arXiv subjects

Shubham Singh

Publications and source records attributed to Shubham Singh.

At least 19 recordsLinked to original sources

arXiv2026

Safe Circumnavigation on Heterogeneous Orbits: A Range-Only HOCBF-QP Framework for Nonholonomic Multi-Agent Systems

Circumnavigating a stationary target with a team of robots requires each robot to hold its own standoff distance, to stay evenly spaced from its neighbours, and to avoid collisions with the target and with each other at every instant. The task becomes arduous when the robots are assigned different orbital radii, as their sensors or roles may demand. This paper presents a safety-critical control framework for this problem. Each robot commands both its acceleration and its turn-rate, measures only its distance to the target, and exchanges information only with its two ring neighbours. The design has three features. First, a structural property of the model lets one control law serve every robot regardless of its assigned radius. Second, the acceleration drives each radius exactly to its target, while the turn-rate balances the formation with the neighbours. Third, a higher-order control-barrier-function quadratic program enforces target, geofence, and inter-robot safety on both inputs at once; it leaves the nominal controller untouched away from the constraints and stays valid while the unmeasured range rate is still being estimated. Simulations confirm these guarantees. In a comparison, the closest existing multi-orbit design, even with full state information, violates both the target standoff and the inter-robot margin, whereas the proposed controller does not.

cs.RO↗

arXiv2026

Safe Unicycle Navigation Among Multiple Obstacles Under Bounded Disturbances: A Learning-Augmented CLF-CBF Approach (Extended Version)

This paper presents a robust control framework for safe navigation of a unicycle robot to a goal among multiple static obstacles under an unknown, time-varying disturbance. The controller solves a single real-time quadratic program (QP) that combines a goal-reaching term with one safety term per obstacle. The goal-reaching term is a cross-track control Lyapunov function built from body-frame tracking errors rather than a bearing angle, which keeps its Lie derivatives bounded everywhere, including the goal. Safety is encoded using robust control barrier functions, one per obstacle, each tightened by a closed-form, state-dependent disturbance bound. When stabilization and safety conflict, a slack variable relaxes only the convergence requirement, so that the safety constraints remain strictly enforced. Whenever the QP is feasible, the robust barrier constraints guarantee forward invariance of every obstacle's safe set under all admissible disturbances. Complementing this safety guarantee, a Lyapunov analysis yields an explicit ultimate bound on the distance to the goal. A learning-augmented variant replaces the fixed objective with a reinforcement-learning reference, which accelerates convergence when multiple constraints are simultaneously active. We further derive the obstacle separation below which the gap between two obstacles becomes too narrow to pass through under the robust constraints. For such gaps, a learned virtual goal for the Lyapunov function steers the robot around the obstacles without compromising safety. Simulations, a Monte Carlo study, and a comparison against a sampled-data robust baseline support the theoretical results.

eess.SY↗

arXiv2026

Full-Weight VLA Fine-Tuning Without an fp32 Master Copy Silently Erases Most Updates

When a vision-language-action (VLA) model is fine-tuned with its trainable weights in bfloat16 (bf16) and no fp32 master copy, AdamW writes each update straight into bf16, silently rounding away any update smaller than 1/512 of a weight. In 9 of 12 open VLA codebases a default or documented recipe trains this way, 4 on full weight matrices, including LeRobot's SmolVLA default and its $π_0$/$π_{0.5}$ guides. In our LIBERO runs without the copy, a probe every 100 steps finds at least 79% of updates to bf16 weights erased. On the Hugging Face Hub, 99% of sampled full-weight SmolVLA fine-tunes store the action expert in bf16, and 84% of recent $π_{0.5}$ fine-tunes with a training configuration set the bf16 flag. On LIBERO-Object, with rules fixed in advance, an fp32 copy raises success over LeRobot's storage from 4.3% to 49.3% for SmolVLA and from 5.1% to 80.9% for $π_{0.5}$ at a ten-times lower learning rate, where both models are undertrained, and from 89.0% to 97.7% for $π_{0.5}$ at its default rate. For SmolVLA at its default rate it adds 10.2 points with open-loop 50-action chunks but only 4.2 when re-planning every 10 actions. In these five comparisons and two more against SmolVLA with every trainable weight in bf16, every run with the copy beats every run without it (p < 0.05); all gaps but the 8.7- and 4.2-point ones clear our 10-point threshold. The fix is to keep the trainable weights in fp32 during training, a one-line change for SmolVLA in LeRobot.

cs.RO↗

arXiv2026

Enforcing a Strict Safety Margin in LLM Text Generation via Barrier Lyapunov Control

Large language models are increasingly deployed without formal guarantees against toxic text generation. Existing control barrier function (CBF) based safety filters can keep the generation trajectory within a toxicity-free region, but do not enforce a positive distance from its boundary, allowing formally safe trajectories to approach the toxicity threshold arbitrarily closely and leaving little buffer against modelling errors or disturbances. We address this limitation with a Barrier Lyapunov Function (BLF) safety filter that enforces a prescribed clearance margin throughout generation while retaining the continuous-time transformer dynamics, including feedforward layers. The resulting safe input set is a half-space defined by a constraint affine in the control input, and is non-empty under certified surjectivity and classifier-nondegeneracy conditions. For margin-compatible initial conditions we prove that the clearance margin is never violated and that the prescribed clearance is restored exponentially, yielding an explicit clearance floor, and show that, as the margin vanishes, the admissible trajectories satisfy the exponential second-order CBF condition. We further derive an explicitly computable sufficient disturbance budget under which the clearance guarantee degrades gracefully. Simulations on a small transformer illustrate the resulting improvement in safety clearance.

eess.SY↗

arXiv2026

Non-Hermitian Purcell Physics in Dissipatively Coupled Planar Photon-Magnon Systems

The Purcell effect has emerged as a powerful mechanism for controlling spontaneous emission and dissipation in cavity and nanophotonic systems; however, its realization in dissipative non-Hermitian hybrid platforms remains largely unexplored. In this work, we investigate the Purcell effect in a dissipatively coupled photon-magnon hybrid quantum system consisting of a yttrium iron garnet (YIG) thin film integrated with an inverted octa-ring resonator (IORR) in a planar geometry. To describe the underlying dissipative hybrid dynamics, we develop a quantum theoretical framework based on non-Hermitian coupled-mode theory combined with the input-output formalism. We also analyze the temporal decay dynamics of the photon-magnon system. Full-wave electromagnetic simulations demonstrate that the system can be engineered to operate in the level-attraction regime through dissipative photon-magnon coupling. By systematically tuning the magnon damping, we uncover the emergence of a Purcell regime in which cavity-photon dissipation is selectively enhanced through magnon-mediated loss channels. We further show that the saturation magnetization (Ms) provides an additional degree of control over the onset, tunability, and robustness of the Purcell enhancement. The combined modulation of magnon damping and Ms strongly influences the effective photon-magnon coupling, hybrid-mode evolution, and dissipation landscape, enabling precise control of hybrid quantum states. These findings establish a versatile strategy for engineering magnetization- and dissipation-controlled photon-magnon interactions in planar, chip-compatible architectures, opening new avenues for non-Hermitian cavity magnonics, tunable microwave dissipation engineering, and hybrid quantum information technologies.

quant-ph↗

arXiv2026

When Recursive Models Finish Computing

Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the dynamics of completion in attention- and MLP-based Tiny Recursive Models (TRMs) on 1,000 hard Sudoku puzzles. Extending recurrence from the nominal 16 steps to 512 steps increases cumulative exact-solve accuracy from 59.2% to 87.5% for the attention model and from 74.4% to 91.9% for the MLP model, solving more than two-thirds of the puzzles unsolved in the nominal budget. Across both architectures, latent-state motion drops sharply after the first exact solution. Completed states are typically locally contractive along the trajectory direction, even though the same local Jacobian retains strongly expanding directions. We characterize this phenomenon as trajectory-conditioned anisotropic stability. Perturbation experiments confirm this directional stability across both models. The multi-step fate of the maximally expanding direction differs: it is absorbed within 16 steps in the attention model but persists longer in the MLP model. The anisotropic-stability pattern also holds for a second attention checkpoint. Together, these results distinguish nominal-budget failure from completed computation and identify a common dynamical signature of completion across two recurrent architectures.

cs.LG↗

arXiv2026

Phase-Coordinated Circular Formation Control of Unicycle Agents Under Non-Concentric Boundary Constraints

This paper addresses the problem of collective circular motion control for unicycle agents, with the objective of achieving phase coordination of their velocity vectors while ensuring that their trajectories remain confined within a prescribed non-concentric circular boundary. To accommodate such nonuniform motion constraints, we build upon our earlier work and extend the use of Mobius transformation to a multi-agent framework. The Mobius transformation maps two nonconcentric circles to concentric ones, thereby converting spatially nonuniform constraints into uniform ones in the transformed plane. Leveraging this property, we introduce the notion of a phase-shifted order parameter, along with the associated concepts of Mobius phase-shift coupled synchronization and balancing, which characterize the phase-coordinated patterns studied in this paper. We establish an equivalence between the unicycle dynamics in the original and transformed planes under the Mobius transformation and its inverse, and show that synchronization is preserved across both planes, whereas balancing is generally not. Distributed control laws are then designed in the transformed plane using barrier Lyapunov functions, under the assumption of an undirected and connected communication topology among agents. These controllers are subsequently mapped back to the original plane to obtain the linear acceleration and turn-rate control inputs applied to the actual agents. Both simulations and experimental results are provided to illustrate the proposed framework.

eess.SY↗

arXiv2026

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult to differentiate models and diminishing their long-term value. In this study, we define benchmark saturation and analyze it across 60 language model benchmarks using 14 properties that relate to saturation. We find that nearly half of our benchmarks exhibit saturation, with rates increasing with age. Further, we find that resilience to saturation is impacted by expert-curation, not by public test data. Our results suggest that design choices can extend benchmark longevity and inform more durable evaluation approaches.

cs.AI↗

arXiv2026

Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking

Scoring functions are used to represent the relevance of individual documents. In modern information retrieval or recommendation systems, they are often learned from data and play a pivotal role in ranking sets of documents or items in a way that maximizes utility to a query or user. With the recent interest in algorithmic fairness, the success of scoring has naturally led to methods that learn scores that simultaneously trade off fairness and utility. In this work, we show that in stark contrast with utility-centric objectives, scoring is sub-optimal in achieving all utility-fairness trade-offs. We establish this with a series of counter-examples with a generic fairness formulation. We show that the issue persists whether we have a deterministic scoring function or a randomized one, or whether we measure fairness at the scope of a single query or across multiple queries. On the positive side, we empirically demonstrate that semi-greedy post-processing has the potential to achieve much better trade-offs, often approaching the ideal of exhaustive post-processing in a tractable way.

cs.IR↗

arXiv2026

Multi-Robot Navigation in Social Mini-Games: Definitions, Taxonomy, and Algorithms

The "Last Mile Challenge" has long been considered an important, yet unsolved, challenge for autonomous vehicles, public service robots, and delivery robots. A central issue in this challenge is the ability of robots to navigate constrained and cluttered environments that have high agency (e.g., doorways, hallways, corridor intersections), often while competing for space with other robots and humans. We refer to these environments as "Social Mini-Games" (SMGs). Traditional navigation approaches designed for MRN do not perform well in SMGs, which has led to focused research on dedicated SMG solvers. However, publications on SMG navigation research make different assumptions, and have different objective functions (safety versus liveness). These assumptions and objectives are sometimes implicitly assumed or described informally. This makes it difficult to establish appropriate baselines for comparison in research papers, as well as making it difficult for practitioners to find the papers relevant to their concrete application. Such ad-hoc representation of the field also presents a barrier to new researchers wanting to start research in this area. SMG navigation research requires its own taxonomy, definitions, and evaluation protocols to guide effective research moving forward. This survey is the first to catalog SMG solvers using a well-defined and unified taxonomy and to classify existing methods accordingly. It also discusses the essential properties of SMG solvers, defines what SMGs are and how they appear in practice, outlines how to evaluate SMG solvers, and highlights the differences between SMG solvers and general navigation systems. The survey concludes with an overview of future directions and open challenges in the field. Our project is open-sourced at https://socialminigames.github.io/{https://socialminigames.github.io/.

cs.RO↗

arXiv2026

Quantum Computing Inspired Approach for Self-Avoiding Walk (SAWs): 2D lattice and 3D lattice SAWs for single chain enumeration

We investigate the application of quantum computing algorithms to enhance the efficiency of enumerating self-avoiding walks (SAWs), utilizing quantum properties such as superposition and interference. A Quantum Amplitude Estimation (QAE)-based algorithm is developed to enumerate SAWs on both 2D and 3D lattices. In case of 2D square lattice, SAWs up to N=71 steps are successfully enumerated within 26.9 minutes - significantly improving upon the classical algorithm, which required approximately 231 hours(Jensen et al., 2012, J. Phys. A: Math. Theor. 45, 115202). The algorithm is further extended to 3D cubic lattices, where SAWs up to N=40 steps are enumerated in 13.06 minutes, compared to the classical result of N=36 in 250 hours (Schram et al., 2011, J. Stat. Mech. P06019). These results demonstrate a substantial reduction in computational time, highlighting the potential of quantum computing for combinatorial enumeration problems.

cond-mat.stat-mech↗

arXiv2025

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies such as refusal rates, G-Eval scores, and toxicity classifiers, all of which have critical blind spots. Aligned models are often vulnerable to jailbreaking, stochasticity of generation, and alignment faking. To address this issue, we introduce the Alignment Quality Index (AQI). This novel geometric and prompt-invariant metric empirically assesses LLM alignment by analyzing the separation of safe and unsafe activations in latent space. By combining measures such as the Davies-Bouldin Score (DBS), Dunn Index (DI), Xie-Beni Index (XBI), and Calinski-Harabasz Index (CHI) across various formulations, AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant. AQI also serves as an early warning signal for alignment faking, offering a robust, decoding invariant tool for behavior agnostic safety auditing. Additionally, we propose the LITMUS dataset to facilitate robust evaluation under these challenging conditions. Empirical tests on LITMUS across different models trained under DPO, GRPO, and RLHF conditions demonstrate AQI's correlation with external judges and ability to reveal vulnerabilities missed by refusal metrics. We make our implementation publicly available to foster future research in this area.

cs.CL↗

arXiv2025

Towards Machine Unlearning for Paralinguistic Speech Processing

In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we propose, SISA++, a novel extension to previous state-of-the-art (SOTA) MU method, SISA by merging models trained on different shards with weight-averaging. With such modifications, we show that SISA++ preserves performance more in comparison to SISA after unlearning in benchmark SER (CREMA-D) and DD (E-DAIC) datasets. Also, to guide future research for easier adoption of MU for PSP, we present ``cookbook recipes'' - actionable recommendations for selecting optimal feature representations and downstream architectures that can mitigate performance degradation after the unlearning process.

eess.AS↗

arXiv2025

Phasing Through the Flames: Rapid Motion Planning with the AGHF PDE for Arbitrary Objective Functions and Constraints

The generation of optimal trajectories for high-dimensional robotic systems under constraints remains computationally challenging due to the need to simultaneously satisfy dynamic feasibility, input limits, and task-specific objectives while searching over high-dimensional spaces. Recent approaches using the Affine Geometric Heat Flow (AGHF) Partial Differential Equation (PDE) have demonstrated promising results, generating dynamically feasible trajectories for complex systems like the Digit V3 humanoid within seconds. These methods efficiently solve trajectory optimization problems over a two-dimensional domain by evolving an initial trajectory to minimize control effort. However, these AGHF approaches are limited to a single type of optimal control problem (i.e., minimizing the integral of squared control norms) and typically require initial guesses that satisfy constraints to ensure satisfactory convergence. These limitations restrict the potential utility of the AGHF PDE especially when trying to synthesize trajectories for robotic systems. This paper generalizes the AGHF formulation to accommodate arbitrary cost functions, significantly expanding the classes of trajectories that can be generated. This work also introduces a Phase1 - Phase 2 Algorithm that enables the use of constraint-violating initial guesses while guaranteeing satisfactory convergence. The effectiveness of the proposed method is demonstrated through comparative evaluations against state-of-the-art techniques across various dynamical systems and challenging trajectory generation problems. Project Page: https://roahmlab.github.io/BLAZE/

cs.RO↗

arXiv2024

Avengers Assemble: Amalgamation of Non-Semantic Features for Depression Detection

In this study, we address the challenge of depression detection from speech, focusing on the potential of non-semantic features (NSFs) to capture subtle markers of depression. While prior research has leveraged various features for this task, NSFs-extracted from pre-trained models (PTMs) designed for non-semantic tasks such as paralinguistic speech processing (TRILLsson), speaker recognition (x-vector), and emotion recognition (emoHuBERT)-have shown significant promise. However, the potential of combining these diverse features has not been fully explored. In this work, we demonstrate that the amalgamation of NSFs results in complementary behavior, leading to enhanced depression detection performance. Furthermore, to our end, we introduce a simple novel framework, FuSeR, designed to effectively combine these features. Our results show that FuSeR outperforms models utilizing individual NSFs as well as baseline fusion techniques and obtains state-of-the-art (SOTA) performance in E-DAIC benchmark with RMSE of 5.51 and MAE of 4.48, establishing it as a robust approach for depression detection.

eess.AS↗

arXiv2024

Towards identifying Source credibility on Information Leakage in Digital Gadget Market

The use of Social media to share content is on a constant rise. One of the capsize effect of information sharing on Social media includes the spread of sensitive information on the public domain. With the digital gadget market becoming highly competitive and ever-evolving, the trend of an increasing number of sensitive posts leaking information on devices in social media is observed. Many web-blogs on digital gadget market have mushroomed recently, making the problem of information leak all pervasive. Credible leaks on specifics of an upcoming device can cause a lot of financial damage to the respective organization. Hence, it is crucial to assess the credibility of the platforms that continuously post about a smartphone or digital gadget leaks. In this work, we analyze the headlines of leak web-blog posts and their corresponding official press-release. We first collect 54, 495 leak and press-release headlines for different smartphones. We train our custom NER model to capture the evolving smartphone names with an accuracy of 82.14% on manually annotated results. We further propose a credibility score metric for the web-blog, based on the number of falsified and authentic smartphone leak posts.

cs.CR↗

arXiv2024

KAN based Autoencoders for Factor Models

Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we introduce a novel approach to latent factor conditional asset pricing models. While previous machine learning applications in asset pricing have predominantly used Multilayer Perceptrons with ReLU activation functions to model latent factor exposures, our method introduces a KAN-based autoencoder which surpasses MLP models in both accuracy and interpretability. Our model offers enhanced flexibility in approximating exposures as nonlinear functions of asset characteristics, while simultaneously providing users with an intuitive framework for interpreting latent factors. Empirical backtesting demonstrates our model's superior ability to explain cross-sectional risk exposures. Moreover, long-short portfolios constructed using our model's predictions achieve higher Sharpe ratios, highlighting its practical value in investment management.

cs.LG↗

arXiv2024

BrainVoxGen: Deep learning framework for synthesis of Ultrasound to MRI

The work proposes a novel deep-learning framework for the synthesis of three-dimensional MRI volumes from corresponding 3D ultrasound images of the brain, leveraging a modified iteration of the Pix2Pix Generative Adversarial Network (GAN) model. Addressing the formidable challenge of bridging the modality disparity between ultrasound and MRI, this research holds promise for transformative applications in medical diagnostics and treatment planning within the neuroimaging domain. While the findings reveal a discernible degree of similarity between the synthesized MRI volumes and anticipated outcomes, they fall short of practical deployment standards, primarily due to constraints associated with dataset scale and computational resources. The methodology yields MRI volumes with a satisfactory similarity score, establishing a foundational benchmark for subsequent investigations.

eess.IV↗