Shubham Agarwal

Alessandro Suglia, José Lopes, Emanuele Bastianelli et al.

Recent video+language datasets cover domains where the interaction is highly structured, such as instructional videos, or where the interaction is scripted, such as TV shows. Both of these properties can lead to spurious cues to be exploited by models rather than learning to ground language. In this paper, we present GrOunded footbAlL commentaries (GOAL), a novel dataset of football (or `soccer') highlights videos with transcribed live commentaries in English. As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding. We also provide state-of-the-art baselines for the following tasks: frame reordering, moment retrieval, live commentary retrieval and play-by-play live commentary generation. Results show that SOTA models perform reasonably well in most tasks. We discuss the implications of these results and suggest new tasks for which GOAL can be used. Our codebase is available at: https://gitlab.com/grounded-sport-convai/goal-baselines.

Shu Liu, Shubham Agarwal, Monishwaran Maheswaran et al.

Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains. In this paradigm, previously evaluated solutions are reused to guide the model toward new candidate solutions. Crucially, the effectiveness of this evolution process depends on the search strategy: how prior solutions are selected and varied to generate new candidates. However, most existing methods rely on fixed search strategies with predefined knobs (e.g., explore-exploit ratios) that remain static throughout execution. While effective in some settings, these approaches often fail to adapt across tasks, or even within the same task as the search space changes over time. We introduce EvoX, an adaptive evolution method that optimizes its own evolution process. EvoX jointly evolves candidate solutions and the search strategies used to generate them, continuously updating how prior solutions are selected and varied based on progress. This enables the system to dynamically shift between different search strategies during the optimization process. Across nearly 200 real-world optimization tasks, EvoX outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.

Swetha Eppalapally, Daksh Dangi, Chaithra Bhat et al.

Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs). However, accurately assessing the performance of these applications remains a challenge, mainly due to the lack of suitable benchmarks that effectively simulate real-world scenarios. To address this challenge, we introduce two product question-answering (QA) datasets focused on Adobe Acrobat and Photoshop products to help evaluate the performance of existing models on domain-specific product QA tasks. Additionally, we propose a novel knowledge-driven RAG-QA framework to enhance the performance of the models in the product QA task. Our experiments demonstrated that inducing domain knowledge through query reformulation allowed for increased retrieval and generative performance when compared to standard RAG-QA methods. This improvement, however, is slight, and thus illustrates the challenge posed by the datasets introduced.

Shubham Agarwal, Ofek Nourian, Michael Sidorov et al.

Understanding plant root systems is critical for advancing research in soil-plant interactions, nutrient uptake, and overall plant health. However, accurate imaging of roots in subterranean environments remains a persistent challenge due to adverse conditions such as occlusion, varying soil moisture, and inherently low contrast, which limit the effectiveness of conventional vision-based approaches. In this work, we propose a novel underground imaging system that captures multiple overlapping views of plant roots and integrates a deep learning-based Multi-Image Super Resolution (MISR) framework designed to enhance root visibility and detail. To train and evaluate our approach, we construct a synthetic dataset that simulates realistic underground imaging scenarios, incorporating key environmental factors that affect image quality. Our proposed MISR algorithm leverages spatial redundancy across views to reconstruct high-resolution images with improved structural fidelity and visual clarity. Quantitative evaluations show that our approach outperforms state-of-the-art super resolution baselines, achieving a 2.3 percent reduction in BRISQUE, indicating improved image quality with the same CLIP-IQA score, thereby enabling enhanced phenotypic analysis of root systems. This, in turn, facilitates accurate estimation of critical root traits, including root hair count and root hair density. The proposed framework presents a promising direction for robust automatic underground plant root imaging and trait quantification for agricultural and ecological research.

Eden Ship, Eitan Spivak, Shubham Agarwal et al.

Accurate classification of weather conditions in images is essential for enhancing the performance of object detection and classification models under varying weather conditions. This paper presents a comprehensive study on classifying weather conditions in images into four categories: rainy, low light, haze, and clear. The motivation for this work stems from the need to improve the reliability and efficiency of automated systems, such as autonomous vehicles and surveillance, which must operate under diverse weather conditions. Misclassification of weather conditions can lead to significant performance degradation in these systems, making robust weather classification crucial. Utilizing the Support Vector Machine (SVM) algorithm, our approach leverages a robust set of features, including brightness, saturation, noise level, blur metric, edge strength, motion blur, Local Binary Patterns (LBP) mean and variance for radii 1, 2, and 3, edges mean and variance, and color histogram mean and variance for blue, green, and red channels. Our SVM-based method achieved a notable accuracy of 92.8%, surpassing typical benchmarks in the literature, which range from 80% to 90% for classical machine learning methods. While deep learning methods can achieve up to 94% accuracy, our approach offers a competitive advantage in terms of computational efficiency and real-time classification capabilities. Detailed analysis of each feature's contribution highlights the effectiveness of texture, color, and edge-related features in capturing the unique characteristics of different weather conditions. This research advances the state-of-the-art in weather image classification and provides insights into the critical features necessary for accurate weather condition differentiation, underscoring the potential of SVMs in practical applications where accuracy is paramount.

Shubham Agarwal, Alexander Krentsel, Shu Liu et al.

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized formal verification can guarantee such correctness, but typically demands months to years of expert effort. As evidence, even SOTA coding agents (Codex with GPT-5.4 and Claude Code with Opus 4.6) succeed on only 2/7 distributed key-value-store specifications. In this paper, we present the first effective approach to addressing this gap, Inductive Deductive Synthesis (IDS), which jointly and incrementally synthesizes implementation and proof, and learns from failed attempts to systematically try promising strategies. Built as an agentic LLM system, IDS achieves 7/7 in about 6.8 hours and $106 per spec on average, roughly 200x faster than expert effort and 17% cheaper than SOTA agents. IDS further incorporates performance feedback into the same loop, yielding implementations up to 3x faster than published verified systems.

Shu Liu, Alexander Krentsel, Shubham Agarwal et al.

Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a different approach tractable: Just-in-Time Systems, in which the entire system is synthesized from scratch, specialized to the environment, workload, and required system properties. We present a JIT system synthesis pipeline, Jitskit, and explore its effectiveness in synthesizing key-value stores from spec cards that span different YCSB workloads, deployment constraints (e.g., compute resources), and system properties (e.g., consistency and durability). Jitskit iteratively refines a system implementation to match the specification against an evolving evaluation test suite. The resulting synthesized systems are performant, beating comparable state-of-the-art systems on 18 of 18 specs tried, by up to 4.6x over the best off-the-shelf baseline on the most favorable spec. Naively running Claude Code either reward-hacks or underperforms Jitskit by up to 5.4x. We discuss the challenges we overcame in building Jitskit and our key takeaways.

Shubham Agarwal, Thomas Searle, Mart Ratas et al.

Electronic Health Records are large repositories of valuable clinical data, with a significant portion stored in unstructured text format. This textual data includes clinical events (e.g., disorders, symptoms, findings, medications and procedures) in context that if extracted accurately at scale can unlock valuable downstream applications such as disease prediction. Using an existing Named Entity Recognition and Linking methodology, MedCAT, these identified concepts need to be further classified (contextualised) for their relevance to the patient, and their temporal and negated status for example, to be useful downstream. This study performs a comparative analysis of various natural language models for medical text classification. Extensive experimentation reveals the effectiveness of transformer-based language models, particularly BERT. When combined with class imbalance mitigation techniques, BERT outperforms Bi-LSTM models by up to 28% and the baseline BERT model by up to 16% for recall of the minority classes. The method has been implemented as part of CogStack/MedCAT framework and made available to the community for further research.

Suranjan Goswami, Abhinav Ravi, Raja Kolla et al.

Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real world settings. Accurate rotation correction is essential for enhancing the performance of downstream tasks such as Optical Character Recognition (OCR) where misalignment commonly arises due to user errors, particularly incorrect base orientations of the camera during capture. In this study, we first introduce OCR-Rotation-Bench (ORB), a new benchmark for evaluating OCR robustness to image rotations, comprising (i) ORB-En, built from rotation-transformed structured and free-form English OCR datasets, and (ii) ORB-Indic, a novel multilingual set spanning 11 Indic mid to low-resource languages. We also present a fast, robust and lightweight rotation classification pipeline built on the vision encoder of Phi-3.5-Vision model with dynamic image cropping, fine-tuned specifically for 4-class rotation task in a standalone fashion. Our method achieves near-perfect 96% and 92% accuracy on identifying the rotations respectively on both the datasets. Beyond classification, we demonstrate the critical role of our module in boosting OCR performance: closed-source (up to 14%) and open-weights models (up to 4x) in the simulated real-world setting.

Abhishek Mukhopadhyay, Shubham Agarwal, Patrick Dylan Zwick et al.

With the increasing prevalence of video recordings there is a growing need for tools that can maintain the privacy of those recorded. In this paper, we define an approach for redacting personally identifiable text from videos using a combination of optical character recognition (OCR) and natural language processing (NLP) techniques. We examine the relative performance of this approach when used with different OCR models, specifically Tesseract and the OCR system from Google Cloud Vision (GCV). For the proposed approach the performance of GCV, in both accuracy and speed, is significantly higher than Tesseract. Finally, we explore the advantages and disadvantages of both models in real-world applications.

Shubham Agarwal, Sarthak Chakraborty, Shaddy Garg et al.

Cloud services are omnipresent and critical cloud service failure is a fact of life. In order to retain customers and prevent revenue loss, it is important to provide high reliability guarantees for these services. One way to do this is by predicting outages in advance, which can help in reducing the severity as well as time to recovery. It is difficult to forecast critical failures due to the rarity of these events. Moreover, critical failures are ill-defined in terms of observable data. Our proposed method, Outage-Watch, defines critical service outages as deteriorations in the Quality of Service (QoS) captured by a set of metrics. Outage-Watch detects such outages in advance by using current system state to predict whether the QoS metrics will cross a threshold and initiate an extreme event. A mixture of Gaussian is used to model the distribution of the QoS metrics for flexibility and an extreme event regularizer helps in improving learning in tail of the distribution. An outage is predicted if the probability of any one of the QoS metrics crossing threshold changes significantly. Our evaluation on a real-world SaaS company dataset shows that Outage-Watch significantly outperforms traditional methods with an average AUC of 0.98. Additionally, Outage-Watch detects all the outages exhibiting a change in service metrics and reduces the Mean Time To Detection (MTTD) of outages by up to 88% when deployed in an enterprise cloud-service system, demonstrating efficacy of our proposed method.

Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi et al. · mila

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

Shubham Agarwal, Asim Biswal, Sepanta Zeighami et al.

Natural language to SQL (NL2SQL) translation enables non-expert users to query relational databases through natural language. Recently, NL2SQL agents, powered by the reasoning capabilities of Large Language Models (LLMs), have significantly advanced NL2SQL translation. Nonetheless, NL2SQL agents still make mistakes when faced with large-scale real-world databases because they lack knowledge of how to correctly leverage the underlying data (e.g., knowledge about the intent of each column) and form misconceptions about the data when querying it, leading to errors. Prior work has studied generating facts about the database to provide more context to NL2SQL agents, but such approaches simply restate database contents without addressing the agent's misconceptions. In this paper, we propose Tk-Boost, a bolt-on framework for augmenting any NL2SQL agent with tribal knowledge: knowledge that corrects the agent's misconceptions in querying the database accumulated through experience using the database. To accumulate experience, Tk-Boost first asks the NL2SQL agent to answer a few queries on the database, identifies the agent's misconceptions by analyzing its mistakes on the database, and generates tribal knowledge to address them. To enable accurate retrieval, Tk-Boost indexes this knowledge with applicability conditions that specify the query features for which the knowledge is useful. When answering new queries, Tk-Boost uses this knowledge to provide feedback to the NL2SQL agent, resolving the agent's misconceptions during SQL generation, and thus improving the agent's accuracy. Extensive experiments across the BIRD and Spider 2.0 benchmarks with various NL2SQL agents shows Tk-Boost improves NL2SQL agents accuracy by up to 16.9% on Spider 2.0 and 13.7% on BIRD

Shubham Agarwal, Raz Birman, Ofer Hadar

This paper introduces WARLearn, a novel framework designed for adaptive representation learning in challenging and adversarial weather conditions. Leveraging the in-variance principal used in Barlow Twins, we demonstrate the capability to port the existing models initially trained on clear weather data to effectively handle adverse weather conditions. With minimal additional training, our method exhibits remarkable performance gains in scenarios characterized by fog and low-light conditions. This adaptive framework extends its applicability beyond adverse weather settings, offering a versatile solution for domains exhibiting variations in data distributions. Furthermore, WARLearn is invaluable in scenarios where data distributions undergo significant shifts over time, enabling models to remain updated and accurate. Our experimental findings reveal a remarkable performance, with a mean average precision (mAP) of 52.6% on unseen real-world foggy dataset (RTTS). Similarly, in low light conditions, our framework achieves a mAP of 55.7% on unseen real-world low light dataset (ExDark). Notably, WARLearn surpasses the performance of state-of-the-art frameworks including FeatEnHancer, Image Adaptive YOLO, DENet, C2PNet, PairLIE and ZeroDCE, by a substantial margin in adverse weather, improving the baseline performance in both foggy and low light conditions. The WARLearn code is available at https://github.com/ShubhamAgarwal12/WARLearn

Shubham Agarwal, Subrata Mitra, Saud Iqbal

Text-to-image (T2I) models have gained significant popularity. Most of these are diffusion models with unique computational characteristics, distinct from both traditional small-scale ML models and large language models. They are highly compute-bound and use an iterative denoising process to generate images, leading to very high inference time. This creates significant challenges in designing a high-throughput system. We discovered that a large fraction of prompts can be served using faster, approximated models. However, the approximation setting must be carefully calibrated for each prompt to avoid quality degradation. Designing a high-throughput system that assigns each prompt to the appropriate model and compatible approximation setting remains a challenging problem. We present Argus, a high-throughput T2I inference system that selects the right level of approximation for each prompt to maintain quality while meeting throughput targets on a fixed-size cluster. Argus intelligently switches between different approximation strategies to satisfy both throughput and quality requirements. Overall, Argus achieves 10x fewer latency service-level objective (SLO) violations, 10% higher average quality, and 40% higher throughput compared to baselines on two real-world workload traces.

Audrey Cheng, Shu Liu, Melissa Pan et al.

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.

Neel Prabhanjan Rachamalla, Aravind Konakalla, Gautam Rajeev et al.

The effectiveness of Large Language Models (LLMs) depends heavily on the availability of high-quality post-training data, particularly instruction-tuning and preference-based examples. Existing open-source datasets, however, often lack multilingual coverage, cultural grounding, and suffer from task diversity gaps that are especially pronounced for Indian languages. We introduce a human-in-the-loop pipeline that combines translations with synthetic expansion to produce reliable and diverse Indic post-training data. Using this pipeline, we curate two datasets: Pragyaan-IT (22.5K) and Pragyaan-Align (100K) across 10 Indian languages covering 13 broad and 56 sub-categories, leveraging 57 diverse datasets. Our dataset protocol incorporates several often-overlooked dimensions and emphasize task diversity, multi-turn dialogue, instruction fidelity, safety alignment, and preservation of cultural nuance, providing a foundation for more inclusive and effective multilingual LLMs.

Guduru Manoj, Neel Prabhanjan Rachamalla, Ashish Kulkarni et al.

In the context of pretraining of Large Language Models (LLMs), synthetic data has emerged as an alternative for generating high-quality pretraining data at scale. This is particularly beneficial in low-resource language settings where the benefits of recent LLMs have been unevenly distributed across languages. In this work, we present a systematic study on the generation and evaluation of synthetic multilingual pretraining data for Indic languages, where we construct a large-scale synthetic dataset BhashaKritika, comprising 540B tokens using 5 different techniques for 10 languages. We explore the impact of grounding generation in documents, personas, and topics. We analyze how language choice, both in the prompt instructions and document grounding, affects data quality, and we compare translations of English content with native generation in Indic languages. To support scalable and language-sensitive evaluation, we introduce a modular quality evaluation pipeline that integrates script and language detection, metadata consistency checks, n-gram repetition analysis, and perplexity-based filtering using KenLM models. Our framework enables robust quality control across diverse scripts and linguistic contexts. Empirical results through model runs reveal key trade-offs in generation strategies and highlight best practices for constructing effective multilingual corpora.

Shaharukh Khan, Ali Faraz, Abhinav Ravi et al.

Multimodal research has predominantly focused on single-image reasoning, with limited exploration of multi-image scenarios. Recent models have sought to enhance multi-image understanding through large-scale pretraining on interleaved image-text datasets. However, most Vision-Language Models (VLMs) are trained primarily on English datasets, leading to inadequate representation of Indian languages. To address this gap, we introduce the Chitrakshara dataset series, covering 11 Indian languages sourced from Common Crawl. It comprises (1) Chitrakshara-IL, a large-scale interleaved pretraining dataset with 193M images, 30B text tokens, and 50M multilingual documents, and (2) Chitrakshara-Cap, which includes 44M image-text pairs with 733M tokens. This paper details the data collection pipeline, including curation, filtering, and processing methodologies. Additionally, we present a comprehensive quality and diversity analysis to assess the dataset's representativeness across Indic languages and its potential for developing more culturally inclusive VLMs.

Shubham Agarwal, Gaurav Sahu, Abhay Puri et al.

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-factual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our project page including the demo and toolkit can be accessed here: https://litllm.github.io

Ali Faraz, Akash, Shaharukh Khan et al.

Vision-language models (VLMs) have demonstrated impressive generalization across multimodal tasks, yet most evaluation benchmarks remain Western-centric, leaving open questions about their performance in culturally diverse and multilingual settings. To address this gap, we introduce IndicVisionBench, the first large-scale benchmark centered on the Indian subcontinent. Covering English and 10 Indian languages, our benchmark spans 3 multimodal tasks, including Optical Character Recognition (OCR), Multimodal Machine Translation (MMT), and Visual Question Answering (VQA), covering 6 kinds of question types. Our final benchmark consists of a total of ~5K images and 37K+ QA pairs across 13 culturally grounded topics. In addition, we release a paired parallel corpus of annotations across 10 Indic languages, creating a unique resource for analyzing cultural and linguistic biases in VLMs. We evaluate a broad spectrum of 8 models, from proprietary closed-source systems to open-weights medium and large-scale models. Our experiments reveal substantial performance gaps, underscoring the limitations of current VLMs in culturally diverse contexts. By centering cultural diversity and multilinguality, IndicVisionBench establishes a reproducible evaluation framework that paves the way for more inclusive multimodal research.

Souvik Rana, Arul Menezes, Ashish Kulkarni et al.

Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse scripts and rich morphological variation. While subword methods such as Byte Pair Encoding (BPE) are widely adopted, their effectiveness in multilingual settings remains underexplored. We present IndicSuperTokenizer, a tokenizer for Indic multilingual LLMs, that combines both subword and multi-word tokenization, along with language-specific pre-tokenization, leading to more linguistically aligned tokens and achieving a new state-of-the-art in fertility score. Evaluated across English, 22 Indian languages and code data, our tokenizer improves the average fertility score by 39.5% over LLaMA4 and by 18% over Sutra (the current best). This translates to 44% improvement in inference throughput over LLaMA4 while maintaining comparable performance on English and Indic benchmarks. We also present detailed ablations across tokenizer training data size, vocabulary size, merging techniques, and pre-tokenization strategies, demonstrating the robustness of our design choices.

Juan A. Rodriguez, Abhay Puri, Shubham Agarwal et al. · mila

Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space, leveraging visual understanding to apply accurate SVG primitives. To train StarVector, we create SVG-Stack, a diverse dataset of 2M samples that enables generalization across vectorization tasks and precise use of primitives like ellipses, polygons, and text. We address challenges in SVG evaluation, showing that pixel-based metrics like MSE fail to capture the unique qualities of vector graphics. We introduce SVG-Bench, a benchmark across 10 datasets, and 3 tasks: Image-to-SVG, Text-to-SVG generation, and diagram generation. Using this setup, StarVector achieves state-of-the-art performance, producing more compact and semantically rich SVGs.

Ali Faraz, Raja Kolla, Ashish Kulkarni et al.

Designing Optical Character Recognition (OCR) systems for India requires balancing linguistic diversity, document heterogeneity, and deployment constraints. In this paper, we study two training strategies for building multilingual OCR systems with Vision-Language Models through the Chitrapathak series. We first follow a popular multimodal approach, pairing a generic vision encoder with a strong multilingual language model and training the system end-to-end for OCR. Alternatively, we explore fine-tuning an existing OCR model, despite not being trained for the target languages. Through extensive evaluation on multilingual Indic OCR benchmarks and deployment-oriented metrics, we find that the second strategy consistently achieves better accuracy-latency trade-offs. Chitrapathak-2 achieves 3-6x speedup over its predecessor with being state-of-the-art (SOTA) in Telugu (6.69 char ANLS) and second best in the rest. In addition, we present Parichay, an independent OCR model series designed specifically for 9 Indian government documents to extract structured key fields, achieving 89.8% Exact Match score with a faster inference. Together, these systems achieve SOTA performance and provide practical guidance for building production-scale OCR pipelines in the Indian context.

Shubham Agarwal, Sai Sundaresan, Subrata Mitra et al.

Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retriever extracts chunks of relevant text from a knowledge base. These chunks are sent to an LLM as part of the input prompt. Typically, any given chunk is repeatedly retrieved across user questions. However, currently, for every question, attention-layers in LLMs fully compute the key values (KVs) repeatedly for the input chunks, as state-of-the-art methods cannot reuse KV-caches when chunks appear at arbitrary locations with arbitrary contexts. Naive reuse leads to output quality degradation. This leads to potentially redundant computations on expensive GPUs and increases latency. In this work, we propose Cache-Craft, a system for managing and reusing precomputed KVs corresponding to the text chunks (we call chunk-caches) in RAG-based systems. We present how to identify chunk-caches that are reusable, how to efficiently perform a small fraction of recomputation to fix the cache to maintain output quality, and how to efficiently store and evict chunk-caches in the hardware for maximizing reuse while masking any overheads. With real production workloads as well as synthetic datasets, we show that Cache-Craft reduces redundant computation by 51% over SOTA prefix-caching and 75% over full recomputation. Additionally, with continuous batching on a real production workload, we get a 1.6X speed up in throughput and a 2X reduction in end-to-end response latency over prefix-caching while maintaining quality, for both the LLaMA-3-8B and LLaMA-3-70B models.

Shubham Agarwal, Gaurav Sahu, Abhay Puri et al.

Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, especially due to the recent influx of research papers. This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract. We decompose the task into two components: 1. Retrieving related works given a query abstract, and 2. Writing a literature review based on the retrieved results. We analyze how effective LLMs are for both components. For retrieval, we introduce a novel two-step search strategy that first uses an LLM to extract meaningful keywords from the abstract of a paper and then retrieves potentially relevant papers by querying an external knowledge base. Additionally, we study a prompting-based re-ranking mechanism with attribution and show that re-ranking doubles the normalized recall compared to naive search methods, while providing insights into the LLM's decision-making process. In the generation phase, we propose a two-step approach that first outlines a plan for the review and then executes steps in the plan to generate the actual review. To evaluate different LLM-based literature review methods, we create test sets from arXiv papers using a protocol designed for rolling use with newly released LLMs to avoid test set contamination in zero-shot evaluations. We release this evaluation protocol to promote additional research and development in this regard. Our empirical results suggest that LLMs show promising potential for writing literature reviews when the task is decomposed into smaller components of retrieval and planning. Our project page including a demonstration system and toolkit can be accessed here: https://litllm.github.io.

Shaharukh Khan, Ayush Tarun, Abhinav Ravi et al.

Recent multimodal foundation models are primarily trained on English or high resource European language data, which hinders their applicability to other medium and low-resource languages. To address this limitation, we introduce Chitrarth (Chitra: Image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Furthermore, we also introduce BharatBench, a comprehensive framework for evaluating VLMs across various Indian languages, ultimately contributing to more diverse and effective AI systems. Our model achieves SOTA results for benchmarks across low resource languages while retaining its efficiency in English. Through our research, we aim to set new benchmarks in multilingual-multimodal capabilities, offering substantial improvements over existing models and establishing a foundation to facilitate future advancements in this arena.

Shaharukh Khan, Ayush Tarun, Ali Faraz et al.

In this work, we provide the system description of our submission as part of the English to Lowres Multimodal Translation Task at the Workshop on Asian Translation (WAT2024). We introduce Chitranuvad, a multimodal model that effectively integrates Multilingual LLM and a vision module for Multimodal Translation. Our method uses a ViT image encoder to extract visual representations as visual token embeddings which are projected to the LLM space by an adapter layer and generates translation in an autoregressive fashion. We participated in all the three tracks (Image Captioning, Text only and Multimodal translation tasks) for Indic languages (ie. English translation to Hindi, Bengali and Malyalam) and achieved SOTA results for Hindi in all of them on the Challenge set while remaining competitive for the other languages in the shared task.

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.

Shubham Agarwal, Subrata Mitra, Sarthak Chakraborty et al.

Text-to-image generation using diffusion models has seen explosive popularity owing to their ability in producing high quality images adhering to text prompts. However, production-grade diffusion model serving is a resource intensive task that not only require high-end GPUs which are expensive but also incurs considerable latency. In this paper, we introduce a technique called approximate-caching that can reduce such iterative denoising steps for an image generation based on a prompt by reusing intermediate noise states created during a prior image generation for similar prompts. Based on this idea, we present an end to end text-to-image system, Nirvana, that uses the approximate-caching with a novel cache management-policy Least Computationally Beneficial and Frequently Used (LCBFU) to provide % GPU compute savings, 19.8% end-to-end latency reduction and 19% dollar savings, on average, on two real production workloads. We further present an extensive characterization of real production text-to-image prompts from the perspective of caching, popularity and reuse of intermediate states in a large production environment.

Shu Liu, Soujanya Ponnapalli, Shreya Shankar et al.

Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores.

Shubham Agarwal, Saud Iqbal, Subrata Mitra

Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to their sensitivity to input prompts and performance degradation caused by large model loading overheads. This work introduces a novel text-to-image inference system that optimally matches prompts across multiple instances of the same model operating at various approximation levels to deliver high-quality images under high loads and fixed budgets.

Ghazi Shazan Ahmad, Shubham Agarwal, Subrata Mitra et al.

Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number of statistics from the datasets and then use machine-learning models to score or classify multiple visualizations choices to recommend the most effective ones, as per the statistics. However, state-of-the art models rely on very large number of expensive statistics and therefore using such models on large datasets become infeasible due to prohibitively large computational time, limiting the effectiveness of such techniques to most real world complex and large datasets. In this paper, we propose a novel reinforcement-learning (RL) based framework that takes a given vis-rec model and a time-budget from the user and identifies the best set of input statistics that would be most effective while generating the visual insights within a given time budget, using the given model. Using two state-of-the-art vis-rec models applied on three large real-world datasets, we show the effectiveness of our technique in significantly reducing time-to visualize with very small amount of introduced error. Our approach is about 10X times faster compared to the baseline approaches that introduce similar amounts of error.

Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena et al.

Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive applications. Existing acceleration methods, like distillation, truncation, or consistency training, either degrade quality, incur costly retraining, or lack generalization. We propose FlowCast, a training-free speculative generation framework that accelerates inference by exploiting the fact that FM models are trained to preserve constant velocity. FlowCast speculates future velocity by extrapolating current velocity without incurring additional time cost, and accepts it if it is within a mean-squared error threshold. This constant-velocity forecasting allows redundant steps in stable regions to be aggressively skipped while retaining precision in complex ones. FlowCast is a plug-and-play framework that integrates seamlessly with any FM model and requires no auxiliary networks. We also present a theoretical analysis and bound the worst-case deviation between speculative and full FM trajectories. Empirical evaluations demonstrate that FlowCast achieves $>2.5\times$ speedup in image generation, video generation, and editing tasks, outperforming existing baselines with no quality loss as compared to standard full generation.

Dhruv Jain, Harshit Shukla, Gautam Rajeev et al.

Large-scale Speech Language Models (SpeechLMs) have enabled voice assistants capable of understanding natural spoken queries and performing complex tasks. However, existing speech benchmarks primarily focus on isolated capabilities such as transcription, or question-answering, and do not systematically evaluate agentic scenarios encompassing multilingual and cultural understanding, as well as adversarial robustness. To address this, we introduce VoiceAgentBench, a comprehensive benchmark designed to evaluate SpeechLMs in realistic spoken agentic settings. It comprises over 5,500 synthetic spoken queries, including dialogues grounded in Indian context, covering single-tool invocations, multi-tool workflows, multi-turn interactions, and safety evaluations. The benchmark supports English, Hindi, and 5 other Indian languages, reflecting real-world linguistic and cultural diversity. We simulate speaker variability using a novel sampling algorithm that selects audios for TTS voice conversion based on its speaker embeddings, maximizing acoustic and speaker diversity. Our evaluation measures tool selection accuracy, structural consistency, and the correctness of tool invocations, including adversarial robustness. Our experiments reveal significant gaps in contextual tool orchestration tasks, Indic generalization, and adversarial robustness, exposing critical limitations of current SpeechLMs.

Aadarsh Anantha Ramakrishnan, Shubham Agarwal, Selvanayagam S et al.

As image generation models grow increasingly powerful and accessible, concerns around authenticity, ownership, and misuse of synthetic media have become critical. The ability to generate lifelike images indistinguishable from real ones introduces risks such as misinformation, deepfakes, and intellectual property violations. Traditional watermarking methods either degrade image quality, are easily removed, or require access to confidential model internals - making them unsuitable for secure and scalable deployment. We are the first to introduce ZK-WAGON, a novel system for watermarking image generation models using the Zero-Knowledge Succinct Non Interactive Argument of Knowledge (ZK-SNARKs). Our approach enables verifiable proof of origin without exposing model weights, generation prompts, or any sensitive internal information. We propose Selective Layer ZK-Circuit Creation (SL-ZKCC), a method to selectively convert key layers of an image generation model into a circuit, reducing proof generation time significantly. Generated ZK-SNARK proofs are imperceptibly embedded into a generated image via Least Significant Bit (LSB) steganography. We demonstrate this system on both GAN and Diffusion models, providing a secure, model-agnostic pipeline for trustworthy AI image generation.

Debabrata Mahapatra, Shubham Agarwal, Apoorv Saxena et al.

Prior work on input-token importance in auto-regressive transformers has relied on Softmax-normalized attention weights, which obscure the richer structure of pre-Softmax query-key logits. We introduce RCStat, a statistical framework that harnesses raw attention logits via Relative Contextualization (RC), a random variable measuring contextual alignment between token segments, and derive an efficient upper bound for RC. We demonstrate two applications: (i) Key-Value compression, where RC-based thresholds drive adaptive key-value eviction for substantial cache reduction with minimal quality loss; and (ii) Attribution, where RC yields higher-fidelity token-, sentence-, and chunk-level explanations than post-Softmax methods. Across question answering, summarization, and attribution benchmarks, RCStat achieves significant empirical gains, delivering state-of-the-art compression and attribution performance without any model retraining.

Shubham Agarwal, Vlad Dinu, Thomas Searle et al.

This study introduces RelCAT (Relation Concept Annotation Toolkit), an interactive tool, library, and workflow designed to classify relations between entities extracted from clinical narratives. Building upon the CogStack MedCAT framework, RelCAT addresses the challenge of capturing complete clinical relations dispersed within text. The toolkit implements state-of-the-art machine learning models such as BERT and Llama along with proven evaluation and training methods. We demonstrate a dataset annotation tool (built within MedCATTrainer), model training, and evaluate our methodology on both openly available gold-standard and real-world UK National Health Service (NHS) hospital clinical datasets. We perform extensive experimentation and a comparative analysis of the various publicly available models with varied approaches selected for model fine-tuning. Finally, we achieve macro F1-scores of 0.977 on the gold-standard n2c2, surpassing the previous state-of-the-art performance, and achieve performance of >=0.93 F1 on our NHS gathered datasets.

Ishita Kumar, Snigdha Viswanathan, Sushrita Yerra et al.

Long-text generation is seemingly ubiquitous in real-world applications of large language models such as generating an email or writing a review. Despite the fundamental importance and prevalence of long-text generation in many practical applications, existing work on personalized generation has focused on the generation of very short text. To overcome these limitations, we study the problem of personalized long-text generation, that is, generating long-text that is personalized for a specific user while being practically useful for the vast majority of real-world applications that naturally require the generation of longer text. In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark. LongLaMP provides a comprehensive and diverse evaluation framework for personalized long-text generation. Extensive experiments on LongLaMP for zero-shot and fine-tuned language tasks demonstrate the effectiveness of the proposed benchmark and its utility for developing and evaluating techniques for personalized long-text generation across a wide variety of long-text generation tasks. The results highlight the importance of personalization across a wide variety of long-text generation tasks. Finally, we release the benchmark for others to use for this important problem.

Anya Belz, Shubham Agarwal, Anastasia Shimorina et al.

Against the background of what has been termed a reproducibility crisis in science, the NLP field is becoming increasingly interested in, and conscientious about, the reproducibility of its results. The past few years have seen an impressive range of new initiatives, events and active research in the area. However, the field is far from reaching a consensus about how reproducibility should be defined, measured and addressed, with diversity of views currently increasing rather than converging. With this focused contribution, we aim to provide a wide-angle, and as near as possible complete, snapshot of current work on reproducibility in NLP, delineating differences and similarities, and providing pointers to common denominators.

Shubham Agarwal, Trung Bui, Joon-Young Lee et al.

Visual Dialog involves "understanding" the dialog history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to generate the correct response. In this paper, we show that co-attention models which explicitly encode dialog history outperform models that don't, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowd-sourcing dataset collection procedure by showing that history is indeed only required for a small amount of the data and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisDialConv) of the VisDial val set and provide a benchmark of 63% NDCG.

Shubham Agarwal, Raghav Goyal

This manuscript describes our approach for the Visual Dialog Challenge 2018. We use an ensemble of three discriminative models with different encoders and decoders for our final submission. Our best performing model on 'test-std' split achieves the NDCG score of 55.46 and the MRR value of 63.77, securing third position in the challenge.

Christian Muise, Tathagata Chakraborti, Shubham Agarwal et al.

Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft. This is in large part due to the rapidly growing market demand for dialogue agents capable of goal-oriented behaviour. Due to the business process nature of these conversations, end-to-end machine learning systems are generally not a viable option, as the generated dialogue agents must be deployable and verifiable on behalf of the businesses authoring them. In this work, we propose a paradigm shift in the creation of goal-oriented complex dialogue systems that dramatically eliminates the need for a designer to manually specify a dialogue tree, which nearly all current systems have to resort to when the interaction pattern falls outside standard patterns such as slot filling. We propose a declarative representation of the dialogue agent to be processed by state-of-the-art planning technology. Our proposed approach covers all aspects of the process; from model solicitation to the execution of the generated plans/dialogue agents. Along the way, we introduce novel planning encodings for declarative dialogue synthesis, a variety of interfaces for working with the specification as a dialogue architect, and a robust executor for generalized contingent plans. We have created prototype implementations of all components, and in this paper, we further demonstrate the resulting system empirically.

Adi Botea, Christian Muise, Shubham Agarwal et al.

Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip require a much more complex multi-turn dialogue. Current limitations of conversational systems have made it difficult to support applications that require personalization, customization and context dependent interactions. We tackle this challenging problem by using domain-independent AI planning to automatically create dialogue plans, customized to guide a dialogue towards achieving a given goal. The input includes a library of atomic dialogue actions, an initial state of the dialogue, and a goal. Dialogue plans are plugged into a dialogue system capable to orchestrate their execution. Use cases demonstrate the viability of the approach. Our work on dialogue planning has been integrated into a product, and it is in the process of being deployed into another.

Shubham Agarwal, Marc Dymetman, Eric Gaussier

This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing delexicalization (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, which opens up a new way of creating artificial datasets for Natural Language Generation.

Shubham Agarwal, Ondrej Dusek, Ioannis Konstas et al.

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system's output.

Shubham Agarwal, Ondrej Dusek, Ioannis Konstas et al.

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB.

Prabhjot Singh, Sumit Dhawan, Shubham Agarwal et al.

This paper exemplifies the implementation of an efficient Information Retrieval (IR) System to compute the similarity between a dataset and a query using Fuzzy Logic. TREC dataset has been used for the same purpose. The dataset is parsed to generate keywords index which is used for the similarity comparison with the user query. Each query is assigned a score value based on its fuzzy similarity with the index keywords. The relevant documents are retrieved based on the score value. The performance and accuracy of the proposed fuzzy similarity model is compared with Cosine similarity model using Precision-Recall curves. The results prove the dominance of Fuzzy Similarity based IR system.