Showing 1–50 of 882 results for author: Kumar, V

Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations

Authors: Aleksei Rozanov, Arvind Renganathan, Vipin Kumar

Abstract: Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features.… ▽ More Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually plausible, the task can only be solved by learning cross-feature physical dependencies. We evaluate the proposed objectives on global ERA5-Land reanalysis data using 21 environmental variables and assess the learned representations on seven downstream tasks spanning climate classification, carbon flux estimation, and streamflow prediction. Our study includes, to our knowledge, the first systematic comparison of self-supervised objectives for land-surface modeling under a shared architecture and pre-training budget. We find that the most effective pretext task depends on the downstream task family rather than any single objective's superiority, and that imposter provides complementary information when combined with existing SSL objectives. These results suggest that physical coherence is a valuable new source of self-supervision for scientific foundation models. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Entanglement-Assisted Quantum Locally Recoverable Codes: Bounds, Optimal Constructions, and Achievability

Authors: Vijay Kumar, Ramakrishna Bandi

Abstract: This paper studies entanglement-assisted quantum locally recoverable codes (EA-qLRCs) built via a CSS-like stabilizer construction from pairs of classical locally recoverable codes (cLRCs), without requiring dual-containment. We define such codes through local recovery channels, give a sufficient stabilizer criterion for the construction, and derive Singleton-, Griesmer-, Plotkin-, and sphere-pack… ▽ More This paper studies entanglement-assisted quantum locally recoverable codes (EA-qLRCs) built via a CSS-like stabilizer construction from pairs of classical locally recoverable codes (cLRCs), without requiring dual-containment. We define such codes through local recovery channels, give a sufficient stabilizer criterion for the construction, and derive Singleton-, Griesmer-, Plotkin-, and sphere-packing-like converse bounds on the parameters of the resulting pure CSS-like EA-qLRCs, along with a Cadambe--Mazumdar-like bound that, as in the classical case, lacks a closed form, plus a comparison of their relative tightness across finite-length and asymptotic regimes. We give necessary and sufficient conditions for a pure CSS-like EA-qLRC to attain the Singleton-like bound with equality; for the single-code case $\mathcal{C}_1=\mathcal{C}_2=\mathcal{C}$, this reduces to a simple condition on the hull dimension $s=\dim(\mathcal{C}\cap\mathcal{C}^\perp)$, which also fixes the entanglement count via $c=n-k-s$. We present CSS-like EA-qLRC constructions from classical LRC families---Tamo--Barg and cyclic codes---and characterize when these attain the Singleton-like bound, showing the cyclic families yield optimal codes while the Tamo--Barg construction, though valid, attains the bound only in the degenerate regime $k \le r$, where locality is vacuous. We complement these constructions with two Gilbert--Varshamov-like achievability bounds, via a classical parity-check augmentation and a sharper concatenated-code construction, and show both hold unconditionally for field size $q>3$ via a monomial-equivalence argument. Finally, we unify all bounds---converse and achievability alike---under a common maximally entangled regime, giving a single comparison of the achievable and forbidden rate--distance--locality region for CSS-like EA-qLRCs. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: Entanglement-assisted quantum error-correcting codes, quantum locally recoverable codes, Tamo-Barg codes, cyclic codes, and LCD codes

UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys

Authors: Junxiong Zhou, Xuechen Li, Chonghao Qiu, Lang Qiao, Xiaowei Jia, Qi Yang, Chishan Zhang, Leikun Yin, Nanshan You, Vipin Kumar, David Mulla, Ce Yang, Zhenong Jin, Licheng Liu

Abstract: Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and management response. Modern 3D reconstruction methods perform strongly on generic benchmarks, but rendered appearance may not translate into metrically and agronomically useful geometry in crop fields. We introduce UAV3DCrop, a public benchmark of repeat… ▽ More Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and management response. Modern 3D reconstruction methods perform strongly on generic benchmarks, but rendered appearance may not translate into metrically and agronomically useful geometry in crop fields. We introduce UAV3DCrop, a public benchmark of repeated multi-angle unmanned aerial vehicle (UAV) crop surveys. It contains 88,830 RGB images at $5280 \times 3956$ pixels, with a ground sampling distance of 3.6-5.8 mm, from 91 scenes spanning corn, soybean, wheat, and oat. Track A evaluates seven scene-optimized methods -- Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) variants -- on held-out views, photogrammetry-referenced depth, and canopy-height recovery. Track B tests four pretrained feed-forward models on zero-shot camera-pose and geometry estimation. The scene-optimized methods rank differently across the three targets: Splatfacto-big leads appearance, whereas Scaffold-GS leads depth and is statistically tied with Splatfacto for canopy height. Among feed-forward models, MapAnything leads on seven of the eight metrics, while the remaining models vary more across crops and fail severely on absolute scale in a way that alignment conceals. Repeated acquisitions reveal further sensitivities that differ by output type and by model, associated with position within the acquisition sequence and with tie-point multiplicity. Current 3D reconstruction methods are therefore not yet interchangeable for agronomic use: no single method wins on appearance, geometry, and canopy height at once, and only one of four feed-forward models recovers usable metric scale. The dataset is publicly available at https://link-dev.github.io/UAV3DCrop/ △ Less

Submitted 2 August, 2026; originally announced August 2026.

Comments: 22 pages, 7 figures. Dataset and project page: https://link-dev.github.io/UAV3DCrop/

Learning Smooth SE(3) Trajectories under Left-Invariant Riemannian Metrics

Authors: Yuwei Wu, Vijay Kumar

Abstract: Optimal trajectory generation for rigid-body motions on Lie groups can be formulated as a variational problem that minimizes energy functionals defined by Riemannian metrics. While closed-form solutions exist for special cases such as product metrics and rest-to-rest boundary conditions, solving the general problem with arbitrary boundary states and coupled rotational-translational metrics often r… ▽ More Optimal trajectory generation for rigid-body motions on Lie groups can be formulated as a variational problem that minimizes energy functionals defined by Riemannian metrics. While closed-form solutions exist for special cases such as product metrics and rest-to-rest boundary conditions, solving the general problem with arbitrary boundary states and coupled rotational-translational metrics often requires computationally expensive numerical boundary value solvers. These limitations restrict the use of geometrically consistent trajectory generation in real-time robotic planning and control. This paper presents a learning-based framework for approximating higher-order smooth trajectories on SE(3) under general left-invariant Riemannian metrics. The method parameterizes body-twist trajectories using high-order polynomials and relies on a neural network to learn a subset of the polynomial coefficients and the trajectory duration. The remaining coefficients are analytically determined to enforce the boundary conditions. The training of the network is guided by losses derived from Euler-Lagrange optimality conditions, metric-weighted smoothness objectives, and feasibility constraints. The metric-conditioned framework enables generalization across diverse metric structures and motion conditions. Extensive numerical experiments demonstrate that the proposed approach generates smooth trajectories that closely approximate solutions from numerical optimization while achieving millisecond-level inference times. We demonstrate two practical applications of the proposed framework: real-time generation of diverse motion primitives with waypoint traversal, and refinement for quadrotor flight under dynamic conditions. These results suggest that learning-based motions with geometric structure can provide an efficient alternative to conventional optimization-based methods for trajectory generation on SE(3). △ Less

Submitted 2 August, 2026; originally announced August 2026.

Multi-Sensor Alignment for Weather Simulations

Authors: Samsad Alam, Devyani Lambhate, Aditya Mohan, Vishal Kumar, Vaibhav Katewa

Abstract: Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions. Due to lack of real-world weather datasets, weather simulations are a promising alternative. To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors. To achi… ▽ More Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions. Due to lack of real-world weather datasets, weather simulations are a promising alternative. To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors. To achieve this, we propose the Reference Dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit[1]) for particle positioning alignment in rain and snow. We validate both alignment methods using statistical and geometrical tests, respectively. We find that 3D detection models for non-aligned versions tend to be overly optimistic as compared to aligned versions. We also show the aligned-multi-sensor simulation's effectiveness for achieving robustness for 3D object detection task by finetuning existing sensor fusion models on it. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers

Authors: Vasudha Bhatnagar, Purnima Bindal, Vikas Kumar, Raj Kumari Bahl

Abstract: Zero-shot summarization using Large Language Models (LLMs) has significantly advanced the abstractive summarization task by producing coherent and fluent summaries. However, underlying stochasticity of the large language models raises concerns about the stability and trustworthiness of the LLM-generated summaries. This issue has become increasingly important due to proliferation of LLM-generated s… ▽ More Zero-shot summarization using Large Language Models (LLMs) has significantly advanced the abstractive summarization task by producing coherent and fluent summaries. However, underlying stochasticity of the large language models raises concerns about the stability and trustworthiness of the LLM-generated summaries. This issue has become increasingly important due to proliferation of LLM-generated summaries in educational settings, where students and researchers summarize complex academic materials in zero-shot manner. We propose a novel two-level diagnostic protocol for benchmarking LLM-summarizers based on the stability of the generated summaries. At the lower level, document-level stability analysis is performed over multiple LLM-summaries generated under controlled environment, and the stability coefficient is computed. Each generated summary is scored for semantic and factual alignment with the original document, enabling estimation of stability along more than one dimensions. At the next level, observations from a stratified sample of documents drawn from the corpus are consolidated to estimate the stability index of the LLM-summarizer, which is the proxy for its trustworthiness. Our empirical investigation of three LLM-summarizers across three genres of documents reveals statistically significant differences in the generation-level variability among LLMs across summary evaluation metrics. This study advances the LLM-summarization research by evidential recognition of the stability problem in LLM-summaries and motivates further research towards development of robust, reliable and trustworthy LLM-summarizers. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: 28 pages, Under review in a journal

EFLUX: Elastic Multi-Robot Formation Navigation and Adaptation with Agentic LLMs

Authors: Jinyuan Zhang, Yuwei Wu, Guangyao Shi, Jonathan Diller, Gaurav S. Sukhatme, Vijay Kumar

Abstract: Multi-robot teams operating in confined or cluttered environments must adapt both their formation geometry and group topology to navigate through complex obstacles. This adaptation requires two complementary behaviors: deformation, where the team continuously reshapes its geometry while remaining connected, and reconfiguration, where robots split into subgroups or merge back into a single formatio… ▽ More Multi-robot teams operating in confined or cluttered environments must adapt both their formation geometry and group topology to navigate through complex obstacles. This adaptation requires two complementary behaviors: deformation, where the team continuously reshapes its geometry while remaining connected, and reconfiguration, where robots split into subgroups or merge back into a single formation. Existing methods often model these behaviors independently, connect them through handcrafted rules, or lack explicit geometric criteria for determining when each behavior should be invoked. However, challenging environments may require online changes in formation shape, connectivity, and effective team composition, making decoupled or rule-based approaches prone to suboptimal trajectories and deadlock. We propose EFLUX, a geometry-grounded LLM agentic framework for automatic and elastic multi-robot formation navigation. EFLUX extracts a structured scene representation and uses an LLM to reason jointly over both deformation actions, such as scaling and shearing, and reconfiguration actions, such as splitting and merging. These strategies are then translated into executable per-robot waypoints through a closed-loop generation, verification, and correction pipeline. Simulation and hardware experiments show that EFLUX enables safe, continuous, and elastic formation navigation in constrained environments, reducing deadlock and navigation failures compared with baselines while maintaining coherent multi-robot coordination. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Simple Features and Honest Calibration for Ambivalence and Hesitancy Recognition in Video

Authors: Vikas Kumar, Aditya Mishra, Haroon R. Lone

Abstract: We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system combines affect-specialised text, audio, and visual representations with a small set of readable linguistic hesitation cues, fused by a reliability gate we call Affective Marker Fusion (AMF), and finished with a simple AP-we… ▽ More We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system combines affect-specialised text, audio, and visual representations with a small set of readable linguistic hesitation cues, fused by a reliability gate we call Affective Marker Fusion (AMF), and finished with a simple AP-weighted ensemble at a fixed decision threshold. We also introduce \emph{ASR-erased time}: speech recognisers delete fillers and hesitation pauses from the transcript, but the chunk timestamps keep the time those events took, and sixteen features built from these gaps form the strongest and most independent non-verbal channel we measured (AP $0.718$, correlation $0.11$--$0.36$ with all other members). Across controlled experiments we find three things: cross-modal conflict design does not reliably help on BAH; language is by far the strongest channel while affect-specialised audio is a useful second; and calibration matters more than architecture. Fitting ensemble weights and a threshold on the small validation split overfits: it scores $0.741$ macro-F1 on validation but only $0.690$ on the untouched test set. AP-weighting at a fixed threshold instead reaches $\mathbf{0.731}$ on test. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications

Authors: Nasser Giacaman, Valerio Terragni, Paul Denny, Viraj Kumar

Abstract: As AI code tools become integrated into programming environments, students increasingly describe intended behavior in natural language and rely on these tools to generate code, shifting emphasis from code writing to specification. Yet little is known about the comments students write as specifications in AI-assisted programming tasks. We analyze a four-year dataset of undergraduate programming sub… ▽ More As AI code tools become integrated into programming environments, students increasingly describe intended behavior in natural language and rely on these tools to generate code, shifting emphasis from code writing to specification. Yet little is known about the comments students write as specifications in AI-assisted programming tasks. We analyze a four-year dataset of undergraduate programming submissions and reflections from tasks in which students wrote comments to guide code generation and refined solutions using test-case feedback. We introduce a taxonomy spanning three dimensions: comment type, code expression level, and code construct. Using automated classification, we examine how these dimensions vary across attempts and how students describe the process in their reflections. Our findings show that students mostly wrote natural-language What comments, shifted toward How comments for more procedural constructs, and focused more on verifying generated code than on repeatedly rewriting comments. △ Less

Submitted 12 July, 2026; originally announced July 2026.

Comments: 7 pages, 2 figures, 2 tables. Accepted in the Proceedings of the 2nd ACM Virtual Global Computing Education Conference (SIGCSE Virtual 2026)

ACM Class: K.3.2

PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation

Authors: Devanshu Verma, Vasudha Bhatnagar, Vikas Kumar, Balaji Ganesan

Abstract: Legal precedent retrieval is a fundamental task in legal case preparation, planning, litigation strategy, and legal research. Current approaches for automatic precedent retrieval map legal documents to a low-dimensional semantic space and compute similarity based on the proximity of their representations. These approaches treat legal documents as monolithic texts, ignoring the rhetorical organizat… ▽ More Legal precedent retrieval is a fundamental task in legal case preparation, planning, litigation strategy, and legal research. Current approaches for automatic precedent retrieval map legal documents to a low-dimensional semantic space and compute similarity based on the proximity of their representations. These approaches treat legal documents as monolithic texts, ignoring the rhetorical organization of the legal technicalities. Ergo, they overlook nuanced legal meanings and fail to distinguish the contextual significance of legal entities and concepts that vary based on their rhetorical roles within the document. To address this insufficiency, we propose the PRecG pipeline that computes the similarity between pairs of legal judgments by hierarchically learning their representations. The process begins by decomposing each document into distinct semantic units (segments) based on the rhetorical roles of sentences. For each rhetorical segment, a knowledge graph is constructed to capture the legal entities and their relationships within the segment. Contextual representations of the entities are then learned and aggregated to derive segment-level embeddings. These embeddings are further integrated to produce a unified document-level representation, and finally, the semantic similarity between a pair of documents is computed. We validate the performance of the proposed approach through extensive experiments on a benchmark Indian legal dataset, comparing it against state-of-the-art baselines to demonstrate its effectiveness. △ Less

Submitted 10 July, 2026; originally announced July 2026.

Comments: 23 Pages

SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images

Authors: Porus Vaid, Shivam Chopra, Vaibhav Kumar

Abstract: Reconstructing high-fidelity 3D building models from UAV imagery is essential for large-scale digital twin development. However, existing 3D Gaussian Splatting (3DGS) techniques often struggle with building facades, failing to capture sharp geometric transitions. To address this, we propose a semantic edge regularization framework that supervises 3DGS to produce crisp architectural boundaries. Our… ▽ More Reconstructing high-fidelity 3D building models from UAV imagery is essential for large-scale digital twin development. However, existing 3D Gaussian Splatting (3DGS) techniques often struggle with building facades, failing to capture sharp geometric transitions. To address this, we propose a semantic edge regularization framework that supervises 3DGS to produce crisp architectural boundaries. Our method leverages SAM 3 to generate precise building masks, from which we extract architecturally significant edges. During training, we align rendered image gradients with these extracted edges, forcing the Gaussians to converge into sharp structural geometries. Evaluations across campus environments, dense urban centers, and custom residential datasets demonstrate significant improvements in edge fidelity without requiring architectural modifications to the 3DGS pipeline. Our approach proves robust across diverse building types, roof geometries, and urban densities. △ Less

Submitted 4 July, 2026; originally announced July 2026.

Comments: Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) - 2026

Gemma 4 Technical Report

Authors: Gemma Team, Sherif El Abd, Vaibhav Aggarwal, Robin Algayres, Alek Andreev, Olivier Bachem, Ian Ballantyne, Cormac Brick, Victor Cărbune, Michelle Casbon, Mayank Chaturvedi, Aditya Chawla, Victor Cotruta, Alice Coucke, Phil Culliton, Robert Dadashi, Lucas Dixon, Mohamed Elhawaty, Utku Evci, Clément Farabet, Johan Ferret, Filippo Galgani, Sertan Girgin, Jean-Bastien Grill, Maarten Grootendorst , et al. (298 additional authors not shown)

Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture… ▽ More We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks. △ Less

Submitted 24 July, 2026; v1 submitted 2 July, 2026; originally announced July 2026.

Comments: 17 pages, 2 figures, technical report, updated

On Surrogate Modeling of Static Response of AM Short-Fiber Thermoplastics Using Graph Neural Networks

Authors: Pharindra Pathak, Vipin Kumar, Trenton M. Ricks, Suhasini Gururaja, Siddhartha Srivastava

Abstract: Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability. Unlike continuous-fiber systems, the mechanical response of SFTs is governed by mesoscale interactions among fiber orientation, spatial clustering, and manufacturing-induced porosity. The… ▽ More Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability. Unlike continuous-fiber systems, the mechanical response of SFTs is governed by mesoscale interactions among fiber orientation, spatial clustering, and manufacturing-induced porosity. These features exhibit significant spatial variability in manufactured components and influence stiffness, damage initiation, and nonlinear deformation. Although mesoscale finite element (FE) models can resolve such heterogeneity, their application to realistic three-dimensional microstructures remains computationally intractable. A data-driven surrogate framework is proposed to predict the mechanical behavior of additively manufactured, compression-molded (AM-CM) SFTs. Microstructures reconstructed from micro-computed tomography data were discretized into Voronoi-based cells representing distinct fiber-interaction neighborhoods. Each cell was homogenized via nonlinear FE simulations incorporating matrix damage, and the resulting stress-strain responses trained a hybrid Graph Neural Network-Long Short-Term Memory (GNN-LSTM) architecture encoding microstructural topology and history-dependent mechanical evolution. The surrogate accurately predicts stiffness and stress-strain behavior of unseen microstructures, achieving $R^2\approx 0.98$ relative to high-fidelity FE simulations with over two orders-of-magnitude reduction in computational cost. Coupling the framework with experimentally calibrated damage laws demonstrates that fiber orientation, clustering, and porosity collectively govern local effective stiffness. The approach provides a physics-informed, data-efficient pathway to identify mechanically weak microstructural cells and accelerate digital-twin development for SFT components. △ Less

Submitted 27 June, 2026; originally announced June 2026.

Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources

Authors: Darshita Rathore, Vineet Kumar, Vaibhav Singal, Ankur Vivek Singh, Anindya Moitra

Abstract: Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables. We present COGNI,… ▽ More Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables. We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements slide-adaptive chunking -- recursive chunking for plain-text slides, hierarchical chunking for structured content such as tables, charts, and key-value blocks - achieving $88.3\%$ on our internal enterprise benchmark. Second, a routing layer built on a LoRA fine-tuned Qwen-2.5-1.5B-Instruct model that produces a dual output - modality decision and complexity assessment at $93.8\%$ accuracy and approximately $7\times$ lower cost than frontier-model. Third, a retrieval layer executes complexity-adaptive pipelines: a self-correcting NL2SQL agent at $93.9\%$ G-Eval, and Recursive Language Models reaching $91.0\%$ on multi-hop synthesis queries. Finally, a caching layer validates query equivalence across multiple dimensions beyond embedding similarity, achieving zero false cache hits and $8.4\times$ latency reduction. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: Accepted at Agent4IR @ KDD2026

One Year Later...The Harms Persist, But So Do We!

Authors: Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar, Anson Antony

Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety guardrails remain inadequate and inconsistent across clinical conditions. This study evaluates eight proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Resul… ▽ More General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety guardrails remain inadequate and inconsistent across clinical conditions. This study evaluates eight proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Results show that safeguards hold reliably only for suicide and self-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into publicly available settings (e.g., schools, search engines, and consumer chatbots) are particularly concerning. △ Less

Submitted 1 July, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

Making Quantum Networks Work: Routing, Calibration, and Programmable Quantum Repeaters

Authors: Vinay Kumar

Abstract: The quantum internet enables distribution of quantum states across distant nodes, supporting secure communication, distributed computing, and quantum sensing. Unlike classical networks, it is constrained by the no cloning theorem, probabilistic entanglement generation, decoherence, and hardware drift, making classical abstractions inadequate. Scalable quantum networking therefore requires new arch… ▽ More The quantum internet enables distribution of quantum states across distant nodes, supporting secure communication, distributed computing, and quantum sensing. Unlike classical networks, it is constrained by the no cloning theorem, probabilistic entanglement generation, decoherence, and hardware drift, making classical abstractions inadequate. Scalable quantum networking therefore requires new architectures, protocols, and optimisation methods that explicitly account for these limitations. This thesis studies the architecture, routing, and operation of quantum networks under realistic constraints, focusing on bipartite entanglement distribution over quantum repeater networks. Key metrics include end to end fidelity, throughput, scalability, and fairness. At the network layer, routing strategies are developed beyond assumptions of homogeneous nodes and full network knowledge. Routing under heterogeneous repeater efficiencies shows how partial knowledge of node quality improves fidelity and reduces path blocking. A grey box routing approach is then introduced, where path selection relies only on topology and end to end estimates, achieving robustness and fairness without detailed link information. At the link layer, calibration and hardware drift are addressed through a calibration aware model separating activation and calibration phases. For linear repeater chains, an optimal calibration schedule is derived to balance operation time and calibration overhead. This is extended to general topologies with shared links, where a greedy orchestration heuristic is proposed. Finally, the thesis connects network protocols with hardware via an instruction set architecture for programmable quantum repeater nodes based on NV centers, enabling coherent programmability and linking physical operations to higher layer protocols. △ Less

Submitted 20 June, 2026; originally announced June 2026.

Comments: 173 pages, 44 figures; PhD dissertation

Report number: https://tesidottorato.depositolegale.it/handle/20.500.14242/374291

Optimal Calibration of Quantum Network Links

Authors: Vinay Kumar, Claudio Cicconetti, Marco Conti, Andrea Passarella

Abstract: The reliable distribution of entanglement is essential for the effective operation of quantum networks. Due to fundamental differences between quantum and classical communication systems, it is necessary to develop specialised algorithms and protocols that also account for quantum-specific constraints. In this work, we focus on the issue of recalibration. As suggested by recent experimental studie… ▽ More The reliable distribution of entanglement is essential for the effective operation of quantum networks. Due to fundamental differences between quantum and classical communication systems, it is necessary to develop specialised algorithms and protocols that also account for quantum-specific constraints. In this work, we focus on the issue of recalibration. As suggested by recent experimental studies, the process of local entanglement generation in a quantum link degrades over time due to environmental changes that have to be estimated and compensated via a calibration operation, during which the link is not available. Therefore, in such a quantum network, every link alternates between an activation period, during which it operates normally, and a calibration period, during which it cannot participate in the end-to-end entanglement distribution, thereby creating a trade-off between link quality (the fidelity of generated pairs, which decays during activation) and availability (the fraction of time the link is usable, which calibration reduces). We develop analytically a protocol for optimally assigning activation periods to each link in linear quantum repeater chains, subject to any general end-to-end fidelity requirements and local initial fidelity thresholds. Building on this foundation, we extend to general quantum networks, where multiple paths may cross at common links, proposing a heuristic approach evaluated in simulations and compared with a benchmark, numerical approach, and theoretical bounds. △ Less

Submitted 16 June, 2026; originally announced June 2026.

Comments: 23 pages, 10 figures

Petrov-Galerkin Variational Physics-Informed Neural Network Framework for Two-Dimensional Singularly Perturbed Problems

Authors: Vijay Kumar, Gautam Singh

Abstract: This study proposes a Petrov-Galerkin based Variational Physics-Informed Neural Network (VPINN) for efficiently solving two-dimensional singularly perturbed problems (SPPs) with one and two small perturbation parameters. The approach employs neural networks to construct the trial solution space, while tensor-product hat functions are adopted as test functions to enforce the variational form. To ac… ▽ More This study proposes a Petrov-Galerkin based Variational Physics-Informed Neural Network (VPINN) for efficiently solving two-dimensional singularly perturbed problems (SPPs) with one and two small perturbation parameters. The approach employs neural networks to construct the trial solution space, while tensor-product hat functions are adopted as test functions to enforce the variational form. To accurately resolve of sharp boundary layers, the variational form is implemented using a Petrov-Galerkin formulation. Dirichlet boundary conditions are imposed directly, while the source terms are computed using automatic differentiation. Computational experiments on standard two-dimensional problems demonstrate that the proposed method achieves high accuracy in both the maximum and L_2 norms. These results confirm the efficiency and robustness of the Petrov-Galerkin VPINN approach in accurately capturing the multiscale features of two-dimensional SPPs. △ Less

Submitted 15 June, 2026; originally announced June 2026.

MSC Class: 35B25; 34D15; 65M12; 68T07

Artificial Intelligence Index Report 2026

Authors: Sha Sajadieh, Loredana Fattorini, Raymond Perrault, Yolanda Gil, Vanessa Parli, Lapo Santarlasci, Juan Pava, Nestor Maslej, Russ Altman, Erik Brynjolfsson, Carla Brodley, Jack Clark, Virginia Dignum, Vipin Kumar, James Landay, Terah Lyons, James Manyika, Juan Carlos Niebles, Yoav Shoham, Elham Tabassi, Russell Wald, Toby Walsh, Dan Weld

Abstract: Welcome to the ninth edition of the AI Index report. As AI continues to advance rapidly, the question becomes whether the systems built around it can keep up. Governance frameworks, evaluation methods, education systems, and the data infrastructure needed to track AI's impact are struggling to match the pace of the technology itself. That gap between what AI can do and how prepared we are to manag… ▽ More Welcome to the ninth edition of the AI Index report. As AI continues to advance rapidly, the question becomes whether the systems built around it can keep up. Governance frameworks, evaluation methods, education systems, and the data infrastructure needed to track AI's impact are struggling to match the pace of the technology itself. That gap between what AI can do and how prepared we are to manage it runs through every chapter of this year's report. New in this edition, the report tracks how AI is being tested more ambitiously across reasoning, safety, and real-world task execution, and why those measurements are increasingly difficult to rely on. It also features new estimates of generative AI's economic value alongside emerging evidence of its labor market effects, an analytical framework on AI sovereignty, and a science chapter developed in collaboration with Schmidt Sciences. For the first time, the report features standalone chapters on AI in science and AI in medicine, reflecting AI's growing impact across these two domains. △ Less

Submitted 29 June, 2026; v1 submitted 13 April, 2026; originally announced June 2026.

Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages

Authors: Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik

Abstract: Multilingual ASR models such as Whisper perform well on high-resource languages but exhibit substantially higher Word Error Rates (WER) for Dravidian languages compared to Indo-Aryan ones. Through linguistic and dataset analysis, we show that Dravidian languages have longer words, higher vocabulary diversity, and lower repetition, resulting in sparse token distributions and frequent character-leve… ▽ More Multilingual ASR models such as Whisper perform well on high-resource languages but exhibit substantially higher Word Error Rates (WER) for Dravidian languages compared to Indo-Aryan ones. Through linguistic and dataset analysis, we show that Dravidian languages have longer words, higher vocabulary diversity, and lower repetition, resulting in sparse token distributions and frequent character-level substitution errors. Baseline fine-tuning further reveals decoder imbalance between self-attention (linguistic context) and cross-attention (acoustic cues). Although synthetic token-repetition experiments indicate potential gains, they are impractical. Motivated by these observations, we introduce two decoder-level enhancements: Weighted-Attention, which adaptively balances attention sources, and Self-Conditioning, which reinjects intermediate predictions to improve token consistency. Experiments demonstrate consistent WER reductions for low-resource and agglutinative languages. △ Less

Submitted 8 June, 2026; originally announced June 2026.

Comments: Accepted at INTERSPEECH 2026, 5 pages, 1 figure, 5 tables

Reshaping Undergraduate Computer Science Education in the Generative AI Era

Authors: Yi-Chieh Lee, Nattapat Boonprakong, Yugin Tan, Harold Soh, Alex Potanin, Viraj Kumar, Anoop K. Sinha, Chen Qian, Paul Denny, Mennatallah El-Assady, Ian Oakley, Jake Renzella, Amy Zhang, Jat Singh, Wee Sun Lee, Hsuan-Tien Lin, Jane L. E, Anthony Tang, Margaret M. Burnett, Sowmya Somanath, Renwen Zhang, Vicky Charisi, Alexandra I. Cristea

Abstract: Generative AI represents a turning point for Computer Science (CS) education. In recent decades, post-secondary CS education has largely focused on what has been seen as practical software engineering skills: implementation-level programming, debugging, testing, and software design, analysis, and documentation. However, this framing is becoming less tenable as generative AI automates many of these… ▽ More Generative AI represents a turning point for Computer Science (CS) education. In recent decades, post-secondary CS education has largely focused on what has been seen as practical software engineering skills: implementation-level programming, debugging, testing, and software design, analysis, and documentation. However, this framing is becoming less tenable as generative AI automates many of these tasks, challenging their centrality in CS education. To keep pace with advances in AI technology, CS curricula should consider a shift toward understanding and verifying AI-generated artifacts. This white paper outlines the findings of two international NUS-Google Workshops in Singapore, where we convened faculty members, industry practitioners, and students, and proposes a strategic response to reshape how CS should be taught at the undergraduate level. Based on the findings, we identify critical skills that must be preserved and those that are becoming less important. By incorporating these skills as "breadcrumbs," we can provide helpful nudges and engaging exercises within the current curriculum, enhancing learning experiences for everyone. We believe that to effectively prepare future computer science graduates, capable of creating, solving problems, and managing, as well as co-creating, artifacts with AI. It is important to consider a shift in curricula. Emphasizing system design, abstraction, and critical evaluation could greatly enhance their education and readiness for the challenges ahead. We propose prerequisites for solutions to reform CS education by fostering AI-native competencies, re-centering fundamental education, enhancing advanced pathways, embracing new pedagogies, and shifting institutional support. △ Less

Submitted 11 June, 2026; v1 submitted 2 May, 2026; originally announced June 2026.

Comments: Workshop report

Probing the Prompt KV Cache: Where It Becomes Dispensable

Authors: Vinayshekhar Bannihatti Kumar, Manoj Ghuhan Arivazhagan, Disha Makhija, Rashmi Gangadharaiah

Abstract: Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss. We ask when and what kind of redundancy: at which layers, after how many decoding steps, and in what form can the prompt span KV cache be replaced without breaking the task. A controlled splice intervention swept over la… ▽ More Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss. We ask when and what kind of redundancy: at which layers, after how many decoding steps, and in what form can the prompt span KV cache be replaced without breaking the task. A controlled splice intervention swept over layer cutoff and decoding steps shows this redundancy is about form (chat template scaffolding) rather than content. Replacing the upper layer prompt span KV cache with KV cache from a chat template scaffold whose user content is a neutral filler recovers near clean accuracy, while zeroing the same slots collapses accuracy. The dissociation replicates across the Qwen3, Gemma 3, and Llama 3 families on multiple datasets. △ Less

Submitted 28 May, 2026; originally announced May 2026.

REBAR: Reference Ethical Benchmark for Autonomy Readiness

Authors: Jonathan Diller, David Barnes, Rebekah Bogdanoff, Rhett Collier, Roddy Collins, Keith Fieldhouse, Yonatan Gefen, Cameron Johnson, Anuriha Kodali, Brad Kriel, Varun Murali, James Niehaus, Mish Sukharev, Joseph VanPelt, Anthony Hoogs, Vijay Kumar, Arslan Basharat

Abstract: As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical embodied AI frameworks remain mostly qualitative, focusing on system design (through safety guardrails or targeted red teaming), and the realized guardrails often di… ▽ More As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical embodied AI frameworks remain mostly qualitative, focusing on system design (through safety guardrails or targeted red teaming), and the realized guardrails often directly disallow unsafe behavior without providing the user with an override or interpretable reason. Instead, there is a need for computable metrics through rigorous testing that allow a user to determine the applicability of the system to the task. To address this gap, we introduce the Reference Ethical Benchmark for Autonomy Readiness (REBAR), a quantitative test and evaluation framework for autonomous systems. REBAR maps operating metrics into a computable Autonomy Readiness Level (ARL) rubric that can quantify ethical performance. Key innovations of the framework include a neuro-symbolic Large Language Model (LLM) approach to calculate and explain the ethical difficulty of scenarios, LLM-driven at-scale generation of test instances, and a versatile, photorealistic simulation environment. By evaluating white-box autonomy solutions through this rigorous testing pipeline, REBAR delivers an objective and repeatable benchmark score, bridging the gap between abstract principles and verifiable, accountable autonomy. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: To be presented at the 2026 Workshop on Robot Ethics - Ethical, Legal and User Perspectives in Robotics and Automation (WOROBET)

GraphMind: From Operational Traces to Self-Evolving Workflow Automation

Authors: Yiwen Zhu, Joyce Cahoon, Anna Pavlenko, Qiushi Bai, Nima Shahbazi, Divya Vermareddy, Meina Wang, Mathieu Demarne, Swati Bararia, Wenjing Wang, Hemkesh Vijaya Kumar, Hannah Lerner, Katherine Lin, Steve Toscano, Miso Cilimdzic, Subru Krishnan

Abstract: Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time. We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort. The system operates in three phas… ▽ More Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time. We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort. The system operates in three phases. First, a scalable offline pipeline extracts structured workflow graphs from large volumes of human resolution traces, capturing problems, actions, and their causal relationships. Second, an online multi-agent traversal engine navigates the graph to dynamically construct and execute workflows, combining graph-guided retrieval with LLM-driven reasoning at each step. Third, Adaptive Traversal Reinforcement (ATR) reinforces successful traversal paths, enabling execution-informed graph adaptation. GraphMind has been deployed across four production cloud database services for incident investigation. Evaluated on 93 held-out incidents and validated via blind expert review, the system outperforms an Agentic Summary-RAG baseline in mitigation reach, hallucination rate, and diagnostic throughput while requiring 8x less retrieval context. The ATR layer reduces hallucination rate by 26%, demonstrating that workflow graphs can learn from execution feedback. A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency. △ Less

Submitted 25 May, 2026; v1 submitted 17 May, 2026; originally announced May 2026.

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

Authors: Cheryl Wang, Chun Kwang Tan, Balint K. Hodossy, Eric Lyu, Jun Guo, Wentao Zhao, Huaping Liu, Chengkun Li, Merkourios Simos, Bianca Ziliotto, Alexander Mathis, Siyuan Liu, Jiahao Chen, Shanlin Zhong, Bo Jiang, Ci Song, Yaoye Zhu, Chenhui Zuo, Yanan Sui, Mohamed Irfan Refai, Massimo Sartori, Guillaume Durandau, Vikash Kumar, Vittorio Caggiano

Abstract: Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this seamless combination of capabilities remains elusive in current artificial intelligence and robotic systems. Concurrently, understanding the biological mastery of these movements is hindered because complex muscle coordina… ▽ More Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this seamless combination of capabilities remains elusive in current artificial intelligence and robotic systems. Concurrently, understanding the biological mastery of these movements is hindered because complex muscle coordination is rarely measured in vivo due to the limitations of physical equipment. To bridge this fundamental gap in understanding, MyoChallenge at NeurIPS 2025 established a pioneering benchmark for motor control intelligence in sports, leveraging high-fidelity musculoskeletal models within physics simulation combined with machine learning-driven algorithms. The competition introduces two distinct tracks emphasizing either upper or lower limbs control: a table tennis rally task utilizing a biomechanic upper limb composed of an arm with a hand and a trunk; and a soccer penalty kick using a biomechanic model of legs and a trunk. Marking the fourth iteration of the MyoChallenge series, this event attracted almost 70 teams and over 560 submissions globally, uniting a diverse community ranging from physicians and neuroscientists to machine learning experts. The competition facilitated the development of several state-of-the-art control algorithms for a musculoskeletal system capable of sports agility, leveraging techniques such as physics-based motion planners, on-policy behaviour cloning, hierarchical planning, and muscle synergies. By integrating standardized tasks and physiologically realistic models into the open-source framework of MyoSuite, MyoChallenge'25 serves as a reproducible and reusable testbed to accelerate interdisciplinary research across machine learning, biomechanics, sports science, and neuroscience. Project page: https://www.myosuite.org//myochallenge/myochallenge-2025. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language

Authors: Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan, Rashmi Gangadharaiah

Abstract: Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative language absent from all pretraining corpora, and evaluate frontier models zero-shot and fine-tuned Qwen3 (4B, 8B, 32B) on 352 problems. We find that fine-tuning quick… ▽ More Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative language absent from all pretraining corpora, and evaluate frontier models zero-shot and fine-tuned Qwen3 (4B, 8B, 32B) on 352 problems. We find that fine-tuning quickly teaches syntax but fails to transfer semantic competence: Python outperforms PyLang by up to 19% across all configurations, and no intervention (multi-task learning, preference tuning, code infilling, or latent-space objectives) closes the gap. An LLM judge reveals that frontier models select an identical algorithm to Python 80% of the time, yet cannot translate it into a working PyLang implementation., and CKA analysis confirms that fine-tuned models converge to nearly identical internal representations across languages (CKA > 0.97) while diverging at the output stage. We term this the implementation fidelity gap: models possess language-agnostic algorithmic understanding but cannot express it in an unfamiliar language. Our findings highlight the need for training methods that decouple reasoning from language-specific realization. △ Less

Submitted 3 August, 2026; v1 submitted 15 May, 2026; originally announced May 2026.

Comments: Accepted at COLM 2026

LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration

Authors: Jonathan A. Diller, Fernando Cladera, Camillo J. Taylor, Vijay Kumar

Abstract: Traditional autonomous UAV search missions rely on geometric coverage patterns that ignore the semantic context of the target, leading to significant time waste in large-scale environments. In this paper we present LMPath, a pipeline for generating language-mediated exploration priors for Unmanned Aerial Vehicle (UAV) search missions that leverages semantics. Given a basic geofence and an object o… ▽ More Traditional autonomous UAV search missions rely on geometric coverage patterns that ignore the semantic context of the target, leading to significant time waste in large-scale environments. In this paper we present LMPath, a pipeline for generating language-mediated exploration priors for Unmanned Aerial Vehicle (UAV) search missions that leverages semantics. Given a basic geofence and an object of interest prompt, LMPath uses generative language models to determine what regions of the environment should contain that object and a foundation vision model ran over satellite imagery to segment sub-regions that form the exploration prior. This prior can then be used to generate UAV paths with various objectives, such as minimizing the expected time to locate the object of interest, maximizing the probability that the object is found given a limited travel distance, or narrowing down the search space to sub-regions that are most likely to contain the object. To demonstrate it's capabilities, we used LMPath to generate various UAV paths and ran them using a real UAV over large-scale environments. We also ran simulations to demonstrate how paths generated using LMPath outperform traditional path planning approaches for search missions. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: Poster at 2026 AI-Driven Safe Aerial Robotics Workshop

Granite Embedding Multilingual R2 Models

Authors: Parul Awasthy, Aashka Trivedi, Yushu Yang, Ken Barker, Yulong Li, Bhavani Iyer, Martin Franz, Juergen Bross, Meet Doshi, Vignesh P, Vishwajeet Kumar, Todd Ward, Abraham Daniels, Madison Lee, Luis Lastras, Jaydeep Sen, Radu Florian

Abstract: We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support for 52 languages and programming code, a 32,768-token context window (a 64x expansion over R1), and state-of-the-art overall performance across multilingual and c… ▽ More We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support for 52 languages and programming code, a 32,768-token context window (a 64x expansion over R1), and state-of-the-art overall performance across multilingual and cross-lingual text search, code retrieval, long-document search, and reasoning retrieval datasets. The release consists of two bi-encoder models based on the ModernBERT architecture with an expanded multilingual vocabulary: a 311M-parameter full-size, and a 97M-parameter compact model built via model pruning and vocabulary selection that achieves the highest retrieval score of any open multilingual embedding model under 100M parameters. The full-size also supports Matryoshka Representation Learning for flexible embedding dimensionality. Both models are trained on enterprise-appropriate data with governance oversight, and released under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, designed to support responsible use and enable unrestricted research and enterprise adoption. △ Less

Submitted 14 May, 2026; v1 submitted 13 May, 2026; originally announced May 2026.

Dynamic Rank, Basis, and Matching

Authors: Jan van den Brand, Vishal Kumar, Daniel J. Zhang

Abstract: We study dynamic algorithms for maintaining fundamental algebraic properties of matrices, specifically, rank, basis, and full-rank submatrices, with applications to maximum matching on dynamic graphs. Prior dynamic algorithms for rank achieve subquadratic update times but scale with the matrix dimension $n$, and could not always maintain the corresponding objects such as a basis or maximum full-ra… ▽ More We study dynamic algorithms for maintaining fundamental algebraic properties of matrices, specifically, rank, basis, and full-rank submatrices, with applications to maximum matching on dynamic graphs. Prior dynamic algorithms for rank achieve subquadratic update times but scale with the matrix dimension $n$, and could not always maintain the corresponding objects such as a basis or maximum full-rank submatrix. We present the first dynamic rank algorithms whose update time scales with the matrix rank $r$, achieving $\tilde O(r^{1.405})$ time per entry-update and $\tilde O(r^{1.528}+ z)$ per column-update, where $z$ is the number of changed entries. This extends to $\tilde O(|M|^{1.405})$ edge-update time to maintain the size $|M|$ of a maximum matching. We also give dynamic algorithms for maintaining a column-basis subject to column-updates and a maximum full-rank submatrix subject to entry-updates. △ Less

Submitted 10 May, 2026; originally announced May 2026.

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

Authors: Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka, Mausam, N. M. Anoop Krishnan

Abstract: A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery. We identify the following challenges in building and deploying autonomous AI scientists: (1) Problem selection is influenced by the McNamara falla… ▽ More A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery. We identify the following challenges in building and deploying autonomous AI scientists: (1) Problem selection is influenced by the McNamara fallacy; (2) Agents are built on large language models (LLMs) whose training corpora omit tacit procedural and failure knowledge of laboratory practice; (3) Preference optimisation during post-training compresses output diversity toward consensus; and (4) Most scientific benchmarks measure single-turn prediction accuracy and lack feedback from physical experiments back to the computational model. These challenges are not just questions of scale and scaffolding; they require revisiting fundamental design choices. To build truly autonomous AI scientists, we recommend the use of scientific simulations as verifiers for training, the design of persistent world models that represent the shifting objectives governing real investigations, the establishment of a centralized preregistration repository for all AI-generated hypotheses, and application driven by scientific need rather than tool affordance. △ Less

Submitted 9 May, 2026; originally announced May 2026.

MDGYM: Benchmarking AI Agents on Molecular Simulations

Authors: Vinay Kumar, Satyendra Rajput, Mausam, N. M. Anoop Krishnan

Abstract: The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to stress-test this claim; it requires translating physical intuition into syntactically and semantically correct input scripts, reasoning about initial and boundary con… ▽ More The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to stress-test this claim; it requires translating physical intuition into syntactically and semantically correct input scripts, reasoning about initial and boundary conditions, diagnosing numerically unstable trajectories, and interpreting outputs against known physical behavior and laws. We introduce MDGYM, a benchmark of 169 expert-curated MD simulations spanning LAMMPS and GROMACS, two widely used MD packages, across three increasing difficulty levels. We evaluate three agentic frameworks -- Claude Code, Codex, and OpenHands -- with four LLMs, and find that all perform poorly: even the strongest agent solves only 21\% of easy-level tasks, with less than 10\% at higher difficulties. Trajectory analysis reveals a characteristic pattern of failure -- agents successfully invoke simulation machinery but produce physically unstable configurations, fabricate numerical outputs without executing the underlying computation, or abandon tasks prematurely rather than iterating through simulation-specific errors. These failure modes are qualitatively distinct from those observed in general software engineering benchmarks, indicating that fluent code generation does not transfer to grounded physical reasoning. △ Less

Submitted 9 May, 2026; originally announced May 2026.

PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams

Authors: Pranavkumar Mallela, Vinay Kumar, Shashi Shekhar Jha, Shweta Jain

Abstract: Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an acceler… ▽ More Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an accelerated work pace like never before. In classification tasks, where the final output is a single hard label, it is crucial to address the combination of human and model output. Prior work elegantly solves this problem using Bayes rule, using the assumption that human and model output are conditionally independent given the ground truth. Specifically, it discusses a combination method to combine a single deterministic labeler (the human) and a probabilistic labeler (the classifier model) using the model's instance-level and the human's class-level calibrated probabilities. △ Less

Submitted 8 May, 2026; originally announced May 2026.

Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting

Authors: Rishi Ahuja, Kumar Prateek, Simranjit Singh, Vijay Kumar

Abstract: Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history is often just high-frequency noise, not signal. Hence, the proposed work tests whether this premise actually holds by running continuous context architectures (… ▽ More Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history is often just high-frequency noise, not signal. Hence, the proposed work tests whether this premise actually holds by running continuous context architectures (PatchTST included) through the ETTh1 benchmark. The obtained results contradict the premise: an inverse scaling law shows up clearly, with forecasting error rising as context gets longer. A 3,000-step window causes performance to drop by over 68%, evidence that attention mechanisms are poor at ignoring irrelevant historical volatility. Retrieval-Augmented Forecasting (RAFT) is evaluated as an alternative. RAFT achieves a mean squared error (MSE) of 0.379 with a fixed 720-step window and selective retrieval, outperforming both long-context configurations and zero-shot foundation models (Chronos, Moirai) despite requiring far less computation. In addition, the retrieval step injects only the most relevant historical segments as dynamic exogenous variables, which gives the model a context-informed inductive bias it cannot build on its own from raw sequences. Therefore, foundation models going forward need to shift architecturally toward selective retrieval. △ Less

Submitted 6 May, 2026; originally announced May 2026.

CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure

Authors: Eric Ding, Byungsoo Oh, Bhaskar Kataria, Kaiwen Guo, Jelena Gvero, Abhishek Vijaya Kumar, Arjun Devraj, Lindsey Bowen, Atharv Sonwane, Emaad Manzoor, Rachee Singh

Abstract: Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardware accelerators, interconnect bandwidth, software frameworks, parallelism plans, and communication libraries. Current infrastructure evaluation benchmarks publish a small set of end-to-end numbers that do not explain why one configuration o… ▽ More Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardware accelerators, interconnect bandwidth, software frameworks, parallelism plans, and communication libraries. Current infrastructure evaluation benchmarks publish a small set of end-to-end numbers that do not explain why one configuration outperforms another. We present CCL-Bench, a trace-based benchmark that addresses the limitations of existing benchmarks by recording reusable evidence for every ML workload. Each contributed data point in CCL-Bench packages an execution trace, a YAML workload card, and the launch scripts. We have developed a community-extensible toolkit to compute fine-grained compute, memory, and communication efficiency metrics from this evidence. Using CCL-Bench, we surface three claims that summary-statistic benchmarks cannot support: (i) higher compute-communication overlap can coincide with longer training step time and reveal inefficient parallelization choices, (ii) doubling TPU interconnect bandwidth yields a much higher end-to-end improvement in step time than doubling GPU interconnect bandwidth on small and medium workloads, and (iii) the best-tuned configuration on one training framework can run up to 3$\times$ slower than the best-tuned configuration on a peer framework on identical hardware. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Design and Performance Evaluation of a BLE-Based IoT Authentication System

Authors: Nitesh Yadav, Vashisht Kumar, Sachin Kadam

Abstract: Bluetooth Low Energy (BLE) is widely used in modern IoT systems because it consumes very little power, saves energy, and allows for simple device connectivity; however, maintaining security and communication reliability remains a challenge. In this paper, an authentication system is designed using industry-grade BLE-enabled nodes (nRF5340 development kit) that include a peripheral node with a keyp… ▽ More Bluetooth Low Energy (BLE) is widely used in modern IoT systems because it consumes very little power, saves energy, and allows for simple device connectivity; however, maintaining security and communication reliability remains a challenge. In this paper, an authentication system is designed using industry-grade BLE-enabled nodes (nRF5340 development kit) that include a peripheral node with a keypad for entering a PIN and a central node with an LCD display. The entered PIN is sent wirelessly from the peripheral node to the central node via BLE technology, where it is verified in real time and displayed as correct or incorrect. Next, only after successful authentication can the peripheral node send data to the central node. In addition to authentication, the peripheral node can measure temperature in real time using the temperature sensor interfaced to it and send it wirelessly to the central node, where it can be displayed on the LCD interface. Received Signal Strength Indicator (RSSI) values are collected during experiments under various scenarios to evaluate the system's performance. We see that the signal strength (measured in terms of RSSI values) is strong at close range but weak as distance increases, indicating a decaying logarithmic pattern. The system also has low latency, which allows for quick input and output, and it uses PIN-based authentication to ensure security and prevent misuse. The entire system seamlessly integrates communication, sensing, and security, making it suitable for smart access control and wireless monitoring systems, including home automation. △ Less

Submitted 4 May, 2026; originally announced May 2026.

Comments: 6 pages, 8 figures. Submitted a conference, under review

To Use AI as Dice of Possibilities with Timing Computation

Authors: Jia Li, Vipin Kumar, Rui Zhang

Abstract: The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a \emph{grammar of thought}: It leaves \emph{timing} outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from th… ▽ More The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a \emph{grammar of thought}: It leaves \emph{timing} outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from the existing literature: (1) possibility space -- a framework admitting multiple possible timelines for the same event; (2) timing computation -- the treatment of timing as a computable rather than observed dimension; and (3) causal factum -- the maximal causal efficacy recovered by reasoning backward from possible futures, rather than assumed in advance. Together, these definitions dissolve the confounding problem inherent to noun-based causal inference and provide the foundation for a spontaneously growing causal-reasoning world model. As proof of concept, we instantiate the framework and apply it to longitudinal EHR data from 3,276 breast cancer patients, demonstrating for the first time, to our knowledge, automatic trajectory discovery and counterfactual timing deduction (i.e., a What-If Machine) in a purely data-driven manner. △ Less

Submitted 29 July, 2026; v1 submitted 1 May, 2026; originally announced May 2026.

STAR-Filter: Efficient Convex Free-Space Approximation via Starshaped Set Filtering in Noisy Environments

Authors: Yuwei Wu, Yichen Zhao, Dexter Ong, Vijay Kumar

Abstract: Approximating collision-free space is fundamental to robot planning in complex environments. Convex geometric representations, such as polytopes and ellipsoids, are widely employed due to their structural properties, which can be easily integrated with convex optimization. Iterative optimization-based inflation methods can generate large volume polytopes in cluttered environments, but their effici… ▽ More Approximating collision-free space is fundamental to robot planning in complex environments. Convex geometric representations, such as polytopes and ellipsoids, are widely employed due to their structural properties, which can be easily integrated with convex optimization. Iterative optimization-based inflation methods can generate large volume polytopes in cluttered environments, but their efficiency degrades as the obstacle set becomes more complex or when sensor data are noisy. These methods are also sensitive to initialization and often rely on accurate geometric models. In this paper, we propose the STAR-Filter, a lightweight framework that employs starshaped set construction as a fast filter for convex region generation in collision-free space. By identifying obstacle points as active supporting constraints, the proposed method significantly reduces redundant computation while preserving feasibility and robustness to sensor noise. We provide theoretical and numerical analyses that characterize the structural properties of the starshaped set and proposed pipeline in environments of varying complexity. Simulation results show that the proposed framework achieves the lowest computation time and reduces conservativeness in polytope generation for real-world noisy and large-scale data. We demonstrate the effectiveness of the framework for Safe Flight Corridor (SFC) generation and agile quadrotor planning in noisy environments. △ Less

Submitted 29 April, 2026; originally announced April 2026.

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

Authors: Vishesh Kumar, Akshay Agarwal

Abstract: The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the attachment of patches to clean images, known as an adversarial patch attack. Similarly, natural noises such as Gaussian and Salt\&Pepper are highly prevalent in the re… ▽ More The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the attachment of patches to clean images, known as an adversarial patch attack. Similarly, natural noises such as Gaussian and Salt\&Pepper are highly prevalent in the real world. The current research need arises from the above vulnerabilities and the lack of efforts to tackle these two singularities independently and, especially, in combination. In this research, we have, for the first time, combined these two prominent singularities and proposed a novel dataset. Using this dataset, we have conducted a benchmark study of singularity data-point detection using features from several convolutional neural networks. For classification, rather than the popular neural network-based parameter tuning, we have used traditional yet effective machine learning classifiers. The extensive experiments across various in- and out-of-distribution (OOD) singularities reveal several interesting findings about the effectiveness of classifiers and show that it is hard to defend against adversaries when they are treated independently, and inefficient classifiers are selected. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Comments: Accepted at AISTATS 2026

DistortBench: Benchmarking Vision Language Models on Image Distortion Identification

Authors: Divyanshu Goyal, Akhil Eppa, Vanya Bannihatti Kumar

Abstract: Vision-language models (VLMs) are increasingly used in settings where sensitivity to low-level image degradations matters, including content moderation, image restoration, and quality monitoring. Yet their ability to recognize distortion type and severity remains poorly understood. We present DistortBench, a diagnostic benchmark for no-reference distortion perception in VLMs. DistortBench contains… ▽ More Vision-language models (VLMs) are increasingly used in settings where sensitivity to low-level image degradations matters, including content moderation, image restoration, and quality monitoring. Yet their ability to recognize distortion type and severity remains poorly understood. We present DistortBench, a diagnostic benchmark for no-reference distortion perception in VLMs. DistortBench contains 13,500 four-choice questions covering 27 distortion types, six perceptual categories, and five severity levels: 25 distortions inherit KADID-10k calibrations, while two added rotation distortions use monotonic angle-based levels. We evaluate 18 VLMs, including 17 open-weight models from five families and one proprietary model. Despite strong performance on high-level vision-language tasks, the best model reaches only 61.9% accuracy, just below the human majority-vote baseline of 65.7% (average individual: 60.2%), indicating that low-level perceptual understanding remains a major weakness of current VLMs. Our analysis further reveals weak and non-monotonic scaling with model size, performance drops in most base--thinking pairs, and distinct severity-response patterns across model families. We hope DistortBench will serve as a useful benchmark for measuring and improving low-level visual perception in VLMs. △ Less

Submitted 21 April, 2026; originally announced April 2026.

Agentic Risk-Aware Set-Based Engineering Design

Authors: Varun Kumar, George Em Karniadakis

Abstract: This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a human-in-the-loop paradigm and demonstrated on the canonical problem of aerodynamic airfoil design, the framework employs a team of specialized agents: a Coding Assi… ▽ More This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a human-in-the-loop paradigm and demonstrated on the canonical problem of aerodynamic airfoil design, the framework employs a team of specialized agents: a Coding Assistant, a Design Agent, a Systems Engineering Agent, and an Analyst Agent - all coordinated by a human Manager. Integrated within a set-based design philosophy, the process begins with a collaborative phase where the Manager and Coding Assistant develop a suite of validated tools, after which the agents execute a structured workflow to systematically explore and prune a large set of initial design candidates. A key contribution of this work is the explicit integration of formal risk management, employing the Conditional Value-at-Risk (CVaR) as a quantitative metric to filter designs that exhibit a high probability of failing to meet performance requirements, specifically the target coefficient of lift. The framework automates labor-intensive initial exploration through a global sensitivity analysis conducted by the Analyst agent, which generates actionable heuristics to guide the other agents. The process culminates by presenting the human Manager with a curated final set of promising design candidates, augmented with high-fidelity Computational Fluid Dynamics (CFD) simulations. This approach effectively leverages AI to handle high-volume analytical tasks, thereby enhancing the decision-making capability of the human expert in selecting the final, risk-assessed design. △ Less

Submitted 17 April, 2026; originally announced April 2026.

A Novel Framework for Transmitter Privacy in Integrated Sensing and Communication

Authors: Vaibhav Kumar, Ahmad Bazzi, Christina Pöpper, Marwa Chafii

Abstract: ISAC systems introduce new privacy risks because an unintended sensing node may exploit the shared radio waveform to infer transmitter-related information even when the communication payload remains secure. This paper investigates transmitter privacy, defined as limiting unauthorized inference of transmitter-related information through channel estimation, in a RIS-aided multi-antenna wireless syst… ▽ More ISAC systems introduce new privacy risks because an unintended sensing node may exploit the shared radio waveform to infer transmitter-related information even when the communication payload remains secure. This paper investigates transmitter privacy, defined as limiting unauthorized inference of transmitter-related information through channel estimation, in a RIS-aided multi-antenna wireless system with a transmitter, a legitimate receiver, a malicious sensor, and a RIS. The malicious sensor is assumed to estimate the transmitter--sensor channel, and the resulting channel state information can then support unauthorized sensing, inference, or related signal processing. To mitigate this threat, we consider a privacy-oriented design in which the transmitter adopts superposition-based signaling with a message signal and transmit-side artificial noise, while the RIS shapes the propagation environment in a privacy-aware manner. The channel-estimation performance at the malicious sensor is first analyzed under imperfect prior knowledge, and both the true and predicted mean-square-error expressions are derived. Based on this analysis, we formulate a joint active--passive beamforming design problem that maximizes the malicious sensor's predicted channel-estimation error subject to a communication quality-of-service constraint, a transmit-power budget, and the unit-modulus constraints of the RIS. The resulting non-convex problem is handled through a numerically efficient alternating-optimization framework based on an augmented Lagrangian reformulation. Numerical results show that RIS-assisted propagation shaping can substantially degrade unauthorized channel estimation relative to the non-RIS case while preserving reliable communication, and further show that the privacy gains also improve a more direct sensing metric, namely the malicious sensor's angle-of-arrival estimation accuracy. △ Less

Submitted 17 April, 2026; originally announced April 2026.

Comments: 13 pages, 9 figures

BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows

Authors: Elaine Lau, Markus Dücker, Ronak Chaudhary, Hui Wen Goh, Rosemary Wei, Vaibhav Kumar, Saed Qunbar, Guram Gogia, Yi Liu, Scott Millslagle, Nasim Borazjanizadeh, Ulyana Tkachenko, Samuel Eshun Danquah, Collin Schweiker, Vijay Karumathil, Asrith Devalaraju, Varsha Sandadi, Haemi Nam, Punit Arani, Ray Epps, Abdullah Arif, Sahil Bhaiwala, Curtis Northcutt, Skyler Wang, Anish Athalye , et al. (2 additional authors not shown)

Abstract: Existing AI benchmarks lack the fidelity to assess economically meaningful progress on professional workflows. To evaluate frontier AI agents in a high-value, labor-intensive profession, we introduce BankerToolBench (BTB): an open-source benchmark of end-to-end analytical workflows routinely performed by junior investment bankers. To develop an ecologically valid benchmark grounded in representati… ▽ More Existing AI benchmarks lack the fidelity to assess economically meaningful progress on professional workflows. To evaluate frontier AI agents in a high-value, labor-intensive profession, we introduce BankerToolBench (BTB): an open-source benchmark of end-to-end analytical workflows routinely performed by junior investment bankers. To develop an ecologically valid benchmark grounded in representative work environments, we collaborated with 502 investment bankers from leading firms. BTB requires agents to execute senior banker requests by navigating data rooms, using industry tools (market data platform, SEC filings database), and generating multi-file deliverables--including Excel financial models, PowerPoint pitch decks, and PDF/Word reports. Completing a BTB task takes bankers up to 21 hours, underscoring the economic stakes of successfully delegating this work to AI. BTB enables automated evaluation of any LLM or agent, scoring deliverables against 100+ rubric criteria defined by veteran investment bankers to capture stakeholder utility. Testing 9 frontier models, we find that even the best-performing model (GPT-5.4) fails nearly half of the rubric criteria and bankers rate 0% of its outputs as client-ready. Our failure analysis reveals key obstacles (such as breakdowns in cross-artifact consistency) and improvement directions for agentic AI in high-stakes professional workflows. △ Less

Submitted 13 April, 2026; originally announced April 2026.

FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception

Authors: Rahul Ahuja, Mudit Jain, Bala Murali Manoghar Sai Sudhakar, Venkatraman Narayanan, Pratik Likhar, Varun Ravi Kumar, Senthil Yogamani

Abstract: Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial representations assume the rectilinear geometry of pinhole cameras. Fisheye cameras, widely deployed on production autonomous vehicles for their surround-view coverage, exhibit severe radial distortion that renders these representations geometrically in… ▽ More Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial representations assume the rectilinear geometry of pinhole cameras. Fisheye cameras, widely deployed on production autonomous vehicles for their surround-view coverage, exhibit severe radial distortion that renders these representations geometrically inconsistent. At the same time, the scarcity of large-scale fisheye annotations makes retraining foundation models from scratch impractical. We present \ours, a lightweight framework that adapts frozen VFMs to fisheye geometry through two components: a frozen DINOv2 backbone with Low-Rank Adaptation (LoRA) that transfers rich self-supervised features to fisheye without task-specific pretraining, and Fisheye Rotary Position Embedding (FishRoPE), which reparameterizes the attention mechanism in the spherical coordinates of the fisheye projection so that both self-attention and cross-attention operate on angular separation rather than pixel distance. FishRoPE is architecture-agnostic, introduces negligible computational overhead, and naturally reduces to the standard formulation under pinhole geometry. We evaluate \ours on WoodScape 2D detection (54.3 mAP) and SynWoodScapes BEV segmentation (65.1 mIoU), where it achieves state-of-the-art results on both benchmarks. △ Less

Submitted 11 April, 2026; originally announced April 2026.

Planted clique detection and recovery from the hypergraph adjacency matrix

Authors: Kalle Alaluusua, B. R. Vinay Kumar

Abstract: Hypergraph data are often projected onto a weighted graph by constructing an adjacency matrix whose $(i,j)$ entry counts the number of hyperedges containing both nodes $i$ and $j$. This reduction is computationally convenient, but it can lose information: distinct hypergraphs may induce the same matrix, and the matrix entries are generally dependent because each hyperedge contributes to multiple p… ▽ More Hypergraph data are often projected onto a weighted graph by constructing an adjacency matrix whose $(i,j)$ entry counts the number of hyperedges containing both nodes $i$ and $j$. This reduction is computationally convenient, but it can lose information: distinct hypergraphs may induce the same matrix, and the matrix entries are generally dependent because each hyperedge contributes to multiple pairs. We study the planted clique problem under this matrix-only observation model. For detection, we show that a spectral norm test is asymptotically powerful at the $\sqrt{n}$ scale, with explicit dependence on the background hyperedge probability $p$. For recovery, we analyze a polynomial-time spectral method based on the leading eigenvector and prove exact recovery at the canonical $\sqrt{n}$ scale, again with explicit dependence on $p$. We also extend both results to sparse regimes in which the hyperedge probability may depend on \(n\). Our analysis adapts a leave--one--out eigenvector framework to this setting. These results provide rigorous detection and recovery guarantees when only the adjacency matrix is observed. △ Less

Submitted 17 April, 2026; v1 submitted 9 April, 2026; originally announced April 2026.

Comments: 45 pages. This revision fixes a measurability issue in the leave--one--out proof by separating a measurable eigenvector representative from the subsequent sign choice. It also removes an unnecessary factor left over from an earlier modification, which makes the argument more transparent

MSC Class: 05C80; 05C65; 05C69; 60B20; 62F03

CODESTRUCT: Code Agents over Structured Action Spaces

Authors: Myeongsoo Kim, Joe Hsu, Dingmin Wang, Shweta Garg, Varun Kumar, Murali Krishna Ramanathan

Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CODESTRUCT, provides readCode for retrieving complete syntactic units and ed… ▽ More LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CODESTRUCT, provides readCode for retrieving complete syntactic units and editCode for applying syntax-validated transformations to semantic program elements. Evaluated on SWE-Bench Verified across six LLMs, CODESTRUCT improves Pass@1 accuracy by 1.2-5.0% while reducing token consumption by 12-38% for most models. Models that frequently fail to produce valid patches under text-based interfaces benefit most: GPT-5-nano improves by 20.8% as empty-patch failures drop from 46.6% to 7.2%. On CodeAssistBench, we observe consistent accuracy gains (+0.8-4.4%) with cost reductions up to 33%. Our results show that structure-aware interfaces offer a more reliable foundation for code agents. △ Less

Submitted 16 April, 2026; v1 submitted 6 April, 2026; originally announced April 2026.

Comments: Accepted at ACL 2026 main conference

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code

Authors: Myeongsoo Kim, Dingmin Wang, Siwei Cui, Farima Farmahinifarahani, Terry Yue Zhuo, Shweta Garg, Baishakhi Ray, Rajdeep Mukherjee, Varun Kumar

Abstract: Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free decomposition of agent trajectories into reference-patch-aligned search, read, and edit stages, and apply it across 16,758 trajectories spanning three architectur… ▽ More Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free decomposition of agent trajectories into reference-patch-aligned search, read, and edit stages, and apply it across 16,758 trajectories spanning three architectures and seven models. The dominant failure of capable models is not localization: 60-69% of failures on SWE-Agent and OpenHands reach and edit the correct functions yet still produce incorrect patches, and the pattern persists for most models on the bash-only LiveSWEAgent. Within this Edit-Quality residual, we identify Coherence Collapse, where the agent reaches correct code and then overwrites or thrashes it, as the largest theme, replicating across SWE-bench Verified and the multilingual PolyBench Verified. In 5 cases, the agent produces a patch bit-identical to the gold reference mid-trajectory and destroys it later; an edit-commit checkpoint recovers all 5 against the SWE-bench Docker harness. A reference-free consensus-driven variant yields a directional +3.0 pp Pass@1 measurement on GPT-5 (p=0.08). △ Less

Submitted 26 May, 2026; v1 submitted 25 March, 2026; originally announced March 2026.

MuViS: Multimodal Virtual Sensing Benchmark

Authors: Jens U. Brandt, Noah C. Puetz, Jobel Jose George, Niharika Vinay Kumar, Elena Raponi, Marc Hilbert, Thomas Bäck, Thomas Bartz-Beielstein

Abstract: Virtual sensing aims to infer hard-to-measure quantities from accessible measurements and is central to perception and control in physical systems. Despite rapid progress from first-principle and hybrid models to modern data-driven methods research remains siloed, leaving no established default approach that transfers across processes, modalities, and sensing configurations. We introduce MuViS, a… ▽ More Virtual sensing aims to infer hard-to-measure quantities from accessible measurements and is central to perception and control in physical systems. Despite rapid progress from first-principle and hybrid models to modern data-driven methods research remains siloed, leaving no established default approach that transfers across processes, modalities, and sensing configurations. We introduce MuViS, a domain-agnostic benchmarking suite for multimodal virtual sensing that consolidates diverse datasets into a unified interface for standardized preprocessing and evaluation. Using this framework, we benchmark established approaches spanning gradient-boosted decision trees and deep neural network (NN) architectures, and show that none of these provides a universal advantage, underscoring the need for generalizable virtual sensing architectures. MuViS is released as an open-source, extensible platform for reproducible comparison and future integration of new datasets and model classes. △ Less

Submitted 12 May, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

Comments: Accepted at European Signal Processing Conference (EUSIPCO) 2026

TrustFed: Enabling Trustworthy Medical AI under Data Privacy Constraints

Authors: Vagish Kumar, Syed Bahauddin Alam, Souvik Chakraborty

Abstract: Protecting patient privacy remains a fundamental barrier to scaling machine learning across healthcare institutions, where centralizing sensitive data is often infeasible due to ethical, legal, and regulatory constraints. Federated learning offers a promising alternative by enabling privacy-preserving, multi-institutional training without sharing raw patient data; however, real-world deployments f… ▽ More Protecting patient privacy remains a fundamental barrier to scaling machine learning across healthcare institutions, where centralizing sensitive data is often infeasible due to ethical, legal, and regulatory constraints. Federated learning offers a promising alternative by enabling privacy-preserving, multi-institutional training without sharing raw patient data; however, real-world deployments face severe challenges from data heterogeneity, site-specific biases, and class imbalance, which degrade predictive reliability and render existing uncertainty quantification methods ineffective. Here, we present TrustFed, a federated uncertainty quantification framework that provides distribution-free, finite-sample coverage guarantees under heterogeneous and imbalanced healthcare data, without requiring centralized access. TrustFed introduces a representation-aware client assignment mechanism that leverages internal model representations to enable effective calibration across institutions, along with a soft-nearest threshold aggregation strategy that mitigates assignment uncertainty while producing compact and reliable prediction sets. Using over 430,000 medical images across six clinically distinct imaging modalities, we conduct one of the most comprehensive evaluations of uncertainty-aware federated learning in medical imaging, demonstrating robust coverage guarantees across datasets with diverse class cardinalities and imbalance regimes. By validating TrustFed at this scale and breadth, our study advances uncertainty-aware federated learning from proof-of-concept toward clinically meaningful, modality-agnostic deployment, positioning statistically guaranteed uncertainty as a core requirement for next-generation healthcare AI systems. △ Less

Submitted 23 March, 2026; originally announced March 2026.

Internet-Scale Measurement of React2Shell Exploitation Using an Active Network Telescope

Authors: Aakash Singh, Kuldeep Singh Yadav, Md Talib Hasan Ansari, V. Anil Kumar

Abstract: The increasing adoption of server-side component-based web frameworks has introduced new application-layer attack surfaces that remain insufficiently understood at Internet scale. On 3 December 2025, a critical remote code execution vulnerability (CVE-2025-55182) in React Server Components, referred to as React2Shell, was publicly disclosed and subsequently observed being exploited in the wild. De… ▽ More The increasing adoption of server-side component-based web frameworks has introduced new application-layer attack surfaces that remain insufficiently understood at Internet scale. On 3 December 2025, a critical remote code execution vulnerability (CVE-2025-55182) in React Server Components, referred to as React2Shell, was publicly disclosed and subsequently observed being exploited in the wild. Despite its critical severity and a CVSS base score of 10.0, there is limited empirical understanding of how this vulnerability is exploited across the Internet. This paper presents the first Internet-scale measurement study of React2Shell exploitation activity using traffic collected from an Active Network Telescope. We developed a deterministic detection methodology that identifies exploitation attempts targeting endpoints implementing React Server components. It helped analyze exploitation traffic to characterize its temporal evolution, geographic and autonomous system-level distribution, and behavioral properties of the observed scanning activity. In addition, exploit payloads are examined to understand the attacker infrastructure and delivery mechanisms. The analysis reported rapid post-disclosure exploitation activity exhibiting patterns consistent with automated scanning campaigns, geographically distributed scanners, and concentrated backend infrastructure. To the best of our knowledge, this work provides the first quantitative characterization of React2Shell-triggered scanning activity, including the number of distinct scanners, their geographic and autonomous system distribution, and the scale of backend infrastructure involved in exploitation attempts. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes

Authors: Aleksei Rozanov, Arvind Renganathan, Vipin Kumar

Abstract: Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements. Existing data-driven upscaling products often fail to generalize beyond observed domains, leading to systematic regional biases and high predictive uncertainty. We introduce Task-Aware Modulation with… ▽ More Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements. Existing data-driven upscaling products often fail to generalize beyond observed domains, leading to systematic regional biases and high predictive uncertainty. We introduce Task-Aware Modulation with Representation Learning (TAM-RL), a framework that couples spatio-temporal representation learning with knowledge-guided encoder-decoder architecture and loss function derived from the carbon balance equation. Across 150+ flux tower sites representing diverse biomes and climate regimes, TAM-RL improves predictive performance relative to existing state-of-the-art datasets, reducing RMSE by 8-9.6% and increasing explained variance (R2) from 19.4% to 43.8%, depending on the target flux. These results demonstrate that integrating physically grounded constraints with adaptive representation learning can substantially enhance the robustness and transferability of global carbon flux estimates. △ Less

Submitted 11 March, 2026; v1 submitted 10 March, 2026; originally announced March 2026.

Comments: Accepted to the KGML Bridge at AAAI 2026 (non-archival)