arXiv subjects

Ashish Kumar

Publications and source records attributed to Ashish Kumar.

At least 19 recordsLinked to original sources

arXiv2026

Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs

Data-driven software systems are increasingly deployed in high-stakes socio-economic domains, from criminal justice to financial lending. However, these systems often exhibit individual discrimination---unjustified disparities in which a program yields different outcomes for similar individuals who differ only in their protected attributes (e.g., race, gender, age). While existing research has focused on detecting and quantifying these bugs, there remains a critical lack of principled mechanisms to explain and localize individual fairness bugs. Current explanation techniques are largely designed for single-input decisions rather than the relational nature of discrimination, which inherently involves a comparison between an original and a counterfactual pair. We present REMI, a framework for the automated localization, explanation, and mitigation of individual discrimination. Inspired by loop-invariant synthesis in formal methods, we treat counterfactual fairness as a relational invariant discovery problem. We introduce a bidirectional relational explanation framework that learns over paired examples $(x, x')$ to identify regions of the input space where fairness is violated. Unlike traditional one-way implication pairs used in invariant inference, our approach enforces bidirectional constraints: requiring identical outcomes for both original and counterfactual samples. REMI utilizes three data-alignment techniques to infer interpretable rule-based models that act as "fairness invariants." These rules serve as guardrails to selectively block or relabel unfair predictions without requiring model retraining. Our evaluation on symbolic and neural network programs demonstrates that REMI localizes ground-truth fairness bugs in over 83% of cases, significantly outperforming state-of-the-art baselines and reducing discriminatory decisions in black-box models by up to 70%.

cs.SE↗

arXiv2026

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust

Extended Berkeley Packet Filter (eBPF) programs are kernel extensions used for networking, observability, and security enforcement in the Linux kernel. The in-kernel eBPF verifier checks low-level memory safety and termination on eBPF programs, but it does not enforce many higher-level source-level properties, such as initialization discipline, schema consistency, or error handling. We document nine classes of source-level bugs that compile, pass the kernel verifier, and can silently corrupt data, leak kernel memory to userspace, or yield incorrect enforcement outcomes. To harden such verifier-accepted buggy programs and support safe migration, we present Heimdall, an automated pipeline that uses large language models to translate legacy libbpf C programs to Aya Rust. Heimdall iteratively repairs compilation and kernel-verifier failures, rejects unsafe escape hatches in Rust-Aya with a static analysis safety engine, and proves per-program equivalence to the original via symbolic execution and Z3-based equivalence checking. Across 115 eBPF programs, Heimdall generates 109 formally proven-equivalent translations (94.8%). In the process, Heimdall identifies nine bugs in real-world eBPF programs and fixes all of them, two of which leak randomized kernel addresses to userspace and break KASLR. Eight of the nine have also been acknowledged and fixed upstream by the developers. Heimdall is the first system to automate memory-safe-language migration of production eBPF programs with per-program formal guarantees that the migration preserves observable behavior.

cs.CR↗

arXiv2026

Direct stroke measurement of Piezos for cavity frequency tuner of the ILC prototype cryomodule using a Laser Displacement Sensor

Piezoelectric actuators are critical for achieving high accelerating gradients and preventing RF trips in narrow-bandwidth superconducting radio-frequency (SRF) cavities by compensating for detuning caused by Lorentz force detuning. Depending on the maximum acceleration gradient an appropriate piezo stroke requirement has to be fulfilled. Since the stroke of piezo actuators decreases at cryogenic temperatures, evaluating their performance under such conditions is essential. Common characterization methods either use the SRF cavity itself as a sensor or rely on capacitance measurements during cool-down. Both these approaches do not measure the stroke directly and involve a trade-off between measurement precision and experimental simplicity, as well as cost and time. We developed a new method for the direct and precise measurement of piezo stroke at cryogenic temperature inside a cryocooler-cooled cryostat using a laser displacement sensor. The setup was used to characterize and evaluate two piezo actuators for cavity frequency tuners of the ILC prototype cryomodule, which is currently being built at KEK. In this article we are reporting on the development, setup, test, and application of this novel method, allowing the direct stroke measurement of piezos in vacuum and at cryogenic temperatures.

physics.acc-ph↗

arXiv2026

Probing the morphology of the Gum Nebula through pulsar observables and a novel distance estimation method

Various existing models of the Gum Nebula differ significantly in their parameters and suggested origins, which can be independently tested for consistency with data on some key observables of pulsars in the direction of the nebula. Our analysis of such data on the Vela pulsar, assuming a dominant scattering region in its foreground, suggests that the fractional distance of the scatterer is $0.89 \pm 0.01$, and for the given distance of the Vela pulsar, it translates to $254 \pm 16$ pc. Using independent distances of ten pulsars, we suggest a refined description of the Gum Nebula electron density model with its basic morphology similar to that used in the YMW16 model, which now provides better estimates of pulsar distances in these directions. In our new Gum Nebula model, as expected, the Vela pulsar would be behind the frontal edge of the Gum shell, which was intriguingly located in front of the nebula in the YMW16 model. We also present a new technique to better constrain the pulsar distances using their dispersion measure and temporal broadening simultaneously, and find that it is less affected by the uncertainties in the Galactic electron density distribution models. Notably, the new approach shows that the expected temporal broadening as a function of trial distance does not follow a monotonic increasing trend, but instead exhibits oscillations at regions of enhanced electron density. This behaviour is expected, as the method employs the integral form of temporal broadening with the appropriate weighting kernel, leading to more reliable estimates.

astro-ph.HE↗

arXiv2026

On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation

Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML algorithms may develop decision logic that disproportionately distributes opportunities, benefits, resources, or information among different population groups, potentially harming marginalized communities. In response to such fairness concerns, the software engineering and ML communities have made significant efforts to establish the best practices for creating fair ML software. These include fairness interventions for training ML models, such as including sensitive features, selecting non-sensitive attributes, and applying bias mitigators. But how reliably can software professionals tasked with developing data-driven systems depend on these recommendations? And how well do these practices generalize in the presence of faulty labels, missing data, or distribution shifts? These questions form the core theme of this paper.

cs.SE↗

arXiv2025

Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations

Fairness in algorithmic decision-making is often framed in terms of individual fairness, which requires that similar individuals receive similar outcomes. A system violates individual fairness if there exists a pair of inputs differing only in protected attributes (such as race or gender) that lead to significantly different outcomes-for example, one favorable and the other unfavorable. While this notion highlights isolated instances of unfairness, it fails to capture broader patterns of systematic or clustered discrimination that may affect entire subgroups. We introduce and motivate the concept of discrimination clustering, a generalization of individual fairness violations. Rather than detecting single counterfactual disparities, we seek to uncover regions of the input space where small perturbations in protected features lead to k-significantly distinct clusters of outcomes. That is, for a given input, we identify a local neighborhood-differing only in protected attributes-whose members' outputs separate into many distinct clusters. These clusters reveal significant arbitrariness in treatment solely based on protected attributes that help expose patterns of algorithmic bias that elude pairwise fairness checks. We present HyFair, a hybrid technique that combines formal symbolic analysis (via SMT and MILP solvers) to certify individual fairness with randomized search to discover discriminatory clusters. This combination enables both formal guarantees-when no counterexamples exist-and the detection of severe violations that are computationally challenging for symbolic methods alone. Given a set of inputs exhibiting high k-unfairness, we introduce a novel explanation method to generate interpretable, decision-tree-style artifacts. Our experiments demonstrate that HyFair outperforms state-of-the-art fairness verification and local explanation methods.

cs.SE↗

arXiv2025

Application of LLMs to Multi-Robot Path Planning and Task Allocation

Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to efficiently explore an environment to learn to solve tasks by multi-agent operating in that environment, of which, the idea of expert exploration is investigated in this work. More specifically, this work investigates the application of large-language models as expert planners for efficient exploration in planning based tasks for multiple agents.

cs.AI↗

arXiv2025

VLBA astrometry of PSRs B0329+54 and B1133+16: Improved pulsar distances and comparison of global ionospheric models

Very long baseline interferometry (VLBI) astrometry is used to determine the three-dimensional position and proper motion of astronomical objects. A typical VLBI astrometric campaign generally includes around ten observations, making it challenging to characterise systematic uncertainties. Our study on two bright pulsars, B0329+54 and B1133+16, involves analysis of broadband Very Long Baseline Array (VLBA) data over $\sim30$ epochs (spanning approximately $3.5\, {\rm years}$). This extended dataset has significantly improved the precision of the astrometric estimates of these pulsars. Our broadband study suggests that, as expected, the primary contribution to systematic uncertainties in L-band VLBI astrometry originates from the ionosphere. We have also assessed the effectiveness of the modified TEC (total electron content) mapping function, which converts vertical TEC to slant TEC, in correcting ionospheric dispersive delays using global TEC maps. The parallax and proper motion obtained from the multiple data sets, calibrated using the traditional and the modified TEC mapping functions, are consistent. However, the reduced chi-square values from least-squares fitting and precision of the fitted astrometric parameters show no significant improvement, and hence, the effectiveness of the new TEC mapping function on astrometry is unclear. For B0329+54, the refined parallax estimate is $0.611^{+0.013}_{-0.013}\, {\rm mas}$, with best-fit proper motion of $\mu_{\alpha} = 16.960^{+0.011}_{-0.010}\, {\rm mas\, yr^{-1}}$ in R.A. and and $\mu_{\delta} = -10.382^{+0.022}_{-0.022}\, {\rm mas\, yr^{-1}}$ in Dec. For B1133+16, the new estimated parallax is $2.705^{+0.009}_{-0.009}\, {\rm mas}$, with proper motions of $\mu_{\alpha} = -73.777^{+0.008}_{-0.008}\, {\rm mas\, yr^{-1}}$ and $\mu_{\delta} = 366.573^{+0.019}_{-0.019}\, {\rm mas\, yr^{-1}}$.

astro-ph.HE↗

arXiv2024

Probabilistic Guarantees for Practical LIA Loop Invariant Automation

Despite the crucial need for formal safety and security verification of programs, discovering loop invariants remains a significant challenge. Static analysis is a primary technique for inferring loop invariants but often relies on substantial assumptions about underlying theories. Data-driven methods supported by dynamic analysis and machine learning algorithms have shown impressive performance in inferring loop invariants for some challenging programs. However, state-of-the-art data-driven techniques do not offer theoretical guarantees for finding loop invariants. We present a novel technique that leverages the simulated annealing (SA) search algorithm combined with SMT solvers and computational geometry to provide probabilistic guarantees for inferring loop invariants using data-driven methods. Our approach enhances the SA search with real analysis to define the search space and employs parallelism to increase the probability of success. To ensure the convergence of our algorithm, we adapt e-nets, a key concept from computational geometry. Our tool, DLIA2, implements these algorithms and demonstrates competitive performance against state-of-the-art techniques. We also identify a subclass of programs, on which we outperform the current state-of-the-art tool GSpacer.

cs.PL↗

arXiv2024

Thrust Microstepping via Acceleration Feedback in Quadrotor Control for Aerial Grasping of Dynamic Payload

In this work, we propose an end-to-end Thrust Microstepping and Decoupled Control (TMDC) of quadrotors. TMDC focuses on precise off-centered aerial grasping of payloads dynamically, which are attached rigidly to the UAV body via a gripper contrary to the swinging payload. The dynamic payload grasping quickly changes UAV's mass, inertia etc, causing instability while performing a grasping operation in-air. We identify that to handle unknown payload grasping, the role of thrust controller is crucial. Hence, we focus on thrust control without involving system parameters such as mass etc. TMDC is based on our novel Thrust Microstepping via Acceleration Feedback (TMAF) thrust controller and Decoupled Motion Control (DMC). TMAF precisely estimates the desired thrust even at smaller loop rates while DMC decouples the horizontal and vertical motion to counteract disturbances in the case of dynamic payloads. We prove the controller's efficacy via exhaustive experiments in practically interesting and adverse real-world cases, such as fully onboard state estimation without any positioning sensor, narrow and indoor flying workspaces with intense wind turbulence, heavy payloads, non-uniform loop rates, etc. Our TMDC outperforms recent direct acceleration feedback thrust controller (DA) and geometric tracking control (GT) in flying stably for aerial grasping and achieves RMSE below 0.04m in contrast to 0.15m of DA and 0.16m of GT.

cs.RO↗

arXiv2024

Design, Localization, Perception, and Control for GPS-Denied Autonomous Aerial Grasping and Harvesting

In this paper, we present a comprehensive UAV system design to perform the highly complex task of off-centered aerial grasping. This task has several interdisciplinary research challenges which need to be addressed at once. The main design challenges are GPS-denied functionality, solely onboard computing, and avoiding off-the-shelf costly positioning systems. While in terms of algorithms, visual perception, localization, control, and grasping are the leading research problems. Hence in this paper, we make interdisciplinary contributions: (i) A detailed description of the fundamental challenges in indoor aerial grasping, (ii) a novel lightweight gripper design, (iii) a complete aerial platform design and in-lab fabrication, and (iv) localization, perception, control, grasping systems, and an end-to-end flight autonomy state-machine. Finally, we demonstrate the resulting aerial grasping system Drone-Bee achieving a high grasping rate for a highly challenging agricultural task of apple-like fruit harvesting, indoors in a vertical farming setting (Fig. 1). To our knowledge, such a system has not been previously discussed in the literature, and with its capabilities, this system pushes aerial manipulation towards 4th generation.

cs.RO↗

arXiv2024

Cross Resolution Encoding-Decoding For Detection Transformers

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism that allows DETR to achieve the accuracy of high-resolution detection while having the speed of low-resolution detection. CRED is based on two modules; Cross Resolution Attention Module (CRAM) and One Step Multiscale Attention (OSMA). CRAM is designed to transfer the knowledge of low-resolution encoder output to a high-resolution feature. While OSMA is designed to fuse multiscale features in a single step and produce a feature map of a desired resolution enriched with multiscale information. When used in prominent DETR methods, CRED delivers accuracy similar to the high-resolution DETR counterpart in roughly 50% fewer FLOPs. Specifically, state-of-the-art DN-DETR, when used with CRED (calling CRED-DETR), becomes 76% faster, with ~50% reduced FLOPs than its high-resolution counterpart with 202 G FLOPs on MS-COCO benchmark. We plan to release pretrained CRED-DETRs for use by the community. Code: https://github.com/ashishkumar822/CRED-DETR

cs.CV↗

arXiv2024

Designing Concise ConvNets with Columnar Stages

In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainly focus on runtime, it is also crucial to simultaneously focus on other aspects, e.g., FLOPs, parameters, etc, to strengthen their utility further. To this end, we introduce a refreshing ConvNet macro design called Columnar Stage Network (CoSNet). CoSNet has a systematically developed simple and concise structure, smaller depth, low parameter count, low FLOPs, and attention-less operations, well suited for resource-constrained deployment. The key novelty of CoSNet is deploying parallel convolutions with fewer kernels fed by input replication, using columnar stacking of these convolutions, and minimizing the use of 1x1 convolution layers. Our comprehensive evaluations show that CoSNet rivals many renowned ConvNets and Transformer designs under resource-constrained scenarios. Code: https://github.com/ashishkumar822/CoSNet

cs.CV↗

arXiv2024

High-Speed Stereo Visual SLAM for Low-Powered Computing Devices

We present an accurate and GPU-accelerated Stereo Visual SLAM design called Jetson-SLAM. It exhibits frame-processing rates above 60FPS on NVIDIA's low-powered 10W Jetson-NX embedded computer and above 200FPS on desktop-grade 200W GPUs, even in stereo configuration and in the multiscale setting. Our contributions are threefold: (i) a Bounded Rectification technique to prevent tagging many non-corner points as a corner in FAST detection, improving SLAM accuracy. (ii) A novel Pyramidal Culling and Aggregation (PyCA) technique that yields robust features while suppressing redundant ones at high speeds by harnessing a GPU device. PyCA uses our new Multi-Location Per Thread culling strategy (MLPT) and Thread-Efficient Warp-Allocation (TEWA) scheme for GPU to enable Jetson-SLAM achieving high accuracy and speed on embedded devices. (iii) Jetson-SLAM library achieves resource efficiency by having a data-sharing mechanism. Our experiments on three challenging datasets: KITTI, EuRoC, and KAIST-VIO, and two highly accurate SLAM backends: Full-BA and ICE-BA show that Jetson-SLAM is the fastest available accurate and GPU-accelerated SLAM system (Fig. 1).

cs.RO↗

arXiv2024

Modeling Text-Label Alignment for Hierarchical Text Classification

Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics of the text should align with the semantics of the labels in this sub-hierarchy. With the sub-hierarchy changing for each sample, the dynamic nature of text-label alignment poses challenges for existing methods, which typically process text and labels independently. To overcome this limitation, we propose a Text-Label Alignment (TLA) loss specifically designed to model the alignment between text and labels. We obtain a set of negative labels for a given text and its positive label set. By leveraging contrastive learning, the TLA loss pulls the text closer to its positive label and pushes it away from its negative label in the embedding space. This process aligns text representations with related labels while distancing them from unrelated ones. Building upon this framework, we introduce the Hierarchical Text-Label Alignment (HTLA) model, which leverages BERT as the text encoder and GPTrans as the graph encoder and integrates text-label embeddings to generate hierarchy-aware representations. Experimental results on benchmark datasets and comparison with existing baselines demonstrate the effectiveness of HTLA for HTC.

cs.CL↗

arXiv2024

NeuFair: Neural Network Fairness Repair with Dropout

This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications. While neural networks are exceptionally good at finding statistical patterns from data, they may encode and amplify existing biases from the historical data. Existing bias mitigation algorithms often require modifying the input dataset or the learning algorithms. We posit that the prevalent dropout methods that prevent over-fitting during training by randomly dropping neurons may be an effective and less intrusive approach to improve the fairness of pre-trained DNNs. However, finding the ideal set of neurons to drop is a combinatorial problem. We propose NeuFair, a family of post-processing randomized algorithms that mitigate unfairness in pre-trained DNNs via dropouts during inference after training. Our randomized search is guided by an objective to minimize discrimination while maintaining the model's utility. We show that our design of randomized algorithms is effective and efficient in improving fairness (up to 69%) with minimal or no model performance degradation. We provide intuitive explanations of these phenomena and carefully examine the influence of various hyperparameters of search algorithms on the results. Finally, we empirically and conceptually compare NeuFair to different state-of-the-art bias mitigators.

cs.LG↗

arXiv2024

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

Channel pruning approaches for convolutional neural networks (ConvNets) deactivate the channels, statically or dynamically, and require special implementation. In addition, channel squeezing in representative ConvNets is carried out via 1x1 convolutions which dominates a large portion of computations and network parameters. Given these challenges, we propose an effective multi-purpose module for dynamic channel sampling, namely Pick-or-Mix (PiX), which does not require special implementation. PiX divides a set of channels into subsets and then picks from them, where the picking decision is dynamically made per each pixel based on the input activations. We plug PiX into prominent ConvNet architectures and verify its multi-purpose utilities. After replacing 1x1 channel squeezing layers in ResNet with PiX, the network becomes 25% faster without losing accuracy. We show that PiX allows ConvNets to learn better data representation than widely adopted approaches to enhance networks' representation power (e.g., SE, CBAM, AFF, SKNet, and DWP). We also show that PiX achieves state-of-the-art performance on network downscaling and dynamic channel pruning applications.

cs.CV↗

arXiv2024

High-Speed Detector For Low-Powered Devices In Aerial Grasping

Autonomous aerial harvesting is a highly complex problem because it requires numerous interdisciplinary algorithms to be executed on mini low-powered computing devices. Object detection is one such algorithm that is compute-hungry. In this context, we make the following contributions: (i) Fast Fruit Detector (FFD), a resource-efficient, single-stage, and postprocessing-free object detector based on our novel latent object representation (LOR) module, query assignment, and prediction strategy. FFD achieves 100FPS@FP32 precision on the latest 10W NVIDIA Jetson-NX embedded device while co-existing with other time-critical sub-systems such as control, grasping, SLAM, a major achievement of this work. (ii) a method to generate vast amounts of training data without exhaustive manual labelling of fruit images since they consist of a large number of instances, which increases the labelling cost and time. (iii) an open-source fruit detection dataset having plenty of very small-sized instances that are difficult to detect. Our exhaustive evaluations on our and MinneApple dataset show that FFD, being only a single-scale detector, is more accurate than many representative detectors, e.g. FFD is better than single-scale Faster-RCNN by 10.7AP, multi-scale Faster-RCNN by 2.3AP, and better than latest single-scale YOLO-v8 by 8AP and multi-scale YOLO-v8 by 0.3 while being considerably faster.

cs.CV↗