran, Newman Cheng, Roman Wang, Nikhil Singh, Taylor L. Patti, Jayson Lynch, Avi Shporer, Nakul Verma, Eugene Wu, Gilbert Strang

Abstract: We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level. We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy. We curate a new dataset of questions from MIT's largest m… ▽ More We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level. We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy. We curate a new dataset of questions from MIT's largest mathematics courses (Single Variable and Multivariable Calculus, Differential Equations, Introduction to Probability and Statistics, Linear Algebra, and Mathematics for Computer Science) and Columbia University's Computational Linear Algebra. We solve questions from a MATH dataset (on Prealgebra, Algebra, Counting and Probability, Intermediate Algebra, Number Theory, and Precalculus), the latest benchmark of advanced mathematics problems designed to assess mathematical reasoning. We randomly sample questions and generate solutions with multiple modalities, including numbers, equations, and plots. The latest GPT-3 language model pre-trained on text automatically solves only 18.8% of these university questions using zero-shot learning and 30.8% using few-shot learning and the most recent chain of thought prompting. In contrast, program synthesis with few-shot learning using Codex fine-tuned on code generates programs that automatically solve 81% of these questions. Our approach improves the previous state-of-the-art automatic solution accuracy on the benchmark topics from 8.8% to 81.1%. We perform a survey to evaluate the quality and difficulty of generated questions. This work is the first to automatically solve university-level mathematics course questions at a human level and the first work to explain and generate university-level mathematics course questions at scale, a milestone for higher education. △ Less

Submitted 30 May, 2022; v1 submitted 31 December, 2021; originally announced December 2021.

Comments: 181 pages, 8 figures, 280 tables

Reputation-based PoS for the Restriction of Illicit Activities on Blockchain: Algorand Usecase

Authors: Mayank Pandey, Rachit Agarwal, Sandeep Kumar Shukla, Nishchal Kumar Verma

Abstract: In cryptocurrency-based permissionless blockchain networks, the decentralized structure enables any user to join and operate across different regions. The criminal entities exploit it by using cryptocurrency transactions on the blockchain to facilitate activities such as money laundering, gambling, and ransomware attacks. In recent times, different machine learning-based techniques can detect such… ▽ More In cryptocurrency-based permissionless blockchain networks, the decentralized structure enables any user to join and operate across different regions. The criminal entities exploit it by using cryptocurrency transactions on the blockchain to facilitate activities such as money laundering, gambling, and ransomware attacks. In recent times, different machine learning-based techniques can detect such criminal elements based on blockchain transaction data. However, there is no provision within the blockchain to deal with such elements. We propose a reputation-based methodology for response to the users detected carrying out the aforementioned illicit activities. We select Algorand blockchain to implement our methodology by incorporating it within the consensus protocol. The theoretical results obtained prove the restriction and exclusion of criminal elements through block proposal rejection and attenuation of the voting power as a validator for such entities. Further, we analyze the efficacy of our method and show that it puts no additional strain on the communication resources. △ Less

Submitted 16 August, 2025; v1 submitted 21 December, 2021; originally announced December 2021.

Responsive parallelized architecture for deploying deep learning models in production environments

Authors: Nikhil Verma, Krishna Prasad

Abstract: Recruiters can easily shortlist candidates for jobs via viewing their curriculum vitae (CV) document. Unstructured document CV beholds candidate's portfolio and named entities listing details. The main aim of this study is to design and propose a web oriented, highly responsive, computational pipeline that systematically predicts CV entities using hierarchically-refined label attention networks. D… ▽ More Recruiters can easily shortlist candidates for jobs via viewing their curriculum vitae (CV) document. Unstructured document CV beholds candidate's portfolio and named entities listing details. The main aim of this study is to design and propose a web oriented, highly responsive, computational pipeline that systematically predicts CV entities using hierarchically-refined label attention networks. Deep learning models specialized for named entity recognition were trained on large dataset to predict relevant fields. The article suggests an optimal strategy to use a number of deep learning models in parallel and predict in real time. We demonstrate selection of light weight micro web framework using Analytical Hierarchy Processing algorithm and focus on an approach useful to deploy large deep learning model-based pipelines in production ready environments using microservices. Deployed models and architecture proposed helped in parsing normal CV in less than 700 milliseconds for sequential flow of requests. △ Less

Submitted 10 July, 2023; v1 submitted 14 December, 2021; originally announced December 2021.

Comments: 20 Pages

An analysis of document graph construction methods for AMR summarization

Authors: Fei-Tzin Lee, Chris Kedzie, Nakul Verma, Kathleen McKeown

Abstract: Meaning Representation (AMR) is a graph-based semantic representation for sentences, composed of collections of concepts linked by semantic relations. AMR-based approaches have found success in a variety of applications, but a challenge to using it in tasks that require document-level context is that it only represents individual sentences. Prior work in AMR-based summarization has automatically m… ▽ More Meaning Representation (AMR) is a graph-based semantic representation for sentences, composed of collections of concepts linked by semantic relations. AMR-based approaches have found success in a variety of applications, but a challenge to using it in tasks that require document-level context is that it only represents individual sentences. Prior work in AMR-based summarization has automatically merged the individual sentence graphs into a document graph, but the method of merging and its effects on summary content selection have not been independently evaluated. In this paper, we present a novel dataset consisting of human-annotated alignments between the nodes of paired documents and summaries which may be used to evaluate (1) merge strategies; and (2) the performance of content selection methods over nodes of a merged or unmerged AMR graph. We apply these two forms of evaluation to prior work as well as a new method for node merging and show that our new method has significantly better performance than prior work. △ Less

Submitted 27 November, 2021; originally announced November 2021.

Solving Probability and Statistics Problems by Program Synthesis

Authors: Leonard Tang, Elizabeth Ke, Nikhil Singh, Nakul Verma, Iddo Drori

Abstract: We solve university level probability and statistics questions by program synthesis using OpenAI's Codex, a Transformer trained on text and fine-tuned on code. We transform course problems from MIT's 18.05 Introduction to Probability and Statistics and Harvard's STAT110 Probability into programming tasks. We then execute the generated code to get a solution. Since these course questions are ground… ▽ More We solve university level probability and statistics questions by program synthesis using OpenAI's Codex, a Transformer trained on text and fine-tuned on code. We transform course problems from MIT's 18.05 Introduction to Probability and Statistics and Harvard's STAT110 Probability into programming tasks. We then execute the generated code to get a solution. Since these course questions are grounded in probability, we often aim to have Codex generate probabilistic programs that simulate a large number of probabilistic dependencies to compute its solution. Our approach requires prompt engineering to transform the question from its original form to an explicit, tractable form that results in a correct program and solution. To estimate the amount of work needed to translate an original question into its tractable form, we measure the similarity between original and transformed questions. Our work is the first to introduce a new dataset of university-level probability and statistics problems and solve these problems in a scalable fashion using the program synthesis capabilities of large language models. △ Less

Submitted 16 November, 2021; originally announced November 2021.

Comments: 33 pages, 4 figures

Solving Linear Algebra by Program Synthesis

Authors: Iddo Drori, Nakul Verma

Abstract: We solve MIT's Linear Algebra 18.06 course and Columbia University's Computational Linear Algebra COMS3251 courses with perfect accuracy by interactive program synthesis. This surprisingly strong result is achieved by turning the course questions into programming tasks and then running the programs to produce the correct answers. We use OpenAI Codex with zero-shot learning, without providing any e… ▽ More We solve MIT's Linear Algebra 18.06 course and Columbia University's Computational Linear Algebra COMS3251 courses with perfect accuracy by interactive program synthesis. This surprisingly strong result is achieved by turning the course questions into programming tasks and then running the programs to produce the correct answers. We use OpenAI Codex with zero-shot learning, without providing any examples in the prompts, to synthesize code from questions. We quantify the difference between the original question text and the transformed question text that yields a correct answer. Since all COMS3251 questions are not available online the model is not overfitting. We go beyond just generating code for questions with numerical answers by interactively generating code that also results visually pleasing plots as output. Finally, we automatically generate new questions given a few sample questions which may be used as new course content. This work is a significant step forward in solving quantitative math problems and opens the door for solving many university level STEM courses by machine. △ Less

Submitted 15 November, 2021; originally announced November 2021.

Comments: 32 pages, 3 figures

Guided Sampling-based Evolutionary Deep Neural Network for Intelligent Fault Diagnosis

Authors: Arun K. Sharma, Nishchal K. Verma

Abstract: The diagnostic performance of most of the deep learning models is greatly affected by the selection of model architecture and hyperparameters. Manual selection of model architecture is not feasible as training and evaluating the different architectures of deep learning models is a time-consuming process. Therefore, we have proposed a novel framework of evolutionary deep neural network which uses p… ▽ More The diagnostic performance of most of the deep learning models is greatly affected by the selection of model architecture and hyperparameters. Manual selection of model architecture is not feasible as training and evaluating the different architectures of deep learning models is a time-consuming process. Therefore, we have proposed a novel framework of evolutionary deep neural network which uses policy gradient to guide the evolution of DNN architecture towards maximum diagnostic accuracy. We have formulated a policy gradient-based controller which generates an action to sample the new model architecture at every generation such that the optimality is obtained quickly. The fitness of the best model obtained is used as a reward to update the policy parameters. Also, the best model obtained is transferred to the next generation for quick model evaluation in the NSGA-II evolutionary framework. Thus, the algorithm gets the benefits of fast non-dominated sorting as well as quick model evaluation. The effectiveness of the proposed framework has been validated on three datasets: the Air Compressor dataset, Case Western Reserve University dataset, and Paderborn university dataset. △ Less

Submitted 23 February, 2022; v1 submitted 12 November, 2021; originally announced November 2021.

Piezoelectric Soft Robot Inchworm Motion by Tuning Ground Friction through Robot Shape: Quasi-Static Modeling and Experimental Validation

Authors: Zhiwu Zheng, Prakhar Kumar, Yenan Chen, Hsin Cheng, Sigurd Wagner, Minjie Chen, Naveen Verma, James C. Sturm

Abstract: Electrically-driven soft robots based on piezoelectric actuators may enable compact form factors and maneuverability in complex environments. In most prior work, piezoelectric actuators are used to control a single degree of freedom. In this work, the coordinated activation of five independent piezoelectric actuators, attached to a common metal foil, is used to implement inchworm-inspired crawling… ▽ More Electrically-driven soft robots based on piezoelectric actuators may enable compact form factors and maneuverability in complex environments. In most prior work, piezoelectric actuators are used to control a single degree of freedom. In this work, the coordinated activation of five independent piezoelectric actuators, attached to a common metal foil, is used to implement inchworm-inspired crawling motion in a robot that is less than 0.5 mm thick. The motion is based on the control of its friction to the ground through the robot's shape, in which one end of the robot (depending on its shape) is anchored to the ground by static friction, while the rest of its body expands or contracts. A complete analytical model of the robot shape, which includes gravity, is developed to quantify the robot shape, friction, and displacement. After validation of the model by experiments, the robot's five actuators are collectively sequenced for inchworm-like forward and backward motion. △ Less

Submitted 14 December, 2023; v1 submitted 1 November, 2021; originally announced November 2021.

Comments: Accepted to IEEE Transactions on Robotics

Journal ref: IEEE Transactions on Robotics. 2024 Jan 11

Knowledge Transfer based Evolutionary Deep Neural Network for Intelligent Fault Diagnosis

Authors: Arun K. Sharma, Nishchal K. Verma

Abstract: A faster response with commendable accuracy in intelligent systems is essential for the reliability and smooth operations of industrial machines. Two main challenges affect the design of such intelligent systems: (i) the selection of a suitable model and (ii) domain adaptation if there is a continuous change in operating conditions. Therefore, we propose an evolutionary Net2Net transformation (Evo… ▽ More A faster response with commendable accuracy in intelligent systems is essential for the reliability and smooth operations of industrial machines. Two main challenges affect the design of such intelligent systems: (i) the selection of a suitable model and (ii) domain adaptation if there is a continuous change in operating conditions. Therefore, we propose an evolutionary Net2Net transformation (EvoN2N) that finds the best suitable DNN architecture with limited availability of labeled data samples. Net2Net transformation-based quick learning algorithm has been used in the evolutionary framework of Non-dominated sorting genetic algorithm II to obtain the best DNN architecture. Net2Net transformation-based quick learning algorithm uses the concept of knowledge transfer from one generation to the next for faster fitness evaluation. The proposed framework can obtain the best model for intelligent fault diagnosis without a long and time-consuming search process. The proposed framework has been validated on the Case Western Reserve University dataset, the Paderborn University dataset, and the gearbox fault detection dataset under different operating conditions. The best models obtained are capable of demonstrating an excellent diagnostic performance and classification accuracy of almost up to 100% for most of the operating conditions. △ Less

Submitted 21 March, 2025; v1 submitted 28 September, 2021; originally announced September 2021.

Comments: Submitted to IEEE Transactions on Sustainable Computing

Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review

Authors: Irene Li, Jessica Pan, Jeremy Goldwasser, Neha Verma, Wai Pan Wong, Muhammed Yavuz Nuzumlalı, Benjamin Rosand, Yixin Li, Matthew Zhang, David Chang, R. Andrew Taylor, Harlan M. Krumholz, Dragomir Radev

Abstract: Electronic health records (EHRs), digital collections of patient healthcare events and observations, are ubiquitous in medicine and critical to healthcare delivery, operations, and research. Despite this central role, EHRs are notoriously difficult to process automatically. Well over half of the information stored within EHRs is in the form of unstructured text (e.g. provider notes, operation repo… ▽ More Electronic health records (EHRs), digital collections of patient healthcare events and observations, are ubiquitous in medicine and critical to healthcare delivery, operations, and research. Despite this central role, EHRs are notoriously difficult to process automatically. Well over half of the information stored within EHRs is in the form of unstructured text (e.g. provider notes, operation reports) and remains largely untapped for secondary use. Recently, however, newer neural network and deep learning approaches to Natural Language Processing (NLP) have made considerable advances, outperforming traditional statistical and rule-based systems on a variety of tasks. In this survey paper, we summarize current neural NLP methods for EHR applications. We focus on a broad scope of tasks, namely, classification and prediction, word embeddings, extraction, generation, and other topics such as question answering, phenotyping, knowledge graphs, medical dialogue, multilinguality, interpretability, etc. △ Less

Submitted 6 July, 2021; originally announced July 2021.

Comments: 33 pages, 11 figures

MSC Class: 68T50 ACM Class: I.2.7

On fine-tuning of Autoencoders for Fuzzy rule classifiers

Authors: Rahul Kumar Sevakula, Nishchal Kumar Verma, Hisao Ishibuchi

Abstract: Recent discoveries in Deep Neural Networks are allowing researchers to tackle some very complex problems such as image classification and audio classification, with improved theoretical and empirical justifications. This paper presents a novel scheme to incorporate the use of autoencoders in Fuzzy rule classifiers (FRC). Autoencoders when stacked can learn the complex non-linear relationships amon… ▽ More Recent discoveries in Deep Neural Networks are allowing researchers to tackle some very complex problems such as image classification and audio classification, with improved theoretical and empirical justifications. This paper presents a novel scheme to incorporate the use of autoencoders in Fuzzy rule classifiers (FRC). Autoencoders when stacked can learn the complex non-linear relationships amongst data, and the proposed framework built towards FRC can allow users to input expert knowledge to the system. This paper further introduces four novel fine-tuning strategies for autoencoders to improve the FRC's classification and rule reduction performance. The proposed framework has been tested across five real-world benchmark datasets. Elaborate comparisons with over 15 previous studies, and across 10-fold cross validation performance, suggest that the proposed methods are capable of building FRCs which can provide state of the art accuracies. △ Less

Submitted 21 June, 2021; originally announced June 2021.

FeTaQA: Free-form Table Question Answering

Authors: Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Nick Schoelkopf, Riley Kong, Xiangru Tang, Murori Mutuma, Ben Rosand, Isabel Trindade, Renusree Bandaru, Jacob Cunningham, Caiming Xiong, Dragomir Radev

Abstract: Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers. To address these issues and to demonstrate the full challenge of table question an… ▽ More Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers. To address these issues and to demonstrate the full challenge of table question answering, we introduce FeTaQA, a new dataset with 10K Wikipedia-based {table, question, free-form answer, supporting table cells} pairs. FeTaQA yields a more challenging table question answering setting because it requires generating free-form text answers after retrieval, inference, and integration of multiple discontinuous facts from a structured knowledge source. Unlike datasets of generative QA over text in which answers are prevalent with copies of short text spans from the source, answers in our dataset are human-generated explanations involving entities and their high-level relations. We provide two benchmark methods for the proposed task: a pipeline method based on semantic-parsing-based QA systems and an end-to-end method based on large pretrained text generation models, and show that FeTaQA poses a challenge for both methods. △ Less

Submitted 1 April, 2021; originally announced April 2021.