Himanshu Gupta

Himanshu Gupta, Shreyas Verma, Ujjwala Anantheswaran et al. · gatech

Multi-modal Large Language Models (MLLMs) exhibit impressive problem-solving abilities in various domains, but their visual comprehension and abstract reasoning skills remain under-evaluated. To this end, we present PolyMATH, a challenging benchmark aimed at evaluating the general cognitive reasoning abilities of MLLMs. PolyMATH comprises 5,000 manually collected high-quality images of cognitive textual and visual challenges across 10 distinct categories, including pattern recognition, spatial reasoning, and relative reasoning. We conducted a comprehensive, and quantitative evaluation of 15 MLLMs using four diverse prompting strategies, including Chain-of-Thought and Step-Back. The best scores achieved on PolyMATH are ~41%, ~36%, and ~27%, obtained by Claude-3.5 Sonnet, GPT-4o and Gemini-1.5 Pro respectively - highlighting the logical and visual complexity of these questions. A further fine-grained error analysis reveals that these models struggle to understand spatial relations and perform drawn-out, high-level reasoning. This is further strengthened by our ablation study estimating MLLM performance when given textual descriptions in place of diagrams. As evidenced by ~4% improvement over textual descriptions as opposed to actual images, we discover that models do not truly comprehend visual diagrams and the spatial information therein, and are thus prone to logical errors. Finally, we evaluate the OpenAI o1 models and find that their performance only matches the human baseline, highlighting the difficulty of the benchmark. The results on PolyMATH highlight the room for improvement in multi-modal reasoning and provide unique insights to guide the development of future MLLMs.

Xiaojie Fan, C. R. Ramakrishnan, Himanshu Gupta

The development of large-scale quantum networks requires not only advances in physical-layer technologies but also a comprehensive protocol stack that integrates communication, control, and resource management across all layers. We present the first such protocol stack, which introduces a Global Entanglement Module (GEM) that maintains a consistent, network-wide view of entanglement resources through distributed synchronization strategies. By enabling real-time adaptive execution of entanglement distribution plans, GEM bridges the gap between static planning and dynamic operation. The stack naturally supports pre-distributed entanglement, purification, and multi-partite state generation, making it applicable to a broad range of quantum networking applications. We design and evaluate multiple adaptive heuristics for real-time execution and show that a lightweight scoring-based strategy consistently achieves the best performance, improving entanglement generation rates by about 20% over a globally optimal but non-adaptive fixed-tree baseline and achieving more than a two-fold improvement relative to recent connectionless approaches. Across all scenarios-including predistribution and fidelity analysis-GEM consistently enables lower latency and robust operation. These results establish a practical pathway toward scalable, adaptive quantum internet systems.

Mihir Parmar, Aakanksha Naik, Himanshu Gupta et al.

Many large language models (LLMs) for medicine have largely been evaluated on short texts, and their ability to handle longer sequences such as a complete electronic health record (EHR) has not been systematically explored. Assessing these models on long sequences is crucial since prior work in the general domain has demonstrated performance degradation of LLMs on longer texts. Motivated by this, we introduce LongBoX, a collection of seven medical datasets in text-to-text format, designed to investigate model performance on long sequences. Preliminary experiments reveal that both medical LLMs (e.g., BioGPT) and strong general domain LLMs (e.g., FLAN-T5) struggle on this benchmark. We further evaluate two techniques designed for long-sequence handling: (i) local-global attention, and (ii) Fusion-in-Decoder (FiD). Our results demonstrate mixed results with long-sequence handling - while scores on some datasets increase, there is substantial room for improvement. We hope that LongBoX facilitates the development of more effective long-sequence techniques for the medical domain. Data and source code are available at https://github.com/Mihir3009/LongBoX.

Himanshu Gupta, Neeraj Varshney, Swaroop Mishra et al. · amazon-science

In current NLP research, large-scale language models and their abilities are widely being discussed. Some recent works have also found notable failures of these models. Often these failure examples involve complex reasoning abilities. This work focuses on a simple commonsense ability, reasoning about when an action (or its effect) is feasible. To this end, we introduce FeasibilityQA, a question-answering dataset involving binary classification (BCQ) and multi-choice multi-correct questions (MCQ) that test understanding of feasibility. We show that even state-of-the-art models such as GPT-3, GPT-2, and T5 struggle to answer the feasibility questions correctly. Specifically, on MCQ and BCQ questions, GPT-3 achieves an accuracy of just (19%, 62%) and (25%, 64%) in zero-shot and few-shot settings, respectively. We also evaluate models by providing relevant knowledge statements required to answer the question. We find that the additional knowledge leads to a 7% gain in performance, but the overall performance still remains low. These results make one wonder how much commonsense knowledge about action feasibility is encoded in state-of-the-art models and how well they can reason about it.

Himanshu Gupta, Kevin Scaria, Ujjwala Anantheswaran et al. · gatech

The rapid advancement of large language models (LLMs) has sparked interest in data synthesis techniques, aiming to generate diverse and high-quality synthetic datasets. However, these synthetic datasets often suffer from a lack of diversity and added noise. In this paper, we present TarGEN, a multi-step prompting strategy for generating high-quality synthetic datasets utilizing a LLM. An advantage of TarGEN is its seedless nature; it does not require specific task instances, broadening its applicability beyond task replication. We augment TarGEN with a method known as self-correction empowering LLMs to rectify inaccurately labeled instances during dataset creation, ensuring reliable labels. To assess our technique's effectiveness, we emulate 8 tasks from the SuperGLUE benchmark and finetune various language models, including encoder-only, encoder-decoder, and decoder-only models on both synthetic and original training sets. Evaluation on the original test set reveals that models trained on datasets generated by TarGEN perform approximately 1-2% points better than those trained on original datasets (82.84% via syn. vs. 81.12% on og. using Flan-T5). When incorporating instruction tuning, the performance increases to 84.54% on synthetic data vs. 81.49% on original data by Flan-T5. A comprehensive analysis of the synthetic dataset compared to the original dataset reveals that the synthetic dataset demonstrates similar or higher levels of dataset complexity and diversity. Furthermore, the synthetic dataset displays a bias level that aligns closely with the original dataset. Finally, when pre-finetuned on our synthetic SuperGLUE dataset, T5-3B yields impressive results on the OpenLLM leaderboard, surpassing the model trained on the Self-Instruct dataset by 4.14% points. We hope that TarGEN can be helpful for quality data generation and reducing the human efforts to create complex benchmarks.

Nihar Sahoo, Himanshu Gupta, Pushpak Bhattacharyya

With the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done to detect unintended social bias from these toxic language datasets. This paper introduces a new dataset ToxicBias curated from the existing dataset of Kaggle competition named "Jigsaw Unintended Bias in Toxicity Classification". We aim to detect social biases, their categories, and targeted groups. The dataset contains instances annotated for five different bias categories, viz., gender, race/ethnicity, religion, political, and LGBTQ. We train transformer-based models using our curated datasets and report baseline performance for bias identification, target generation, and bias implications. Model biases and their mitigation are also discussed in detail. Our study motivates a systematic extraction of social bias data from toxic language datasets. All the codes and dataset used for experiments in this work are publicly available

Yunfan Li, Vinayak Shenoy, Prateek Prasanna et al.

Automatic recognition of surgical phases in surgical videos is a fundamental task in surgical workflow analysis. In this report, we propose a Transformer-based method that utilizes calibrated confidence scores for a 2-stage inference pipeline, which dynamically switches between a baseline model and a separately trained transition model depending on the calibrated confidence level. Our method outperforms the baseline model on the Cholec80 dataset, and can be applied to a variety of action segmentation methods.

Sandhya Singh, Prapti Roy, Nihar Sahoo et al.

Movies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always found to be the need of storyline but can creep in as the author's bias. Movie production houses would prefer to ascertain that the bias present in a script is the story's demand. Today, when deep learning models can give human-level accuracy in multiple tasks, having an AI solution to identify the biases present in the script at the writing stage can help them avoid the inconvenience of stalled release, lawsuits, etc. Since AI solutions are data intensive and there exists no domain specific data to address the problem of biases in scripts, we introduce a new dataset of movie scripts that are annotated for identity bias. The dataset contains dialogue turns annotated for (i) bias labels for seven categories, viz., gender, race/ethnicity, religion, age, occupation, LGBTQ, and other, which contains biases like body shaming, personality bias, etc. (ii) labels for sensitivity, stereotype, sentiment, emotion, emotion intensity, (iii) all labels annotated with context awareness, (iv) target groups and reason for bias labels and (v) expert-driven group-validation process for high quality annotations. We also report various baseline performances for bias identification and category detection on our dataset.

Kevin Scaria, Himanshu Gupta, Siddharth Goyal et al.

We introduce InstructABSA, an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model (Tk-Instruct) for ABSA subtasks, yielding significant performance improvements. Experimental results on the Sem Eval 2014, 15, and 16 datasets demonstrate that InstructABSA outperforms the previous state-of-the-art (SOTA) approaches on Term Extraction (ATE), Sentiment Classification(ATSC) and Sentiment Pair Extraction (ASPE) subtasks. In particular, InstructABSA outperforms the previous state-of-the-art (SOTA) on the Rest14 ATE subtask by 5.69% points, the Rest15 ATSC subtask by 9.59% points, and the Lapt14 AOPE subtask by 3.37% points, surpassing 7x larger models. We also get competitive results on AOOE, AOPE, and AOSTE subtasks indicating strong generalization ability to all subtasks. Exploring sample efficiency reveals that just 50% train data is required to get competitive results with other instruction tuning approaches. Lastly, we assess the quality of instructions and observe that InstructABSA's performance experiences a decline of ~10% when adding misleading examples.

Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta et al. · amazon-science

Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under fixed active computation, model quality scales predictably with total parameters, and MoEs realize this by increasing expert count. However, training large MoEs is expensive, as memory requirements and inter-device communication both scale with total parameter count. We propose expert upcycling, a method for progressively expanding MoE capacity by increasing the number of experts during continued pre-training (CPT). Given a trained E-expert model, the upcycling operator constructs an mE-expert model through expert duplication and router extension while holding top-K routing fixed, preserving per-token inference cost. Duplication provides a warm initialization: the expanded model inherits the source checkpoint's learned representations, starting from a substantially lower loss than random initialization. Subsequent CPT then breaks the symmetry among duplicated experts to drive specialization. We formalize the upcycling operator and develop a theoretical framework decomposing the quality gap into a capacity term and an initialization term. We further introduce utility-based expert selection, which uses gradient-based importance scores to guide non-uniform duplication, more than tripling gap closure when CPT is limited. In our 7B-13B total parameter experiments, the upcycled model matches the fixed-size baseline on validation loss while saving 32% of GPU hours. Comprehensive ablations across model scales, activation ratios, MoE architectures, and training budgets yield a practical recipe for deploying expert upcycling, establishing it as a principled, compute-efficient alternative to training large MoE models from scratch.

Himanshu Gupta, Bradley Hayes, Zachary Sunberg

This paper presents a hybrid online Partially Observable Markov Decision Process (POMDP) planning system that addresses the problem of autonomous navigation in the presence of multi-modal uncertainty introduced by other agents in the environment. As a particular example, we consider the problem of autonomous navigation in dense crowds of pedestrians and among obstacles. Popular approaches to this problem first generate a path using a complete planner (e.g., Hybrid A*) with ad-hoc assumptions about uncertainty, then use online tree-based POMDP solvers to reason about uncertainty with control over a limited aspect of the problem (i.e. speed along the path). We present a more capable and responsive real-time approach enabling the POMDP planner to control more degrees of freedom (e.g., both speed AND heading) to achieve more flexible and efficient solutions. This modification greatly extends the region of the state space that the POMDP planner must reason over, significantly increasing the importance of finding effective roll-out policies within the limited computational budget that real time control affords. Our key insight is to use multi-query motion planning techniques (e.g., Probabilistic Roadmaps or Fast Marching Method) as priors for rapidly generating efficient roll-out policies for every state that the POMDP planning tree might reach during its limited horizon search. Our proposed approach generates trajectories that are safe and significantly more efficient than the previous approach, even in densely crowded dynamic environments with long planning horizons.

Yunfan Li, Himanshu Gupta, Haibin Ling et al.

Cholecystectomy (gallbladder removal) is one of the most common procedures in the US, with more than 1.2M procedures annually. Compared with classical open cholecystectomy, laparoscopic cholecystectomy (LC) is associated with significantly shorter recovery period, and hence is the preferred method. However, LC is also associated with an increase in bile duct injuries (BDIs), resulting in significant morbidity and mortality. The primary cause of BDIs from LCs is misidentification of the cystic duct with the bile duct. Critical view of safety (CVS) is the most effective of safety protocols, which is said to be achieved during the surgery if certain criteria are met. However, due to suboptimal understanding and implementation of CVS, the BDI rates have remained stable over the last three decades. In this paper, we develop deep-learning techniques to automate the assessment of CVS in LCs. An innovative aspect of our research is on developing specialized learning techniques by incorporating domain knowledge to compensate for the limited training data available in practice. In particular, our CVS assessment process involves a fusion of two segmentation maps followed by an estimation of a certain region of interest based on anatomical structures close to the gallbladder, and then finally determination of each of the three CVS criteria via rule-based assessment of structural information. We achieved a gain of over 11.8% in mIoU on relevant classes with our two-stream semantic segmentation approach when compared to a single-model baseline, and 1.84% in mIoU with our proposed Sobel loss function when compared to a Transformer-based baseline model. For CVS criteria, we achieved up to 16% improvement and, for the overall CVS assessment, we achieved 5% improvement in balanced accuracy compared to DeepCVS under the same experiment settings.

Himanshu Gupta, Pratik Jayarao, Chaitanya Dwivedi et al.

Code-mixing and code-switching (CSW) remain challenging phenomena for large language models (LLMs). Despite recent advances in multilingual modeling, LLMs often struggle in mixed-language settings, exhibiting systematic degradation in grammaticality, factuality, and safety behavior. This work provides a comprehensive overview of CSW research in modern large language model settings. We introduce a unifying taxonomy that organizes prior work along dimensions of data, modeling, and evaluation, and we distill these findings into a practical playbook of actionable recommendations for building, adapting, and evaluating CSW-capable LLMs. We review modeling approaches ranging from CSW-tailored pre-training and task-specific post-training to prompting strategies and in-context learning. We analyze current evaluation practices, highlighting sources of instability and limited reproducibility, and we catalog existing benchmarks while critically examining their linguistic coverage and English-centric biases. Finally, we discuss emerging safety concerns, including use of code-mixing as a mechanism for bypassing model safeguards, and identify open research challenges.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

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

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Himanshu Gupta, Paul Motter, Aritra Chakrabarty et al.

Solving multi-robot motion planning (MRMP) requires generating collision-free kinodynamically feasible trajectories for multiple interacting robots. We introduce Kinodynamic Translation-Invariant Edge Bundles or KiTE-Extend, a planner-agnostic action selection mechanism for sampling-based kinodynamic motion planning. KiTE-Extend uses a library of trajectory segments computed offline to guide action selection during online planning, improving the ability of existing planners to identify feasible motion segments without altering state propagation, collision checking, or cost evaluation, and without changing their theoretical guarantees. While KiTE-Extend can modestly improve single-agent planners, its benefits are most clear in the multi-agent setting, where it is able to explore more effectively and significantly improve planning through the dense spatiotemporal constraints introduced by robot-robot interaction. Through experiments on multiple kinodynamic systems and environments, we show that KiTE-Extend reduces planning time and improves scalability across the three most common MRMP paradigms: centralized, prioritized, and conflict-based.

Prerna Agarwal, Himanshu Gupta, Soujanya Soni et al.

Recent advancements in Large Language Models (LLMs) has lead to the development of agents capable of complex reasoning and interaction with external tools. In enterprise contexts, the effective use of such tools that are often enabled by application programming interfaces (APIs), is hindered by poor documentation, complex input or output schema, and large number of operations. These challenges make tool selection difficult and reduce the accuracy of payload formation by up to 25%. We propose ACE, an automated tool creation and enrichment framework that transforms enterprise APIs into LLM-compatible tools. ACE, (i) generates enriched tool specifications with parameter descriptions and examples to improve selection and invocation accuracy, and (ii) incorporates a dynamic shortlisting mechanism that filters relevant tools at runtime, reducing prompt complexity while maintaining scalability. We validate our framework on both proprietary and open-source APIs and demonstrate its integration with agentic frameworks. To the best of our knowledge, ACE is the first end-to-end framework that automates the creation, enrichment, and dynamic selection of enterprise API tools for LLM agents.

Pratik Jayarao, Himanshu Gupta, Neeraj Varshney et al. · amazon-science

As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison of "thinking" and "non-thinking" LLMs in the LLM-as-a-judge paradigm using open-source Qwen 3 models of relatively small sizes (0.6B, 1.7B, and 4B parameters). We evaluate both accuracy and computational efficiency (FLOPs) on RewardBench tasks, and further examine augmentation strategies for non-thinking models, including in-context learning, rubric-guided judging, reference-based evaluation, and n-best aggregation. Our results show that despite these enhancements, non-thinking models generally fall short of their thinking counterparts. Our results show that thinking models achieve approximately 10% points higher accuracy with little overhead (under 2x), in contrast to augmentation strategies like few-shot learning, which deliver modest gains at a higher cost (>8x). Bias and robustness analyses further demonstrate that thinking models maintain significantly greater consistency under a variety of bias conditions such as positional, bandwagon, identity, diversity, and random biases (6% higher on average). We further extend our experiments to the multilingual setting and our results confirm that explicit reasoning extends its benefits beyond English. Overall, our work results in several important findings that provide systematic evidence that explicit reasoning offers clear advantages in the LLM-as-a-judge paradigm not only in accuracy and efficiency but also in robustness.

Himanshu Gupta, Aditya Jaiswal

Predicting a fast and accurate model for stock price forecasting is been a challenging task and this is an active area of research where it is yet to be found which is the best way to forecast the stock price. Machine learning, deep learning and statistical analysis techniques are used here to get the accurate result so the investors can see the future trend and maximize the return of investment in stock trading. This paper will review many deep learning algorithms for stock price forecasting. We use a record of s&p 500 index data for training and testing. The survey motive is to check various deep learning and statistical model techniques for stock price forecasting that are Moving Averages, ARIMA which are statistical techniques and LSTM, RNN, CNN, and FULL CNN which are deep learning models. It will discuss various models, including the Auto regression integration moving average model, the Recurrent neural network model, the long short-term model which is the type of RNN used for long dependency for data, the convolutional neural network model, and the full convolutional neural network model, in terms of error calculation or percentage of accuracy that how much it is accurate which measures by the function like Root mean square error, mean absolute error, mean squared error. The model can be used to predict the stock price by checking the low MAE value as lower the MAE value the difference between the predicting and the actual value will be less and this model will predict the price more accurately than other models.

Aditya Kallappa, Palash Kamble, Abhinav Ravi et al.

India is a diverse society with unique challenges in developing AI systems, including linguistic diversity, oral traditions, data accessibility, and scalability. Existing foundation models are primarily trained on English, limiting their effectiveness for India's population. Indic languages comprise only 1 percent of Common Crawl corpora despite India representing 18 percent of the global population, leading to linguistic biases. Thousands of regional languages, dialects, and code mixing create additional representation challenges due to sparse training data. We introduce Krutrim LLM, a 2 trillion token multilingual model designed for India's linguistic landscape. It incorporates the largest known Indic dataset, mitigating data scarcity and ensuring balanced performance across dialects. Krutrim outperforms or matches state-of-the-art models on Indic benchmarks while maintaining competitive English performance. Despite being significantly smaller in training flops, Krutrim LLM matches or exceeds models like LLAMA-2 on 10 out of 16 tasks, with an average score of 0.57 versus 0.55. This evidences Krutrim's flexible multilingual fluency across diverse linguistic contexts. Krutrim is integrated with real-time search to improve factual accuracy in conversational AI applications. This enhances accessibility for over 1 billion users worldwide. Through intentional design choices addressing data imbalances, Krutrim LLM signifies meaningful progress in building ethical, globally representative AI models.

Purnendu Prabhat, Himanshu Gupta, Ajeet Kumar Vishwakarma

The majority of computer vision applications that handle images featuring humans use face detection as a core component. Face detection still has issues, despite much research on the topic. Face detection's accuracy and speed might yet be increased. This review paper shows the progress made in this area as well as the substantial issues that still need to be tackled. The paper provides research directions that can be taken up as research projects in the field of face detection.

Gemini Team, Rohan Anil, Sebastian Borgeaud et al.

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

Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar et al.

Event detection refers to identifying event occurrences in a text and comprises of two subtasks; event identification and classification. We present EDM3, a novel approach for Event Detection that formulates three generative tasks: identification, classification, and combined detection. We show that EDM3 helps to learn transferable knowledge that can be leveraged to perform Event Detection and its subtasks concurrently, mitigating the error propagation inherent in pipelined approaches. Unlike previous dataset- or domain-specific approaches, EDM3 utilizes the existing knowledge of language models, allowing it to be trained over any classification schema. We evaluate EDM3 on multiple event detection datasets: RAMS, WikiEvents, MAVEN, and MLEE, showing that EDM3 outperforms 1) single-task performance by 8.4% on average and 2) multi-task performance without instructional prompts by 2.4% on average. We obtain SOTA results on RAMS (71.3% vs. 65.1% F-1) and competitive performance on other datasets. We analyze our approach to demonstrate its efficacy in low-resource and multi-sentence settings. We also show the effectiveness of this approach on non-standard event configurations such as multi-word and multi-class event triggers. Overall, our results show that EDM3 is a promising approach for Event Detection that has the potential for real-world applications.

Himanshu Gupta, Saurabh Arjun Sawant, Swaroop Mishra et al.

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream training data for finetuning. Often in real-world situations, there is a scarcity of data available for finetuning, falling somewhere between few shot inference and fully supervised finetuning. In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks by estimating the minimal downstream training data required by them to perform transfer learning and match the performance of state-of-the-art (SOTA) supervised models. We conduct experiments on 119 tasks from Super Natural Instructions (SuperNI) in both the single task learning (STL) and multi task learning (MTL) settings. Our findings reveal that, in the STL setting, instruction tuned models equipped with 25% of the downstream train data surpass the SOTA performance on the downstream tasks. In the MTL setting, an instruction tuned model trained on only 6% of downstream training data achieve SOTA, while using 100% of the training data results in a 3.69% points improvement (ROUGE-L 74.68) over the previous SOTA. We conduct an analysis on T5 vs Tk-Instruct by developing several baselines to demonstrate that instruction tuning aids in increasing both sample efficiency and transfer learning. Additionally, we observe a consistent ~4% performance increase in both settings when pre-finetuning is performed with instructions. Finally, we conduct a categorical study and find that contrary to previous results, tasks in the question rewriting and title generation categories suffer from instruction tuning.

Neeraj Varshney, Himanshu Gupta, Eric Robertson et al.

State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel' instances that do not belong to any known class are often observed. This renders the ability to deal with novelties crucial. To initiate a systematic research in this important area of 'dealing with novelties', we introduce 'NoveltyTask', a multi-stage task to evaluate a system's performance on pipelined novelty 'detection' and 'accommodation' tasks. We provide mathematical formulation of NoveltyTask and instantiate it with the authorship attribution task that pertains to identifying the correct author of a given text. We use Amazon reviews corpus and compile a large dataset (consisting of 250k instances across 200 authors/labels) for NoveltyTask. We conduct comprehensive experiments and explore several baseline methods for the task. Our results show that the methods achieve considerably low performance making the task challenging and leaving sufficient room for improvement. Finally, we believe our work will encourage research in this underexplored area of dealing with novelties, an important step en route to developing robust systems.

Tyrone Machado, David Fassbender, Abdolreza Taheri et al.

Heavy-duty mobile machines (HDMMs) are a wide range of machinery used in diverse and critical application areas which are currently facing several issues like skilled labor shortage, poor safety records, and harsh work environments. Consequently, efforts are underway to increase automation in HDMMs for increased productivity and safety, eventually transitioning to operator-less autonomous HDMMs to address skilled labor shortages. However, HDMM are complex machines requiring continuous physical and cognitive inputs from human-operators. Thus, developing autonomous HDMM is a huge challenge, with current research and developments being performed in several independent research domains. Through this study, we use the bounded rationality concept to propose multidisciplinary collaborations for new autonomous HDMMs and apply the transaction cost economics framework to suggest future implications in the HDMM industry. Furthermore, we introduce a conceptual understanding of collaborations in the autonomous HDMM as a unified approach, while highlighting the practical implications and challenges of the complex nature of such multidisciplinary collaborations. The collaborative challenges and potentials are mapped out between the following topics: mechanical systems, AI methods, software systems, sensors, connectivity, simulations and process optimization, business cases, organization theories, and finally, regulatory frameworks.

Himanshu Gupta, Shreyas Verma, Santosh Mashetty et al.

Named Entity Recognition (NER) has seen significant progress in recent years, with numerous state-of-the-art (SOTA) models achieving high performance. However, very few studies have focused on the generation of entities' context. In this paper, we introduce CONTEXT-NER, a task that aims to generate the relevant context for entities in a sentence, where the context is a phrase describing the entity but not necessarily present in the sentence. To facilitate research in this task, we also present the EDGAR10-Q dataset, which consists of annual and quarterly reports from the top 1500 publicly traded companies. The dataset is the largest of its kind, containing 1M sentences, 2.8M entities, and an average of 35 tokens per sentence, making it a challenging dataset. We propose a baseline approach that combines a phrase generation algorithm with inferencing using a 220M language model, achieving a ROUGE-L score of 27% on the test split. Additionally, we perform a one-shot inference with ChatGPT, which obtains a 30% ROUGE-L, highlighting the difficulty of the dataset. We also evaluate models such as T5 and BART, which achieve a maximum ROUGE-L of 49% after supervised finetuning on EDGAR10-Q. We also find that T5-large, when pre-finetuned on EDGAR10-Q, achieve SOTA results on downstream finance tasks such as Headline, FPB, and FiQA SA, outperforming vanilla version by 10.81 points. To our surprise, this 66x smaller pre-finetuned model also surpasses the finance-specific LLM BloombergGPT-50B by 15 points. We hope that our dataset and generated artifacts will encourage further research in this direction, leading to the development of more sophisticated language models for financial text analysis

Himanshu Gupta, Tanmay G. Kulkarni, Lov Kumar et al.

Code Smell, similar to a bad smell, is a surface indication of something tainted but in terms of software writing practices. This metric is an indication of a deeper problem lies within the code and is associated with an issue which is prominent to experienced software developers with acceptable coding practices. Recent studies have often observed that codes having code smells are often prone to a higher probability of change in the software development cycle. In this paper, we developed code smell prediction models with the help of features extracted from source code to predict eight types of code smell. Our work also presents the application of data sampling techniques to handle class imbalance problem and feature selection techniques to find relevant feature sets. Previous studies had made use of techniques such as Naive - Bayes and Random forest but had not explored deep learning methods to predict code smell. A total of 576 distinct Deep Learning models were trained using the features and datasets mentioned above. The study concluded that the deep learning models which used data from Synthetic Minority Oversampling Technique gave better results in terms of accuracy, AUC with the accuracy of some models improving from 88.47 to 96.84.

Himanshu Gupta, Abhiram Anand Gulanikar, Lov Kumar et al.

A code smell is a surface indicator of an inherent problem in the system, most often due to deviation from standard coding practices on the developers part during the development phase. Studies observe that code smells made the code more susceptible to call for modifications and corrections than code that did not contain code smells. Restructuring the code at the early stage of development saves the exponentially increasing amount of effort it would require to address the issues stemming from the presence of these code smells. Instead of using traditional features to detect code smells, we use user comments to manually construct features to predict code smells. We use three Extreme learning machine kernels over 629 packages to identify eight code smells by leveraging feature engineering aspects and using sampling techniques. Our findings indicate that the radial basis functional kernel performs best out of the three kernel methods with a mean accuracy of 98.52.

Adeniyi Jide Kehinde, Abidemi Emmanuel Adeniyi, Roseline Oluwaseun Ogundokun et al.

Many researchers have studied student academic performance in supervised and unsupervised learning using numerous data mining techniques. Neural networks often need a greater collection of observations to achieve enough predictive ability. Due to the increase in the rate of poor graduates, it is necessary to design a system that helps to reduce this menace as well as reduce the incidence of students having to repeat due to poor performance or having to drop out of school altogether in the middle of the pursuit of their career. It is therefore necessary to study each one as well as their advantages and disadvantages, so as to determine which is more efficient in and in what case one should be preferred over the other. The study aims to develop a system to predict student performance with Artificial Neutral Network using the student demographic traits so as to assist the university in selecting candidates (students) with a high prediction of success for admission using previous academic records of students granted admissions which will eventually lead to quality graduates of the institution. The model was developed based on certain selected variables as the input. It achieved an accuracy of over 92.3 percent, showing Artificial Neural Network potential effectiveness as a predictive tool and a selection criterion for candidates seeking admission to a university.

Pradyumna Gupta, Himanshu Gupta, Aman Sinha

Memes have become an ubiquitous social media entity and the processing and analysis of suchmultimodal data is currently an active area of research. This paper presents our work on theMemotion Analysis shared task of SemEval 2020, which involves the sentiment and humoranalysis of memes. We propose a system which uses different bimodal fusion techniques toleverage the inter-modal dependency for sentiment and humor classification tasks. Out of all ourexperiments, the best system improved the baseline with macro F1 scores of 0.357 on SentimentClassification (Task A), 0.510 on Humor Classification (Task B) and 0.312 on Scales of SemanticClasses (Task C).

Himanshu Gupta, Dharanipragada Janakiram

Blockchain is maintained as a global log between a network of nodes and uses cryptographic distributed protocols to synchronize the updates. As adopted by Bitcoin and Ethereum these update operations to the ledger are serialized, and executed in batches. To safeguard the system against the generation of conflicting sets of updates and maintain the consistency of the ledger, the frequency of the updates is controlled, which severely affects the performance of the system. This paper presents Converging Directed Acyclic Graph (CDAG), as a substitute for the chain and DAG structures used in other blockchain protocols. CDAG allows multiple parallel updates to the ledger and converges them at the next step providing finality to the blocks. It partitions the updates into non-intersecting buckets of transactions to prevent the generation of conflicting blocks and divide the time into slots to provide enough time for them to propagate in the network. Multiple simultaneous updates improve the throughput of CDAG, and the converging step helps to finalize them faster, even in the presence of conflicts. Moreover, CDAG provides a total order among the blocks of the ledger to support smart contracts, unlike some of the other blockDAG protocols. We evaluate the performance of CDAG on Google Cloud Platform using Google Kubernetes Engine, simulating a real-time network. Experimental results show that CDAG achieves a throughput of more than 2000 transactions per second and confirms them well in under 2 minutes. Also, the protocol scales well in comparison to other permissioned protocols, and the capacity of the network only limits the performance.