Shubham Kumar

Shreya Saxena, Raj Sangani, Siva Prasad et al.

Recent advances in the healthcare industry have led to an abundance of unstructured data, making it challenging to perform tasks such as efficient and accurate information retrieval at scale. Our work offers an all-in-one scalable solution for extracting and exploring complex information from large-scale research documents, which would otherwise be tedious. First, we briefly explain our knowledge synthesis process to extract helpful information from unstructured text data of research documents. Then, on top of the knowledge extracted from the documents, we perform complex information retrieval using three major components- Paragraph Retrieval, Triplet Retrieval from Knowledge Graphs, and Complex Question Answering (QA). These components combine lexical and semantic-based methods to retrieve paragraphs and triplets and perform faceted refinement for filtering these search results. The complexity of biomedical queries and documents necessitates using a QA system capable of handling queries more complex than factoid queries, which we evaluate qualitatively on the COVID-19 Open Research Dataset (CORD-19) to demonstrate the effectiveness and value-add.

Shubham Kumar, Narendra Ahuja

Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more autonomously in higher-stakes settings may similarly be vulnerable to such attacks. Prior work has studied jailbreak success by examining the model's intermediate representations, identifying directions in this space that causally encode concepts like harmfulness and refusal. Then, they globally explain all jailbreak attacks as attempting to reduce or strengthen these concepts (e.g., reduce harmfulness). However, different jailbreak strategies may succeed by strengthening or suppressing different intermediate concepts, and the same jailbreak strategy may not work for different harmful request categories (e.g., violence vs. cyberattack); thus, we seek to give a local explanation -- i.e., why did this specific jailbreak succeed? To address this gap, we introduce LOCA, a method that gives Local, CAusal explanations of jailbreak success by identifying a minimal set of interpretable, intermediate representation changes that causally induce model refusal on an otherwise successful jailbreak request. We evaluate LOCA on harmful original-jailbreak pairs from a large jailbreak benchmark across Gemma and Llama chat models, comparing against prior methods adapted to this setting. LOCA can successfully induce refusal by making, on average, six interpretable changes; prior work routinely fails to achieve refusal even after 20 changes. LOCA is a step toward mechanistic, local explanations of jailbreak success in LLMs. Code to be released.

Shubham Kumar, Anshuman Sahoo

Accurate wellbore trajectory prediction is a paramount challenge in subsurface engineering, governed by complex interactions between the drilling assembly and heterogeneous geological formations. This research establishes a comprehensive, mathematically rigorous framework for trajectory prediction that moves beyond empirical modeling to a geomechanically-informed, data-driven surrogate approach.The study leverages Log ASCII Standard (LAS) and wellbore deviation (DEV) data from 14 wells in the Gulfaks oil field, treating petrophysical logs not merely as input features, but as proxies for the mechanical properties of the rock that fundamentally govern drilling dynamics. A key contribution of this work is the formal derivation of wellbore kinematic models, including the Average Angle method and Dogleg Severity, from the first principles of vector calculus and differential geometry, contextualizing them as robust numerical integration schemes. The core of the predictive model is a Gated Recurrent Unit (GRU) network, for which we provide a complete, step-by-step derivation of the forward propagation dynamics and the Backpropagation Through Time (BPTT) training algorithm. This detailed theoretical exposition, often omitted in applied studies, clarifies the mechanisms by which the network learns temporal dependencies. The methodology encompasses a theoretically justified data preprocessing pipeline, including feature normalization, uniform depth resampling, and sequence generation. Trajectory post-processing and error analysis are conducted using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R2).

Shubham Kumar, Vijay Pratap Sharma, Vaibhav Neema et al.

The rapid adoption of low-precision arithmetic in artificial intelligence and edge computing has created a strong demand for energy-efficient and flexible floating-point multiply-accumulate (MAC) units. This paper presents a fully pipelined dual-precision floating-point MAC processing engine supporting FP8 formats (E4M3, E5M2) and FP4 formats (E2M1, E1M2), specifically optimized for low-power and high-throughput AI workloads. The proposed architecture employs a novel bit-partitioning technique that enables a single 4-bit unit multiplier to operate either as a standard 4x4 multiplier for FP8 or as two parallel 2x2 multipliers for 2-bit operands, achieving 100 percent hardware utilization without duplicating logic. Implemented in 28 nm technology, the proposed processing engine achieves an operating frequency of 1.94 GHz with an area of 0.00396 mm^2 and power consumption of 2.13 mW, resulting in up to 60.4 percent area reduction and 86.6 percent power savings compared to state-of-the-art designs.

Sourya Dipta Das, Shubham Kumar, Kuldeep Yadav

Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature. Developing accurate grammar scoring models further requires extensive expert annotation, making large-scale data creation impractical. To address these limitations, we propose a zero-shot grammar competency estimation framework that leverages unlabeled data and Large Language Models (LLMs) without relying on manual labels. During training, we employ LLM-generated predictions on unlabeled data by using grammar competency rubric-based prompts. These predictions, treated as pseudo labels, are utilized to train a transformer-based model through a novel training framework designed to handle label noise effectively. We show that the choice of LLM for pseudo-label generation critically affects model performance and that the ratio of clean-to-noisy samples during training strongly influences stability and accuracy. Finally, a qualitative analysis of error intensity and score prediction confirms the robustness and interpretability of our approach. Experimental results demonstrate the efficacy of our approach in estimating grammar competency scores with high accuracy, paving the way for scalable, low-resource grammar assessment systems.

Shubham Kumar, Narendra Ahuja

Deep vision models perform input-output computations that are hard to interpret. Concept-based explanation methods (CBEMs) increase interpretability by re-expressing parts of the model with human-understandable semantic units, or concepts. Checking if the derived explanations are faithful -- that is, they represent the model's internal computation -- requires a surrogate that combines concepts to compute the output. Simplifications made for interpretability inevitably reduce faithfulness, resulting in a tradeoff between the two. State-of-the-art unsupervised CBEMs (U-CBEMs) have reported increasingly interpretable concepts, while also being more faithful to the model. However, we observe that the reported improvement in faithfulness artificially results from either (1) using overly complex surrogates, which introduces an unmeasured cost to the explanation's interpretability, or (2) relying on deletion-based approaches that, as we demonstrate, do not properly measure faithfulness. We propose Surrogate Faithfulness (SURF), which (1) replaces prior complex surrogates with a simple, linear surrogate that measures faithfulness without changing the explanation's interpretability and (2) introduces well-motivated metrics that assess loss across all output classes, not just the predicted class. We validate SURF with a measure-over-measure study by proposing a simple sanity check -- explanations with random concepts should be less faithful -- which prior surrogates fail. SURF enables the first reliable faithfulness benchmark of U-CBEMs, revealing that many visually compelling U-CBEMs are not faithful. Code to be released.

Shubham Kumar, Sailesh Conjeti, Abhijit Guha Roy et al.

We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended for other segmentation tasks involving multi-modalities. InfiNet consists of double encoder arms for T1 and T2 input scans that feed into a joint-decoder arm that terminates in the classification layer. The novelty of InfiNet lies in the manner in which the decoder upsamples lower resolution input feature map(s) from multiple encoder arms. Specifically, the pooled indices computed in the max-pooling layers of each of the encoder blocks are related to the corresponding decoder block to perform non-linear learning-free upsampling. The sparse maps are concatenated with intermediate encoder representations (skip connections) and convolved with trainable filters to produce dense feature maps. InfiNet is trained end-to-end to optimize for the Generalized Dice Loss, which is well-suited for high class imbalance. InfiNet achieves the whole-volume segmentation in under 50 seconds and we demonstrate competitive performance against multiple state-of-the art deep architectures and their multi-modal variants.

Shubham Kumar, Abhijit Guha Roy, Ping Wu et al.

Several diseases of parkinsonian syndromes present similar symptoms at early stage and no objective widely used diagnostic methods have been approved until now. Positron emission tomography (PET) with $^{18}$F-FDG was shown to be able to assess early neuronal dysfunction of synucleinopathies and tauopathies. Tensor factorization (TF) based approaches have been applied to identify characteristic metabolic patterns for differential diagnosis. However, these conventional dimension-reduction strategies assume linear or multi-linear relationships inside data, and are therefore insufficient to distinguish nonlinear metabolic differences between various parkinsonian syndromes. In this paper, we propose a Deep Projection Neural Network (DPNN) to identify characteristic metabolic pattern for early differential diagnosis of parkinsonian syndromes. We draw our inspiration from the existing TF methods. The network consists of a (i) compression part: which uses a deep network to learn optimal 2D projections of 3D scans, and a (ii) classification part: which maps the 2D projections to labels. The compression part can be pre-trained using surplus unlabelled datasets. Also, as the classification part operates on these 2D projections, it can be trained end-to-end effectively with limited labelled data, in contrast to 3D approaches. We show that DPNN is more effective in comparison to existing state-of-the-art and plausible baselines.