Searcharxiv⌕ Search

arXiv subjects

Saurabh Kumar

Publications and source records attributed to Saurabh Kumar.

At least 19 recordsLinked to original sources

Simultaneous tests of post-Newtonian inspiral using GW250114 and GW250207

We perform the one of the most general tests of post-Newtonian (PN) inspiral in binary black holes to date by allowing all eight phase coefficients up to 3.5PN order to vary simultaneously from their general-relativistic values. Using two of the loudest binary black hole events observed to date, GW250114 and GW250207, we carry out Bayesian inference with the IMRPhenomXPHM_SpinTaylor waveform model augmented by parametrized deviations in the post-Newtonian phasing. We then identify the combinations of phase coefficients most strongly constrained by the data through a principal component analysis of the eight-dimensional deformation space. We find that the data constrain the three leading principal components beyond their priors, and that all three are consistent with the predictions of general relativity. These results demonstrate that exceptionally loud gravitational-wave events enable robust, high-dimensional tests of inspiral dynamics and provide direct access to the measurable subspace of post-Newtonian deformations.

gr-qc↗

What Does It Cost to Force-Close a Lightning Channel? Evidence from 974,000 Channel Closes, 2018-2026

Bitcoin's Lightning payment network returns the funds of a channel that cannot close cooperatively through pre-signed transactions whose fees and delays fall on its operators. That fee design is being replaced: Bitcoin Core 31.0 removed the mempool rule anchor channels relied on, and the Lightning specification adopted zero-fee commitments in May 2026. What the old design costs has never been measured across fee regimes. We trace every public channel close and every force close on-chain from January 2018 to October 2026, 973,581 closes, and follow each output to its spend. A separate chain index confirms all 698,476 public closes we could compare. Fee spikes did not bring a wave of force closes. Force closes in a spike week and the next were 0.97 times the four weeks before, against 1.02 after ordinary weeks of the same years. A force close costs 2-6 times a cooperative close in fees and locks the closer's balance for days, which outweighs the fees only in low-fee years. When fees are high, pending payments are exposed: in 2023, 18.2% of HTLC timeouts confirmed more than 40 blocks after expiry. Yet since 2021, forwarding nodes lost only 38 payments, each with the preimage already on-chain. Anchor outputs cut late timeouts in fee spikes (20.6% against 30.5%), yet owners rarely bump commitments with them, and miners take most of what third parties sweep. Zero-fee commitments would save only 12% of the anchor mechanism's block space; they should be judged by how promptly payments resolve when fees spike.

cs.CR↗

Admissibility-Preserving Control for Block Strict-Feedback Systems Under Time-Varying Asymmetric Actuator and State Constraints

This paper addresses the tracking control of block strict-feedback nonlinear systems subject to time-varying asymmetric actuator and full state constraints. To that end, we develop a time-varying Admissibility-Preserving Control (APC) framework, in which the Admissibility-Preserving Input Realization (APIR) generates the plant input through a dynamic realization. The APIR guarantees input admissibility under the moving actuator set whenever each actuator bound contracts slower than the decay rate of the realization, and a closed-form lower bound on its gain is derived. The state constraints are handled by a logarithmic barrier coordinate at every backstepping step, with widths measured from the virtual control to the moving envelope of the corresponding state. We prove that every state lies inside its envelope, with each virtual control only required to remain inside the envelope of the next state, while the tracking error converges to zero exponentially. Simulations demonstrate the efficacy of the proposed safety-critical control scheme.

eess.SY↗

A Unified Framework for License Plate Identification and Character-Recognition

This paper presents a unified framework for license plate detection and character recognition on low-power edge hardware. The proposed network uses a shared CSP-Darknet and PANet feature encoder with an anchor-free localization head and a RoIAlign-based sequence-recognition branch. Character decoding is performed directly on aligned feature maps, avoiding image-space plate cropping and a second recognition backbone. The model is trained on an AI-assisted dataset of approximately 37,000 manually verified images covering license plate layouts from all 50 United States. The dataset includes variations in illumination, viewpoint, weather, blur, occlusion, and plate design. The framework is converted to an INT8 TensorRT engine and evaluated on an NVIDIA Jetson Orin Nano with 8 GB memory. The INT8 model shows an mAP50 of 97.8% and a full-sequence accuracy of 90.7%. It records 147 FPS at 6.8 ms end-to-end latency, with 315 MB inference memory and 9.4 W average power consumption. Relative to the YOLOv8s+CRNN baseline, the proposed deployment provides a 7.1x throughput increase and a 77.8% reduction in allocated inference memory

cs.LG↗

Multi-Node Transformers for Object Detection and Captioning Across Distributed Edge Networks

This paper presents a unified transformer-based framework for object detection and dense region captioning across distributed edge networks. The architecture uses a shared visual encoder followed by detection, region extraction, and autoregressive language-decoding stages, allowing localization and region description to reuse the same image features. This design removes the second image-encoding path required by decoupled detection and captioning pipelines. To support execution on resource-limited devices, a workload-allocation formulation assigns model stages and input streams across connected edge nodes while accounting for execution time, memory capacity, processor utilization, power limits, and intermediate tensor transfer cost. The framework is evaluated on a six-device edge testbed comprising four NVIDIA Jetson Orin Nano and Orin NX inference nodes and two Raspberry Pi 5 auxiliary CPU nodes, with TensorRT FP16 and INT8 execution on the NVIDIA devices. On a Jetson Orin Nano, the unified INT8 model achieves 38.1 FPS with 3.5 GB peak memory use and 11.8 W measured power. Under four concurrent streams, the proposed allocation achieves 35.2 FPS and 28.4 ms mean end-to-end latency with an internode transfer rate of 6.8 MB/s.

cs.DC↗

Does Client Diversity Protect the Lightning Network? Evidence from the 2026 Core Lightning Shutdown

Client diversity is often cited as the Lightning Network's defence against a bug in any one implementation, yet LND runs 80% of public nodes (84% counting one operator's fleet of about 2,000 tiny nodes) and holds 84% of public channel capacity, a capacity share that has barely moved since 2023. We test what diversity buys with a natural experiment. On 26 August 2026, amid security fixes in every implementation, Core Lightning (CLN) maintainers told operators who could not upgrade to disconnect their nodes. Using 805 daily gossip snapshots, 132,360 on-chain channel closes and a client classifier validated against self-identifying aliases and against the wallet that builds each node's funding transactions, we find that 22% of CLN nodes went dark overnight, ten times the usual rate, mostly Tor-reachable ones; a third were still dark five weeks later. The rest of the network barely noticed. Reachability among all node pairs fell by 7.8 percentage points, a loss exceeded in 4 of 94 ordinary two-day windows and half that of a Tor denial-of-service wave in July, while among CLN pairs it fell by 24.5 points, more than in any ordinary window. Calibrated failure scenarios explain the containment: the blast radius depends on whether a failure reaches the hubs, not on how many nodes run the failing software. Losing ACINQ's Eclair node alone costs the surviving network four times the reachability lost with all 619 routable CLN nodes, and minority clients' reliance on LND for connectivity is what their size implies; CLN nodes in fact peer with each other more than chance. Diversity statistics that count nodes mislead; the quantity to track is which software the hubs run.

cs.CR↗

Who Patches the Lightning Network? Evidence from Release Lines in Gossip, 2023-2026

Every implementation of Bitcoin's Lightning payment network disclosed security vulnerabilities in 2026, and every advisory told operators to upgrade. Whether they do has never been measured, because Lightning gossip carries no software version. Matching the feature bits a node announces against the source of every LND, Core Lightning, Eclair and LDK release, we show that gossip reveals a node's release line after all. Where Core Lightning nodes state their version, the inferred line is exact for 132 of 136 node-line pairs. Across 814 daily snapshots of the public graph from 2023 to 2026, the network patches on release and platform schedules, not on disclosures. Half of LND nodes upgrade within 88 days of a release; small nodes and those that skipped releases lag far behind. The three largest upgrade waves came about a day after the Umbrel app store shipped a new LND version. Since June 2025, 17% of LND upgrades came in the 48 hours after a platform release, windows that cover 4.4% of the time. Disclosures, a median 256 days after the fix, moved few operators: of 12 we can test, only Core Lightning's of July 2026 sped up upgrades, and only among nodes one release line behind. Its later call to restart offline was followed mostly by nodes already patched. Two months after Lightning Labs' August 2026 batch, 71% of the LND nodes exposed at disclosure still ran an affected release. For maintainers, the lever on the nodes that lag is the platforms that package their releases.

cs.CR↗

Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped

A bipedal robot cannot deviate from its path to avoid an obstacle without disturbing its balance, and this coupling is most severe on underactuated platforms such as the biped considered here, which has four actuated joints per leg and no hip or ankle roll. This paper presents a Hierarchical Reinforcement Learning (HRL) framework in which a High-Level (HL) policy observes the robot pose, 36 raycast proximity measurements, moving-obstacle states, and a receding-horizon local goal, and outputs a body-velocity command $(v_x, v_y, ω_{yaw})$ every ten control steps, while a velocity-conditioned Low-Level (LL) policy tracks each command through PD-controlled joint targets. Both policies are trained jointly with Soft Actor-Critic (SAC). Because the converged gait is task-agnostic, it is frozen and driven by classical planners over the same command interface, yielding three controlled baselines: SAC+A*, SAC+RRT*, and SAC+APF. Across 100 evaluation trials per method in randomized PyBullet environments, the proposed method reaches the goal in 98.0% of static and 88.0% of dynamic trials, against at most 78.0% and 68.0% for the planner hybrids, with path lengths within 4% of the A* reference, and ablations confirm that each observation channel and reward term contributes materially to this performance.

cs.RO↗

Admissibility-Preserving Control for Multi-Input Systems with Joint Capacity Constraints

This paper addresses the control of multi-input strict-feedback nonlinear systems subject to a joint capacity constraint, in which the admissible input set is a coupled subset of the individual actuator limits. Unlike existing constraint-handling methods that enforce actuator bounds channel by channel and may unnecessarily suppress admissible control directions, we develop an Anisotropic Joint-Admissibility-Preserving Input Realization (AJ-APIR) framework that explicitly exploits the geometry of the joint constraint. The proposed realization constructs a state-dependent gain matrix whose spectral decomposition separates the commanded input into normal and tangential directions relative to the constraint boundary. The normal component is attenuated as the boundary is approached, while the tangential component is preserved, which allows the admissible control effort to be redistributed without loss of tracking authority. Integrated with a backstepping controller, the AJ-APIR framework guarantees forward invariance of the joint admissible set for all time. We establish exponential convergence of the tracking error to zero together with uniform boundedness of all closed-loop signals, and characterize the resulting command-demand behavior under the joint constraint. Simulation results for a representative second-order, two-input nonlinear system subject to a power-budget constraint demonstrate the efficacy of the proposed method to enforce the joint input constraint.

eess.SY↗

A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition

Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally verbatim transcripts contain localized differences in pronunciation, spelling, or lexical realization that the acoustics do not uniquely determine. Omni-temporal Classification (OTC) tolerates such noise by adding wildcard paths to the connectionist temporal classification (CTC) alignment graph, but its word-level arcs are too coarse, since bypassing one unsupported token discards supervision for the whole word. We move wildcard arcs to token granularity so unsupported tokens can be bypassed while the rest of the word stays supervised, and we combine token- and word-level arcs as complementary escape paths. Across 19 languages and three corpora, token-level OTC improves over CTC on all 25 tasks. We also replace epoch-indexed relaxation of the wildcard weights with a predictive-entropy-indexed schedule, which performs comparably while reducing dependence on training length. Combining this schedule with the hybrid graph gives the lowest mean word error rate (WER) on every corpus and a 9.45% average relative WER reduction over CTC. Independent validator transcriptions show that token-level models place significantly more wildcard-bypass probability than CTC on disputed characters, indicating that token-level tolerance targets localized transcript ambiguity.

cs.CL↗

Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi

Benchmarking is critical for the systematic evaluation of machine learning systems. While several open-source datasets are available for Hindi, existing benchmarks remain limited in terms of modality, geographic diversity, demographic representation, and transcription robustness. We introduce an inclusive, multimodal Hindi benchmark dataset collected from 102 districts across India. The dataset consists of spontaneous speech elicited using image prompts and recorded under real-world acoustic conditions across diverse demographic groups. Each audio segment is associated with the image prompt that elicited it and is annotated with three independent transcriptions, enabling multi-reference evaluation that accounts for permissible orthographic and lexical variations. We show that single-reference evaluation overstates errors, while multi-reference evaluation provides a more robust, inclusive, and realistic assessment of automatic speech recognition (ASR) systems. The pairing of each utterance with its eliciting image further enables image retrieval evaluation using both speech and text queries. We evaluate multiple multimodal embedding models for image retrieval and report their performance on the combined speech--image and text--image retrieval tasks. The results reveal a performance gap between text-based and audio-based retrieval, with text-based retrieval consistently achieving higher performance.

eess.AS↗

Equivalent-Agent Guidance for Cooperative UAV Payload Transportation

This paper develops a guidance framework for cooperative transportation of a rigid payload by two uncrewed aerial vehicles (UAVs) to stationary and maneuvering landing platforms. A virtual equivalent-agent representation is first introduced to describe the translational motion of the rigidly coupled UAV-payload system, allowing the transportation problem to be formulated in terms of relative range and line-of-sight dynamics with respect to the landing platform. A geometric analysis establishes the terminal feasibility conditions for payload delivery. In particular, an arbitrary prescribed approach angle can be achieved for a stationary platform, whereas successful delivery to a maneuvering platform with zero relative velocity requires terminal velocity and heading angle synchronization and consequently a zero landing angle. Leveraging this framework, a robust fixed-time sliding mode guidance strategy is developed to regulate both relative range and line-of-sight dynamics. A separate link-orientation controller and control allocation scheme is presented to map virtual equivalent agent commands to the individual UAV's control inputs. The proposed strategy guarantees convergence to the desired landing configuration within a uniformly bounded time, independent of initial engagement geometries, while explicitly accommodating uncertainties arising from target maneuvers. Numerical simulations demonstrate accurate delivery under different terminal approach angles and platform maneuvers, while processor-in-the-loop implementation on a Raspberry Pi demonstrates that the guidance algorithm satisfies the real-time computational requirements. Nonetheless, a comparative analysis shows that the proposed framework achieves better tracking accuracy and faster sliding surface convergence while requiring significantly less control energy from each UAV.

eess.SY↗

Admissibility-Preserving Control for Strict-Feedback Nonlinear Systems with Asymmetric Actuator Constraints

This paper develops Admissibility-Preserving Control (APC), a realization-centered safety-critical control framework for strict-feedback systems subject to asymmetric actuator limits, time-varying output constraints, and actuator-rate limitations. APC denotes the overall control architecture, whereas an Admissibility-Preserving Input Realization (APIR) denotes its constraint-realization module. Therein, the APIR dynamically generates the physical plant input while rendering its prescribed asymmetric actuator set forward invariant. In contrast to algebraic clipping and post-design saturation compensation, the actuator limits are embedded directly in a continuously differentiable dynamic realization with user-selectable regularity and interpretable tuning parameters. The APIR is integrated with recursive backstepping by treating the realized plant input as an additional state. The resulting design does not require an input-to-state stability assumption on the uncontrolled plant. Instead, the nonlinear drift terms are compensated recursively, subject to an explicit compatibility condition between the desired motion, the available control authority, and the APIR interior gain. The framework is further extended to time-varying output-safe tracking through a smooth asymmetric logarithmic barrier coordinate and its associated Lyapunov function and to simultaneous actuator-magnitude and rate constraints through a cascaded APIR. Rigorous Lyapunov and invariance analyses establish regional asymptotic tracking, forward invariance of the compatible admissible sets, and boundedness of all closed-loop signals. Numerical studies illustrate asymmetric actuator utilization, output-safety preservation, and magnitude-rate constraint enforcement.

eess.SY↗

Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion

Automatic Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian languages, many of which are low-resource and exhibit significant dialectal differences. Existing methods often optimize ASR or DID individually, resulting in performance trade-offs. In this work, we propose a multimodal framework that jointly improves ASR and DID. Our method employs a Bottleneck Encoder to extract dialectal features from Conformer-based speech representations and a RoBERTa encoder to process ASR-generated CTC embeddings. A gating mechanism merges these features, followed by an attention encoder to refine the representations. The learned embeddings are concatenated with Conformer outputs to enhance ASR features. Evaluated on eight Indian languages with thirty-three dialects, our method achieves an average DID accuracy of 81.63% and average CER and WER of 4.65% and 17.73%, respectively. These results highlight the effectiveness of our method for joint ASR-DID modeling.

cs.CL↗

An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensors

Pixel-bin image sensors are becoming the default choice for smartphone cameras due to their resolution vs light-gathering trade-off. However, their larger inter-color separation compared to the Bayer color filter array (CFA) makes them challenging to demosaic. Furthermore, existing deep learning-based demosaicing methods are CFA-specific, requiring multiple individual models that take up precious onboard resources and demand larger development and maintenance efforts. In this work, we propose a modular unified architecture for demosaicing various pixel-bin sensors that provides higher image quality while being extensible and lightweight. Additionally, to enable plug-and-play operation, we introduce a learning-free CFA-identification module to detect the CFA type of raw data accurately.

cs.CV↗

VAANI: Capturing the language landscape for an inclusive digital India

Voice based technologies have the potential to bridge digital accessibility gaps; however, existing datasets fail to capture the linguistic and regional diversity of Indic languages. We present Project VAANI, a large scale multimodal dataset designed to represent India's linguistic landscape across 165 districts. Speech data is collected using image based prompts to elicit spontaneous responses, while images are curated through a separate pipeline covering diverse themes across regions. The dataset undergoes a rigorous multi stage quality control process, combining automated and manual evaluation to ensure high audio quality and transcription accuracy. We release approximately 289K images, 31,255 hours of speech, and 2,043 hours of transcribed audio spanning 105 languages from 28 states and 3 union territories. Many of these languages are represented at this scale for the first time, making VAANI a foundational resource for inclusive speech technology. The dataset enables the development of robust, multilingual, and multimodal models, and supports research in speech recognition, language understanding, and cross-modal learning for underrepresented languages.

eess.AS↗

RNG: Flat Datacenter Networks at Scale

We design and deploy in production the first flat datacenter networks. Our design, called RNG, is based on quasi-random graphs. While the cost and fault-tolerance benefits of such topologies have been long known, their practical realization has been hampered by a lack of scalable routing and cabling approaches. RNG has a new distributed routing protocol that exploits the properties of random graphs to find a large number of edge disjoint paths between pairs of endpoints. It uses a novel passive optical device that internally shuffles cables, which makes its cabling complexity similar to that of fat trees. We show that RNG matches or exceeds the performance of fat trees for a range of traffic patterns, despite being up to 45% cheaper. RNG is now the default datacenter network for most workloads at Amazon.

cs.NI↗

Path-Following Guidance for Unmanned Aerial Vehicle with Bounded Lateral Acceleration

This paper addresses the three-dimensional path-following guidance problem for unmanned aerial vehicles under explicit actuator constraints. Unlike conventional approaches that assume unbounded control inputs or handle saturation heuristically, the proposed method incorporates bounded lateral acceleration directly into the guidance design. A nonlinear guidance framework is developed employing a nested saturation-based control technique. The proposed guidance strategy guarantees bounded control inputs while ensuring exponential convergence of cross-track errors to zero. The formulation is applicable to general smooth paths and is systematically extended from planar to three-dimensional scenarios using a path-tangent coordinate framework. Rigorous stability analysis based on Lyapunov theory establishes convergence and feasibility properties of the closed-loop system. Numerical simulations on representative paths, including straight-line, circular, and sinusoidal paths, demonstrate that the proposed method achieves superior tracking performance, reduced control effort, and robustness against disturbances compared to existing guidance laws. The simplicity of the design and its compatibility with practical actuator limits make it suitable for real-world UAV applications.

eess.SY↗