Mohit Gupta

Mohit Gupta, Akiko Aizawa, Rajiv Ratn Shah

The emergence of large language models (LLMs) has significantly influenced numerous fields, including healthcare, by enhancing the capabilities of automated systems to process and generate human-like text. However, despite their advancements, the reliability and accuracy of LLMs in medical contexts remain critical concerns. Current evaluation methods often lack robustness and fail to provide a comprehensive assessment of LLM performance, leading to potential risks in clinical settings. In this work, we propose Med-CoDE, a specifically designed evaluation framework for medical LLMs to address these challenges. The framework leverages a critique-based approach to quantitatively measure the degree of disagreement between model-generated responses and established medical ground truths. This framework captures both accuracy and reliability in medical settings. The proposed evaluation framework aims to fill the existing gap in LLM assessment by offering a systematic method to evaluate the quality and trustworthiness of medical LLMs. Through extensive experiments and case studies, we illustrate the practicality of our framework in providing a comprehensive and reliable evaluation of medical LLMs.

Varun Sundar, Sizhuo Ma, Aswin C. Sankaranarayanan et al. · cmu

We present a novel structured light technique that uses Single Photon Avalanche Diode (SPAD) arrays to enable 3D scanning at high-frame rates and low-light levels. This technique, called "Single-Photon Structured Light", works by sensing binary images that indicates the presence or absence of photon arrivals during each exposure; the SPAD array is used in conjunction with a high-speed binary projector, with both devices operated at speeds as high as 20~kHz. The binary images that we acquire are heavily influenced by photon noise and are easily corrupted by ambient sources of light. To address this, we develop novel temporal sequences using error correction codes that are designed to be robust to short-range effects like projector and camera defocus as well as resolution mismatch between the two devices. Our lab prototype is capable of 3D imaging in challenging scenarios involving objects with extremely low albedo or undergoing fast motion, as well as scenes under strong ambient illumination.

Varun Sundar, Matthew Dutson, Andrei Ardelean et al.

Event cameras capture the world at high time resolution and with minimal bandwidth requirements. However, event streams, which only encode changes in brightness, do not contain sufficient scene information to support a wide variety of downstream tasks. In this work, we design generalized event cameras that inherently preserve scene intensity in a bandwidth-efficient manner. We generalize event cameras in terms of when an event is generated and what information is transmitted. To implement our designs, we turn to single-photon sensors that provide digital access to individual photon detections; this modality gives us the flexibility to realize a rich space of generalized event cameras. Our single-photon event cameras are capable of high-speed, high-fidelity imaging at low readout rates. Consequently, these event cameras can support plug-and-play downstream inference, without capturing new event datasets or designing specialized event-vision models. As a practical implication, our designs, which involve lightweight and near-sensor-compatible computations, provide a way to use single-photon sensors without exorbitant bandwidth costs.

Carter Sifferman, Yeping Wang, Mohit Gupta et al.

We provide methods which recover planar scene geometry by utilizing the transient histograms captured by a class of close-range time-of-flight (ToF) distance sensor. A transient histogram is a one dimensional temporal waveform which encodes the arrival time of photons incident on the ToF sensor. Typically, a sensor processes the transient histogram using a proprietary algorithm to produce distance estimates, which are commonly used in several robotics applications. Our methods utilize the transient histogram directly to enable recovery of planar geometry more accurately than is possible using only proprietary distance estimates, and consistent recovery of the albedo of the planar surface, which is not possible with proprietary distance estimates alone. This is accomplished via a differentiable rendering pipeline, which simulates the transient imaging process, allowing direct optimization of scene geometry to match observations. To validate our methods, we capture 3,800 measurements of eight planar surfaces from a wide range of viewpoints, and show that our method outperforms the proprietary-distance-estimate baseline by an order of magnitude in most scenarios. We demonstrate a simple robotics application which uses our method to sense the distance to and slope of a planar surface from a sensor mounted on the end effector of a robot arm.

Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma et al.

In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTorch models . Built using the MLIR framework, our compiler applies a structured sequence of passes to exploit NPU architectural features to accelerate AI workloads. It enables faster deployment of new Triton kernels (hand-written or subgraphs from PyTorch 2.0), for our target by providing automated compilation from kernel to binary. By ingesting Triton kernels, we generate mega-kernels that maximize data locality in the NPU's Tightly Coupled Memory (TCM), reducing the bandwidth bottlenecks inherent in library-based approaches. This initiative complements our commercial toolchains by providing developers with an open-source MLIR-based compilation stack that gives them a path to advance AI compilation capabilities through a more flexible approach. Hexagon-MLIR is a work-in-progress, and we are continuing to add many more optimizations and capabilities in this effort.

Matthew Dutson, Yin Li, Mohit Gupta

Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are often applied repeatedly across frames or temporal chunks. In this work, we exploit temporal redundancy between subsequent inputs to reduce the cost of Transformers for video processing. We describe a method for identifying and re-processing only those tokens that have changed significantly over time. Our proposed family of models, Eventful Transformers, can be converted from existing Transformers (often without any re-training) and give adaptive control over the compute cost at runtime. We evaluate our method on large-scale datasets for video object detection (ImageNet VID) and action recognition (EPIC-Kitchens 100). Our approach leads to significant computational savings (on the order of 2-4x) with only minor reductions in accuracy.

Sacha Jungerman, Atul Ingle, Yin Li et al.

Time-resolved image sensors that capture light at pico-to-nanosecond timescales were once limited to niche applications but are now rapidly becoming mainstream in consumer devices. We propose low-cost and low-power imaging modalities that capture scene information from minimal time-resolved image sensors with as few as one pixel. The key idea is to flood illuminate large scene patches (or the entire scene) with a pulsed light source and measure the time-resolved reflected light by integrating over the entire illuminated area. The one-dimensional measured temporal waveform, called \emph{transient}, encodes both distances and albedoes at all visible scene points and as such is an aggregate proxy for the scene's 3D geometry. We explore the viability and limitations of the transient waveforms by themselves for recovering scene information, and also when combined with traditional RGB cameras. We show that plane estimation can be performed from a single transient and that using only a few more it is possible to recover a depth map of the whole scene. We also show two proof-of-concept hardware prototypes that demonstrate the feasibility of our approach for compact, mobile, and budget-limited applications.

Aryan Garg, Sizhuo Ma, Mohit Gupta

Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but raw \emph{quanta frames} contain only sparse, noisy, binary photon detections. Recovering a coherent image from a burst of such frames requires handling alignment, denoising, and demosaicing (for color) under noise statistics far outside those assumed by standard restoration pipelines or modern generative models. We present an approach that adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging. Our method leverages the structural and semantic priors of internet-scale diffusion models while introducing mechanisms to handle Bernoulli photon statistics. By integrating latent-space restoration with burst-level spatio-temporal reasoning, our approach produces reconstructions that are both photometrically faithful and perceptually pleasing, even under high-speed motion. We evaluate the method on synthetic benchmarks and new real-world datasets, including the first color SPAD burst dataset and a challenging \textit{Deforming (XD)} video benchmark. Across all settings, the approach substantially improves perceptual quality over classical and modern learning-based baselines, demonstrating the promise of adapting large generative priors to extreme photon-limited sensing. Code at \href{https://github.com/Aryan-Garg/gQIR}{https://github.com/Aryan-Garg/gQIR}.

Sacha Jungerman, Atul Ingle, Mohit Gupta

Scene reconstruction in the presence of high-speed motion and low illumination is important in many applications such as augmented and virtual reality, drone navigation, and autonomous robotics. Traditional motion estimation techniques fail in such conditions, suffering from too much blur in the presence of high-speed motion and strong noise in low-light conditions. Single-photon cameras have recently emerged as a promising technology capable of capturing hundreds of thousands of photon frames per second thanks to their high speed and extreme sensitivity. Unfortunately, traditional computer vision techniques are not well suited for dealing with the binary-valued photon data captured by these cameras because these are corrupted by extreme Poisson noise. Here we present a method capable of estimating extreme scene motion under challenging conditions, such as low light or high dynamic range, from a sequence of high-speed image frames such as those captured by a single-photon camera. Our method relies on iteratively improving a motion estimate by grouping and aggregating frames after-the-fact, in a stratified manner. We demonstrate the creation of high-quality panoramas under fast motion and extremely low light, and super-resolution results using a custom single-photon camera prototype. For code and supplemental material see our $\href{https://wisionlab.com/project/panoramas-from-photons/}{\text{project webpage}}$.

Bhavya Goyal, Jean-François Lalonde, Yin Li et al.

Scene inference under low-light is a challenging problem due to severe noise in the captured images. One way to reduce noise is to use longer exposure during the capture. However, in the presence of motion (scene or camera motion), longer exposures lead to motion blur, resulting in loss of image information. This creates a trade-off between these two kinds of image degradations: motion blur (due to long exposure) vs. noise (due to short exposure), also referred as a dual image corruption pair in this paper. With the rise of cameras capable of capturing multiple exposures of the same scene simultaneously, it is possible to overcome this trade-off. Our key observation is that although the amount and nature of degradation varies for these different image captures, the semantic content remains the same across all images. To this end, we propose a method to leverage these multi exposure captures for robust inference under low-light and motion. Our method builds on a feature consistency loss to encourage similar results from these individual captures, and uses the ensemble of their final predictions for robust visual recognition. We demonstrate the effectiveness of our approach on simulated images as well as real captures with multiple exposures, and across the tasks of object detection and image classification.

Avery Gump, Connor Henley, Sungjin Cheong et al.

Modern LiDARs are rapidly transitioning from bulky, mechanically scanned systems to ultra-compact, low-cost, solid-state arrays. This miniaturization-while enabling scalability, affordability, and camera-like data structures-introduces a new and severe failure mode: internal-multipath glare. When light from a bright or retroreflective surface reflects and scatters within the LiDAR, light that should reach a single pixel spreads across the pixel array. The resulting artifacts create phantom objects, obscure real ones, and produce safety-critical "ghosts in the point clouds." This paper introduces a physically grounded sensing model and algorithmic techniques for addressing this effect. We show that internal glare can be represented as a linear, scene-independent operator-the Transient Glare Spread Function (TGSF)-acting on the transient measurements. Building on this model, we develop a training-free approach that operates on low-level LiDAR detections (or echoes) prior to point-cloud formation, leveraging knowledge of the glare spread function to reason about the likelihood of each detection arising from glare. The resulting approach is compatible with existing LiDAR signal-processing pipelines, and deployable on unmodified commercial sensors. Using experiments with real single-photon LiDAR hardware, we demonstrate substantial suppression of severe glare artifacts while preserving true scene structure.

Narayana Darapaneni, Arjun Tanndalam, Mohit Gupta et al.

India is the second largest producer of fruits and vegetables in the world, and one of the largest consumers of fruits like Banana, Papaya and Mangoes through retail and ecommerce giants like BigBasket, Grofers and Amazon Fresh. However, adoption of technology in supply chain and retail stores is still low and there is a great potential to adopt computer-vision based technology for identification and classification of fruits. We have chosen banana fruit to build a computer vision based model to carry out the following three use-cases (a) Identify Banana from a given image (b) Determine sub-family or variety of Banana (c) Determine the quality of Banana. Successful execution of these use-cases using computer-vision model would greatly help with overall inventory management automation, quality control, quick and efficient weighing and billing which all are manual labor intensive currently. In this work, we suggest a machine learning pipeline that combines the ideas of CNNs, transfer learning, and data augmentation towards improving Banana fruit sub family and quality image classification. We have built a basic CNN and then went on to tune a MobileNet Banana classification model using a combination of self-curated and publicly-available dataset of 3064 images. The results show an overall 93.4% and 100% accuracy for sub-family/variety and for quality test classifications respectively.

Carter Sifferman, William Sun, Mohit Gupta et al.

We investigate methods for determining if a planar surface contains geometric deviations (e.g., protrusions, objects, divots, or cliffs) using only an instantaneous measurement from a miniature optical time-of-flight sensor. The key to our method is to utilize the entirety of information encoded in raw time-of-flight data captured by off-the-shelf distance sensors. We provide an analysis of the problem in which we identify the key ambiguity between geometry and surface photometrics. To overcome this challenging ambiguity, we fit a Gaussian mixture model to a small dataset of planar surface measurements. This model implicitly captures the expected geometry and distribution of photometrics of the planar surface and is used to identify measurements that are likely to contain deviations. We characterize our method on a variety of surfaces and planar deviations across a range of scenarios. We find that our method utilizing raw time-of-flight data outperforms baselines which use only derived distance estimates. We build an example application in which our method enables mobile robot obstacle and cliff avoidance over a wide field-of-view.

Sacha Jungerman, Aryan Garg, Mohit Gupta

Neural radiance fields, or NeRFs, have become the de facto approach for high-quality view synthesis from a collection of images captured from multiple viewpoints. However, many issues remain when capturing images in-the-wild under challenging conditions, such as low light, high dynamic range, or rapid motion leading to smeared reconstructions with noticeable artifacts. In this work, we introduce quanta radiance fields, a novel class of neural radiance fields that are trained at the granularity of individual photons using single-photon cameras (SPCs). We develop theory and practical computational techniques for building radiance fields and estimating dense camera poses from unconventional, stochastic, and high-speed binary frame sequences captured by SPCs. We demonstrate, both via simulations and a SPC hardware prototype, high-fidelity reconstructions under high-speed motion, in low light, and for extreme dynamic range settings.

Varun Sundar, Andrei Ardelean, Tristan Swedish et al.

Reinterpretable cameras are defined by their post-processing capabilities that exceed traditional imaging. We present "SoDaCam" that provides reinterpretable cameras at the granularity of photons, from photon-cubes acquired by single-photon devices. Photon-cubes represent the spatio-temporal detections of photons as a sequence of binary frames, at frame-rates as high as 100 kHz. We show that simple transformations of the photon-cube, or photon-cube projections, provide the functionality of numerous imaging systems including: exposure bracketing, flutter shutter cameras, video compressive systems, event cameras, and even cameras that move during exposure. Our photon-cube projections offer the flexibility of being software-defined constructs that are only limited by what is computable, and shot-noise. We exploit this flexibility to provide new capabilities for the emulated cameras. As an added benefit, our projections provide camera-dependent compression of photon-cubes, which we demonstrate using an implementation of our projections on a novel compute architecture that is designed for single-photon imaging.

Matthew Dutson, Nathan Labiosa, Yin Li et al.

When applied sequentially to video, frame-based networks often exhibit temporal inconsistency - for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this work, we introduce a general approach for adapting frame-based models for stable and robust inference on video. We describe a class of stability adapters that can be inserted into virtually any architecture and a resource-efficient training process that can be performed with a frozen base network. We introduce a unified conceptual framework for describing temporal stability and corruption robustness, centered on a proposed accuracy-stability-robustness loss. By analyzing the theoretical properties of this loss, we identify the conditions where it produces well-behaved stabilizer training. Our experiments validate our approach on several vision tasks including denoising (NAFNet), image enhancement (HDRNet), monocular depth (Depth Anything v2), and semantic segmentation (DeepLabv3+). Our method improves temporal stability and robustness against a range of image corruptions (including compression artifacts, noise, and adverse weather), while preserving or improving the quality of predictions.

Lucas J. Koerner, Shantanu Gupta, Atul Ingle et al.

Single-photon cameras (SPCs) are emerging as sensors of choice for various challenging imaging applications. One class of SPCs based on the single-photon avalanche diode (SPAD) detects individual photons using an avalanche process; the raw photon data can then be processed to extract scene information under extremely low light, high dynamic range, and rapid motion. Yet, single-photon sensitivity in SPADs comes at a cost -- each photon detection consumes more energy than that of a CMOS camera. This avalanche power significantly limits sensor resolution and could restrict widespread adoption of SPAD-based SPCs. We propose a computational-imaging approach called \emph{photon inhibition} to address this challenge. Photon inhibition strategically allocates detections in space and time based on downstream inference task goals and resource constraints. We develop lightweight, on-sensor computational inhibition policies that use past photon data to disable SPAD pixels in real-time, to select the most informative future photons. As case studies, we design policies tailored for image reconstruction and edge detection, and demonstrate, both via simulations and real SPC captured data, considerable reduction in photon detections (over 90\% of photons) while maintaining task performance metrics. Our work raises the question of ``which photons should be detected?'', and paves the way for future energy-efficient single-photon imaging.

Avinash Anand, Mohit Gupta, Kritarth Prasad et al.

The rapid progress in the field of natural language processing (NLP) systems and the expansion of large language models (LLMs) have opened up numerous opportunities in the field of education and instructional methods. These advancements offer the potential for tailored learning experiences and immediate feedback, all delivered through accessible and cost-effective services. One notable application area for this technological advancement is in the realm of solving mathematical problems. Mathematical problem-solving not only requires the ability to decipher complex problem statements but also the skill to perform precise arithmetic calculations at each step of the problem-solving process. However, the evaluation of the arithmetic capabilities of large language models remains an area that has received relatively little attention. In response, we introduce an extensive mathematics dataset called "MathQuest" sourced from the 11th and 12th standard Mathematics NCERT textbooks. This dataset encompasses mathematical challenges of varying complexity and covers a wide range of mathematical concepts. Utilizing this dataset, we conduct fine-tuning experiments with three prominent LLMs: LLaMA-2, WizardMath, and MAmmoTH. These fine-tuned models serve as benchmarks for evaluating their performance on our dataset. Our experiments reveal that among the three models, MAmmoTH-13B emerges as the most proficient, achieving the highest level of competence in solving the presented mathematical problems. Consequently, MAmmoTH-13B establishes itself as a robust and dependable benchmark for addressing NCERT mathematics problems.

Fangzhou Mu, Carter Sifferman, Sacha Jungerman et al.

We present a method for reconstructing 3D shape of arbitrary Lambertian objects based on measurements by miniature, energy-efficient, low-cost single-photon cameras. These cameras, operating as time resolved image sensors, illuminate the scene with a very fast pulse of diffuse light and record the shape of that pulse as it returns back from the scene at a high temporal resolution. We propose to model this image formation process, account for its non-idealities, and adapt neural rendering to reconstruct 3D geometry from a set of spatially distributed sensors with known poses. We show that our approach can successfully recover complex 3D shapes from simulated data. We further demonstrate 3D object reconstruction from real-world captures, utilizing measurements from a commodity proximity sensor. Our work draws a connection between image-based modeling and active range scanning and is a step towards 3D vision with single-photon cameras.

Avinash Anand, Kritarth Prasad, Ujjwal Goel et al.

Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into extensive literature and grapple with articulating relevant content. To address this challenge, the field of citation text generation (CTG) has emerged. However, while earlier methods have primarily centered on creating single-sentence citations, practical scenarios frequently necessitate citing multiple papers within a single paragraph. To bridge this gap, we propose a method that leverages Large Language Models (LLMs) to generate multi-citation sentences. Our approach involves a single source paper and a collection of target papers, culminating in a coherent paragraph containing multi-sentence citation text. Furthermore, we introduce a curated dataset named MCG-S2ORC, composed of English-language academic research papers in Computer Science, showcasing multiple citation instances. In our experiments, we evaluate three LLMs LLaMA, Alpaca, and Vicuna to ascertain the most effective model for this endeavor. Additionally, we exhibit enhanced performance by integrating knowledge graphs from target papers into the prompts for generating citation text. This research underscores the potential of harnessing LLMs for citation generation, opening a compelling avenue for exploring the intricate connections between scientific documents.

Avinash Anand, Mohit Gupta, Kritarth Prasad et al.

Citation Text Generation (CTG) is a task in natural language processing (NLP) that aims to produce text that accurately cites or references a cited document within a source document. In CTG, the generated text draws upon contextual cues from both the source document and the cited paper, ensuring accurate and relevant citation information is provided. Previous work in the field of citation generation is mainly based on the text summarization of documents. Following this, this paper presents a framework, and a comparative study to demonstrate the use of Large Language Models (LLMs) for the task of citation generation. Also, we have shown the improvement in the results of citation generation by incorporating the knowledge graph relations of the papers in the prompt for the LLM to better learn the relationship between the papers. To assess how well our model is performing, we have used a subset of standard S2ORC dataset, which only consists of computer science academic research papers in the English Language. Vicuna performs best for this task with 14.15 Meteor, 12.88 Rouge-1, 1.52 Rouge-2, and 10.94 Rouge-L. Also, Alpaca performs best, and improves the performance by 36.98% in Rouge-1, and 33.14% in Meteor by including knowledge graphs.

Avinash Anand, Raj Jaiswal, Pijush Bhuyan et al.

The automatic recognition of tabular data in document images presents a significant challenge due to the diverse range of table styles and complex structures. Tables offer valuable content representation, enhancing the predictive capabilities of various systems such as search engines and Knowledge Graphs. Addressing the two main problems, namely table detection (TD) and table structure recognition (TSR), has traditionally been approached independently. In this research, we propose an end-to-end pipeline that integrates deep learning models, including DETR, CascadeTabNet, and PP OCR v2, to achieve comprehensive image-based table recognition. This integrated approach effectively handles diverse table styles, complex structures, and image distortions, resulting in improved accuracy and efficiency compared to existing methods like Table Transformers. Our system achieves simultaneous table detection (TD), table structure recognition (TSR), and table content recognition (TCR), preserving table structures and accurately extracting tabular data from document images. The integration of multiple models addresses the intricacies of table recognition, making our approach a promising solution for image-based table understanding, data extraction, and information retrieval applications. Our proposed approach achieves an IOU of 0.96 and an OCR Accuracy of 78%, showcasing a remarkable improvement of approximately 25% in the OCR Accuracy compared to the previous Table Transformer approach.

Vansh Gupta, Mohit Gupta, Jai Garg et al.

Address matching is an important task for many businesses especially delivery and take out companies which help them to take out a certain address from their data warehouse. Existing solution uses similarity of strings, and edit distance algorithms to find out the similar addresses from the address database, but these algorithms could not work effectively with redundant, unstructured, or incomplete address data. This paper discuss semantic Address matching technique, by which we can find out a particular address from a list of possible addresses. We have also reviewed existing practices and their shortcoming. Semantic address matching is an essentially NLP task in the field of deep learning. Through this technique We have the ability to triumph the drawbacks of existing methods like redundant or abbreviated data problems. The solution uses the OCR on invoices to extract the address and create the data pool of addresses. Then this data is fed to the algorithm BM-25 for scoring the best matching entries. Then to observe the best result, this will pass through BERT for giving the best possible result from the similar queries. Our investigation exhibits that our methodology enormously improves both accuracy and review of cutting-edge technology existing techniques.

Avinash Anand, Kritarth Prasad, Chhavi Kirtani et al.

Large Language Models (LLMs) have demonstrated strong capabilities in text-based tasks but struggle with the complex reasoning required for physics problems, particularly in advanced arithmetic and conceptual understanding. While some research has explored ways to enhance LLMs in physics education using techniques such as prompt engineering and Retrieval Augmentation Generation (RAG), not enough effort has been made in addressing their limitations in physics reasoning. This paper presents a novel approach to improving LLM performance on physics questions using Reinforcement Learning with Human and Artificial Intelligence Feedback (RLHAIF). We evaluate several reinforcement learning methods, including Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO), and Remax optimization. These methods are chosen to investigate RL policy performance with different settings on the PhyQA dataset, which includes challenging physics problems from high school textbooks. Our RLHAIF model, tested on leading LLMs like LLaMA2 and Mistral, achieved superior results, notably with the MISTRAL-PPO model, demonstrating marked improvements in reasoning and accuracy. It achieved high scores, with a 58.67 METEOR score and a 0.74 Reasoning score, making it a strong example for future physics reasoning research in this area.

Mohit Gupta, Nitesh Garg, Jai Garg et al.

Parcels delivery is a critical activity in railways. More importantly, each parcel must be thoroughly checked and sorted according to its destination address. We require an efficient and robust IoT system capable of doing all of these tasks with great precision and minimal human interaction. This paper discusses, We created a fully-fledged solution using IoT and machine learning to assist trains in performing this operation efficiently. In this study, we covered the product, which consists mostly of two phases. Scanning is the first step, followed by sorting. During the scanning process, the parcel will be passed through three scanners that will look for explosives, drugs, and any dangerous materials in the parcel and will trash it if any of the tests fail. When the scanning step is over, the parcel moves on to the sorting phase, where we use QR codes to retrieve the details of the parcels and sort them properly. The simulation of the system is done using the blender software. Our research shows that our procedure significantly improves accuracy as well as the assessment of cutting-edge technology and existing techniques.

Avinash Anand, Raj Jaiswal, Mohit Gupta et al.

Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of annotated instances, which is both expensive and time-consuming. As a result, differences between the source and target domains may significantly impact how well these models function. To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain. In this research, we introduced a synthetic document dataset called RanLayNet, enriched with automatically assigned labels denoting spatial positions, ranges, and types of layout elements. The primary aim of this endeavor is to develop a versatile dataset capable of training models with robustness and adaptability to diverse document formats. Through empirical experimentation, we demonstrate that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents. Moreover, we conduct a comparative analysis by fine-tuning inference models using both PubLayNet and IIIT-AR-13K datasets on the Doclaynet dataset. Our findings emphasize that models enriched with our dataset are optimal for tasks such as achieving 0.398 and 0.588 mAP95 score in the scientific document domain for the TABLE class.

Bhavya Goyal, Felipe Gutierrez-Barragan, Wei Lin et al.

LiDAR-based 3D sensors provide point clouds, a canonical 3D representation used in various scene understanding tasks. Modern LiDARs face key challenges in several real-world scenarios, such as long-distance or low-albedo objects, producing sparse or erroneous point clouds. These errors, which are rooted in the noisy raw LiDAR measurements, get propagated to downstream perception models, resulting in potentially severe loss of accuracy. This is because conventional 3D processing pipelines do not retain any uncertainty information from the raw measurements when constructing point clouds. We propose Probabilistic Point Clouds (PPC), a novel 3D scene representation where each point is augmented with a probability attribute that encapsulates the measurement uncertainty (or confidence) in the raw data. We further introduce inference approaches that leverage PPC for robust 3D object detection; these methods are versatile and can be used as computationally lightweight drop-in modules in 3D inference pipelines. We demonstrate, via both simulations and real captures, that PPC-based 3D inference methods outperform several baselines using LiDAR as well as camera-LiDAR fusion models, across challenging indoor and outdoor scenarios involving small, distant, and low-albedo objects, as well as strong ambient light. Our project webpage is at https://bhavyagoyal.github.io/ppc .

Rishit Tyagi, Rahul Bouri, Mohit Gupta

Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predictions using a GPT-4o pipeline for consistency. For narrative explanation, we propose a ReACT (Reasoning + Acting) framework with semantic retrieval-based few-shot prompting, ensuring grounded and relevant justifications. To enhance factual accuracy and reduce hallucinations, we incorporate a structured taxonomy table as an auxiliary knowledge base. Our results show that integrating auxiliary knowledge in prompts improves classification accuracy and justification reliability, with applications in media analysis, education, and intelligence gathering.

Mohit Gupta, Debjit Bhowmick, Meead Saberi et al.

Accurate bicycling volume estimation is crucial for making informed decisions and planning about future investments in bicycling infrastructure. However, traditional link-level volume estimation models are effective for motorized traffic but face significant challenges when applied to the bicycling context because of sparse data and the intricate nature of bicycling mobility patterns. To the best of our knowledge, we present the first study to utilize a Graph Convolutional Network (GCN) architecture to model link-level bicycling volumes and systematically investigate the impact of varying levels of data sparsity (0%--99%) on model performance, simulating real-world scenarios. We have leveraged Strava Metro data as the primary source of bicycling counts across 15,933 road segments/links in the City of Melbourne, Australia. To evaluate the effectiveness of the GCN model, we benchmark it against traditional machine learning models, such as linear regression, support vector machines, and random forest. Our results show that the GCN model outperforms these traditional models in predicting Annual Average Daily Bicycle (AADB) counts, demonstrating its ability to capture the spatial dependencies inherent in bicycle traffic networks. While GCN remains robust up to 80% sparsity, its performance declines sharply beyond this threshold, highlighting the challenges of extreme data sparsity. These findings underscore the potential of GCNs in enhancing bicycling volume estimation, while also emphasizing the need for further research on methods to improve model resilience under high-sparsity conditions. Our findings offer valuable insights for city planners aiming to improve bicycling infrastructure and promote sustainable transportation.

Carter Sifferman, Yiquan Li, Yiming Li et al.

We aim to recover the geometry of 3D parametric scenes using very few depth measurements from low-cost, commercially available time-of-flight sensors. These sensors offer very low spatial resolution (i.e., a single pixel), but image a wide field-of-view per pixel and capture detailed time-of-flight data in the form of time-resolved photon counts. This time-of-flight data encodes rich scene information and thus enables recovery of simple scenes from sparse measurements. We investigate the feasibility of using a distributed set of few measurements (e.g., as few as 15 pixels) to recover the geometry of simple parametric scenes with a strong prior, such as estimating the 6D pose of a known object. To achieve this, we design a method that utilizes both feed-forward prediction to infer scene parameters, and differentiable rendering within an analysis-by-synthesis framework to refine the scene parameter estimate. We develop hardware prototypes and demonstrate that our method effectively recovers object pose given an untextured 3D model in both simulations and controlled real-world captures, and show promising initial results for other parametric scenes. We additionally conduct experiments to explore the limits and capabilities of our imaging solution.

Rishit Tyagi, Mohit Gupta, Rahul Bouri

Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query generation, answer extraction, verification, and iterative refinement. Experiments demonstrate the effectiveness of our approach, achieving 70.5\% accuracy on DataBench QA and 71.6\% on DataBench Lite QA, significantly surpassing baseline scores of 26\% and 27\% respectively. This paper details our methodology, experimental results, and alternative approaches, providing insights into the strengths and limitations of LLM-driven Table QA.

Mohit Gupta, Debjit Bhowmick, Rhys Newbury et al.

Accurate link-level bicycling volume estimation is essential for sustainable urban transportation planning. However, many cities face significant challenges of high data sparsity due to limited bicycling count sensor coverage. To address this issue, we propose INSPIRE-GNN, a novel Reinforcement Learning (RL)-boosted hybrid Graph Neural Network (GNN) framework designed to optimize sensor placement and improve link-level bicycling volume estimation in data-sparse environments. INSPIRE-GNN integrates Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) with a Deep Q-Network (DQN)-based RL agent, enabling a data-driven strategic selection of sensor locations to maximize estimation performance. Applied to Melbourne's bicycling network, comprising 15,933 road segments with sensor coverage on only 141 road segments (99% sparsity) - INSPIRE-GNN demonstrates significant improvements in volume estimation by strategically selecting additional sensor locations in deployments of 50, 100, 200 and 500 sensors. Our framework outperforms traditional heuristic methods for sensor placement such as betweenness centrality, closeness centrality, observed bicycling activity and random placement, across key metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Furthermore, our experiments benchmark INSPIRE-GNN against standard machine learning and deep learning models in the bicycle volume estimation performance, underscoring its effectiveness. Our proposed framework provides transport planners actionable insights to effectively expand sensor networks, optimize sensor placement and maximize volume estimation accuracy and reliability of bicycling data for informed transportation planning decisions.

Mohit Gupta, Debjit Bhowmick, Ben Beck

Accurate link-level bicycle volume estimation is essential for informed urban and transport planning but it is challenged by extremely sparse count data in urban bicycling networks worldwide. We propose BikeVAE-GNN, a novel dual-task framework augmenting a Hybrid Graph Neural Network (GNN) with Variational Autoencoder (VAE) to estimate Average Daily Bicycle (ADB) counts, addressing sparse bicycle networks. The Hybrid-GNN combines Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and GraphSAGE to effectively model intricate spatial relationships in sparse networks while VAE generates synthetic nodes and edges to enrich the graph structure and enhance the estimation performance. BikeVAE-GNN simultaneously performs - regression for bicycling volume estimation and classification for bicycling traffic level categorization. We demonstrate the effectiveness of BikeVAE-GNN using OpenStreetMap data and publicly available bicycle count data within the City of Melbourne - where only 141 of 15,933 road segments have labeled counts (resulting in 99% count data sparsity). Our experiments show that BikeVAE-GNN outperforms machine learning and baseline GNN models, achieving a mean absolute error (MAE) of 30.82 bicycles per day, accuracy of 99% and F1-score of 0.99. Ablation studies further validate the effective role of Hybrid-GNN and VAE components. Our research advances bicycling volume estimation in sparse networks using novel and state-of-the-art approaches, providing insights for sustainable bicycling infrastructures.

Tianyi Zhang, Matthew Dutson, Vivek Boominathan et al.

Recently quanta image sensors (QIS) -- ultra-fast, zero-read-noise binary image sensors -- have demonstrated remarkable imaging capabilities in many challenging scenarios. Despite their potential, the adoption of these sensors is severely hampered by (a) high data rates and (b) the need for new computational pipelines to handle the unconventional raw data. We introduce a simple, low-bandwidth computational pipeline to address these challenges. Our approach is based on a novel streaming representation with a small memory footprint, efficiently capturing intensity information at multiple temporal scales. Updating the representation requires only 16 floating-point operations/pixel, which can be efficiently computed online at the native frame rate of the binary frames. We use a neural network operating on this representation to reconstruct videos in real-time (10-30 fps). We illustrate why such representation is well-suited for these emerging sensors, and how it offers low latency and high frame rate while retaining flexibility for downstream computer vision. Our approach results in significant data bandwidth reductions ~100X and real-time image reconstruction and computer vision -- $10^4$-$10^5$ reduction in computation than existing state-of-the-art approach while maintaining comparable quality. To the best of our knowledge, our approach is the first to achieve online, real-time image reconstruction on QIS.

Harman Singh, Poorva Garg, Mohit Gupta et al.

We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning (NSCL), which has been quite effective for the task of Visual Question Answering (VQA), for the task of image manipulation. Our system referred to as NeuroSIM can perform complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA. NeuroSIM parses an instruction into a symbolic program, based on a Domain Specific Language (DSL) comprising of object attributes and manipulation operations, that guides its execution. We create a new dataset for the task, and extensive experiments demonstrate that NeuroSIM is highly competitive with or beats SOTA baselines that make use of supervised data for manipulation.

Matthew Dutson, Yin Li, Mohit Gupta

Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We propose Event Neural Networks (EvNets), which leverage this redundancy to achieve considerable computation savings during video inference. A defining characteristic of EvNets is that each neuron has state variables that provide it with long-term memory, which allows low-cost, high-accuracy inference even in the presence of significant camera motion. We show that it is possible to transform a wide range of neural networks into EvNets without re-training. We demonstrate our method on state-of-the-art architectures for both high- and low-level visual processing, including pose recognition, object detection, optical flow, and image enhancement. We observe roughly an order-of-magnitude reduction in computational costs compared to conventional networks, with minimal reductions in model accuracy.

Bhavya Goyal, Mohit Gupta

Scene understanding under low-light conditions is a challenging problem. This is due to the small number of photons captured by the camera and the resulting low signal-to-noise ratio (SNR). Single-photon cameras (SPCs) are an emerging sensing modality that are capable of capturing images with high sensitivity. Despite having minimal read-noise, images captured by SPCs in photon-starved conditions still suffer from strong shot noise, preventing reliable scene inference. We propose photon scale-space a collection of high-SNR images spanning a wide range of photons-per-pixel (PPP) levels (but same scene content) as guides to train inference model on low photon flux images. We develop training techniques that push images with different illumination levels closer to each other in feature representation space. The key idea is that having a spectrum of different brightness levels during training enables effective guidance, and increases robustness to shot noise even in extreme noise cases. Based on the proposed approach, we demonstrate, via simulations and real experiments with a SPAD camera, high-performance on various inference tasks such as image classification and monocular depth estimation under ultra low-light, down to < 1 PPP.

Vaishali Ingale, Anush Mohan, Divit Adlakha et al.

This paper explores the idea of utilising Long Short-Term Memory neural networks (LSTMNN) for the generation of musical sequences in ABC notation. The proposed approach takes ABC notations from the Nottingham dataset and encodes it to be fed as input for the neural networks. The primary objective is to input the neural networks with an arbitrary note, let the network process and augment a sequence based on the note until a good piece of music is produced. Multiple calibrations have been done to amend the parameters of the network for optimal generation. The output is assessed on the basis of rhythm, harmony, and grammar accuracy.

Atul Ingle, Trevor Seets, Mauro Buttafava et al.

Digital camera pixels measure image intensities by converting incident light energy into an analog electrical current, and then digitizing it into a fixed-width binary representation. This direct measurement method, while conceptually simple, suffers from limited dynamic range and poor performance under extreme illumination -- electronic noise dominates under low illumination, and pixel full-well capacity results in saturation under bright illumination. We propose a novel intensity cue based on measuring inter-photon timing, defined as the time delay between detection of successive photons. Based on the statistics of inter-photon times measured by a time-resolved single-photon sensor, we develop theory and algorithms for a scene brightness estimator which works over extreme dynamic range; we experimentally demonstrate imaging scenes with a dynamic range of over ten million to one. The proposed techniques, aided by the emergence of single-photon sensors such as single-photon avalanche diodes (SPADs) with picosecond timing resolution, will have implications for a wide range of imaging applications: robotics, consumer photography, astronomy, microscopy and biomedical imaging.

Felipe Gutierrez-Barragan, Huaijin Chen, Mohit Gupta et al.

Indirect Time-of-Flight (iToF) cameras are a promising depth sensing technology. However, they are prone to errors caused by multi-path interference (MPI) and low signal-to-noise ratio (SNR). Traditional methods, after denoising, mitigate MPI by estimating a transient image that encodes depths. Recently, data-driven methods that jointly denoise and mitigate MPI have become state-of-the-art without using the intermediate transient representation. In this paper, we propose to revisit the transient representation. Using data-driven priors, we interpolate/extrapolate iToF frequencies and use them to estimate the transient image. Given direct ToF (dToF) sensors capture transient images, we name our method iToF2dToF. The transient representation is flexible. It can be integrated with different rule-based depth sensing algorithms that are robust to low SNR and can deal with ambiguous scenarios that arise in practice (e.g., specular MPI, optical cross-talk). We demonstrate the benefits of iToF2dToF over previous methods in real depth sensing scenarios.

Athena Sayles, Ashish Hooda, Mohit Gupta et al.

Physical adversarial examples for camera-based computer vision have so far been achieved through visible artifacts -- a sticker on a Stop sign, colorful borders around eyeglasses or a 3D printed object with a colorful texture. An implicit assumption here is that the perturbations must be visible so that a camera can sense them. By contrast, we contribute a procedure to generate, for the first time, physical adversarial examples that are invisible to human eyes. Rather than modifying the victim object with visible artifacts, we modify light that illuminates the object. We demonstrate how an attacker can craft a modulated light signal that adversarially illuminates a scene and causes targeted misclassifications on a state-of-the-art ImageNet deep learning model. Concretely, we exploit the radiometric rolling shutter effect in commodity cameras to create precise striping patterns that appear on images. To human eyes, it appears like the object is illuminated, but the camera creates an image with stripes that will cause ML models to output the attacker-desired classification. We conduct a range of simulation and physical experiments with LEDs, demonstrating targeted attack rates up to 84%.

Sizhuo Ma, Shantanu Gupta, Arin C. Ulku et al.

Single-photon avalanche diodes (SPADs) are an emerging sensor technology capable of detecting individual incident photons, and capturing their time-of-arrival with high timing precision. While these sensors were limited to single-pixel or low-resolution devices in the past, recently, large (up to 1 MPixel) SPAD arrays have been developed. These single-photon cameras (SPCs) are capable of capturing high-speed sequences of binary single-photon images with no read noise. We present quanta burst photography, a computational photography technique that leverages SPCs as passive imaging devices for photography in challenging conditions, including ultra low-light and fast motion. Inspired by recent success of conventional burst photography, we design algorithms that align and merge binary sequences captured by SPCs into intensity images with minimal motion blur and artifacts, high signal-to-noise ratio (SNR), and high dynamic range. We theoretically analyze the SNR and dynamic range of quanta burst photography, and identify the imaging regimes where it provides significant benefits. We demonstrate, via a recently developed SPAD array, that the proposed method is able to generate high-quality images for scenes with challenging lighting, complex geometries, high dynamic range and moving objects. With the ongoing development of SPAD arrays, we envision quanta burst photography finding applications in both consumer and scientific photography.

Anant Gupta, Atul Ingle, Mohit Gupta

Single-photon avalanche diodes (SPADs) are becoming popular in time-of-flight depth-ranging due to their unique ability to capture individual photons with picosecond timing resolution. However, ambient light (e.g., sunlight) incident on a SPAD-based 3D camera leads to severe non-linear distortions (pileup) in the measured waveform, resulting in large depth errors. We propose asynchronous single-photon 3D imaging, a family of acquisition schemes to mitigate pileup during data acquisition itself. Asynchronous acquisition temporally misaligns SPAD measurement windows and the laser cycles through deterministically predefined or randomized offsets. Our key insight is that pileup distortions can be "averaged out" by choosing a sequence of offsets that span the entire depth range. We develop a generalized image formation model and perform theoretical analysis to explore the space of asynchronous acquisition schemes and design high-performance schemes. Our simulations and experiments demonstrate an improvement in depth accuracy of up to an order of magnitude as compared to the state-of-the-art, across a wide range of imaging scenarios, including those with high ambient flux.

Sizhuo Ma, Brandon M. Smith, Mohit Gupta

This paper presents novel techniques for recovering 3D dense scene flow, based on differential analysis of 4D light fields. The key enabling result is a per-ray linear equation, called the ray flow equation, that relates 3D scene flow to 4D light field gradients. The ray flow equation is invariant to 3D scene structure and applicable to a general class of scenes, but is under-constrained (3 unknowns per equation). Thus, additional constraints must be imposed to recover motion. We develop two families of scene flow algorithms by leveraging the structural similarity between ray flow and optical flow equations: local 'Lucas-Kanade' ray flow and global 'Horn-Schunck' ray flow, inspired by corresponding optical flow methods. We also develop a combined local-global method by utilizing the correspondence structure in the light fields. We demonstrate high precision 3D scene flow recovery for a wide range of scenarios, including rotation and non-rigid motion. We analyze the theoretical and practical performance limits of the proposed techniques via the light field structure tensor, a 3x3 matrix that encodes the local structure of light fields. We envision that the proposed analysis and algorithms will lead to design of future light-field cameras that are optimized for motion sensing, in addition to depth sensing.

Anant Gupta, Atul Ingle, Andreas Velten et al.

Single photon avalanche diodes (SPADs) are starting to play a pivotal role in the development of photon-efficient, long-range LiDAR systems. However, due to non-linearities in their image formation model, a high photon flux (e.g., due to strong sunlight) leads to distortion of the incident temporal waveform, and potentially, large depth errors. Operating SPADs in low flux regimes can mitigate these distortions, but, often requires attenuating the signal and thus, results in low signal-to-noise ratio. In this paper, we address the following basic question: what is the optimal photon flux that a SPAD-based LiDAR should be operated in? We derive a closed form expression for the optimal flux, which is quasi-depth-invariant, and depends on the ambient light strength. The optimal flux is lower than what a SPAD typically measures in real world scenarios, but surprisingly, considerably higher than what is conventionally suggested for avoiding distortions. We propose a simple, adaptive approach for achieving the optimal flux by attenuating incident flux based on an estimate of ambient light strength. Using extensive simulations and a hardware prototype, we show that the optimal flux criterion holds for several depth estimators, under a wide range of illumination conditions.

Atul Ingle, Andreas Velten, Mohit Gupta

Single-photon avalanche diodes (SPADs) are an emerging technology with a unique capability of capturing individual photons with high timing precision. SPADs are being used in several active imaging systems (e.g., fluorescence lifetime microscopy and LiDAR), albeit mostly limited to low photon flux settings. We propose passive free-running SPAD (PF-SPAD) imaging, an imaging modality that uses SPADs for capturing 2D intensity images with unprecedented dynamic range under ambient lighting, without any active light source. Our key observation is that the precise inter-photon timing measured by a SPAD can be used for estimating scene brightness under ambient lighting conditions, even for very bright scenes. We develop a theoretical model for PF-SPAD imaging, and derive a scene brightness estimator based on the average time of darkness between successive photons detected by a PF-SPAD pixel. Our key insight is that due to the stochastic nature of photon arrivals, this estimator does not suffer from a hard saturation limit. Coupled with high sensitivity at low flux, this enables a PF-SPAD pixel to measure a wide range of scene brightness, from very low to very high, thereby achieving extreme dynamic range. We demonstrate an improvement of over 2 orders of magnitude over conventional sensors by imaging scenes spanning a dynamic range of 1,000,000:1.

Jian Wang, Mohit Gupta, Aswin C. Sankaranarayanan

The measurement rate of cameras that take spatially multiplexed measurements by using spatial light modulators (SLM) is often limited by the switching speed of the SLMs. This is especially true for single-pixel cameras where the photodetector operates at a rate that is many orders-of-magnitude greater than the SLM. We study the factors that determine the measurement rate for such spatial multiplexing cameras (SMC) and show that increasing the number of pixels in the device improves the measurement rate, but there is an optimum number of pixels (typically, few thousands) beyond which the measurement rate does not increase. This motivates the design of LiSens, a novel imaging architecture, that replaces the photodetector in the single-pixel camera with a 1D linear array or a line-sensor. We illustrate the optical architecture underlying LiSens, build a prototype, and demonstrate results of a range of indoor and outdoor scenes. LiSens delivers on the promise of SMCs: imaging at a megapixel resolution, at video rate, using an inexpensive low-resolution sensor.