Computer Vision · Cross-listed from eess.IV
A deep dictionary network-based foundation model for ultra-low-dose CT denoising
Baoshun Shi, Shuangyi Yang, Ke Jiang et al. (+3 more)
Ultra-low-dose computed
tomography (ULDCT) reduces radiation exposure but suffers from severe noise that degrades diagnostic image quality. Existing deep learning-based denoising methods are typically trained in an organ-specific fashion, resulting in limited generalization across heterogeneous multi?organ imaging scenarios. Foundation models present a promising all-in-one paradigm for unified multi-organ denoising. However, their architectures suffer from poor interpretability and rely on heuristic training strategies. To address these limitations, we propose an architecture?interpretable foundation model based on the deep dictionary network (DDN) for unified multi-organ ULDCT denoising. Inspired by multilayer sparse representation theory, DDN cascades convolutional sparse coding layers with iterative soft-thresholding, providing inherent architectural interpretability. Furthermore, a dynamic dictionary module and a threshold generation module are embedded within each layer to enhance representation ability. We conduct DDN pre-training on more than one million multi-organ normal-dose CT images by recovering clean images from Gaussian-noised inputs. Sparse regularization is additionally imposed on latent feature representations, guiding the network to learn compact and noise-robust priors. The complete architecture is jointly fine-tuned on multi-organ ULDCT
datasets, enabling a single unified model to perform denoising across diverse anatomical regions. Extensive experiments validate that our proposed method achieves state-of-the?art performance and consistently surpasses competing ULDCT methods across all mul
Read the full abstract ▾
All authors Baoshun Shi, Shuangyi Yang, Ke Jiang, Bin Zhu, Zhanli Hu, Huazhu Fu
Machine Learning
AttnFuse: A Composable DSL for Compiling Attentions to Fused GPU Kernels
Varun Kumar Dasoju and Tian Zhao
Modern AI systems are built on the
Transformer architecture, whose core operation,
attention, accounts for the majority of computation and
memory cost. Researchers continually propose new
attention variants to improve quality, efficiency, or context length, but each variant currently requires expert-written GPU code to run at usable speeds. PyTorch's recent flex\_
attention lets researchers describe custom
attention patterns in Python and compile them to fused kernels, but its design is limited to modifications applied after the central
matrix multiplication, excluding Rotary Position
Embedding (RoPE), the positional encoding used by every major LLM. We introduce AttnFuse, a small DSL for
attention that makes pre-multiplication transformations like RoPE first-class operations. Researchers compose ten high-level building blocks to describe a variant, and AttnFuse's compiler emits a single fused GPU kernel for the entire computation. On an RTX 3090, AttnFuse achieves a 2.10$\times$ speedup over flex\_
attention on the RoPE+causal pattern. On an H100, it runs a full Llama-3-8B training step within 5% of PyTorch's hand-tuned backend. Our investigation reveals the Rotation Calculus: whether to fuse RoPE or apply it separately depends on the GPU's compute-to-bandwidth ratio, with a derived crossover that matches measurement. AttnFuse demonstrates that a small,
attention-specific compiler can close the gap between flexible research code and production kernels.
Read the full abstract ▾
Computation and Language
In the Blind: Building Pseudo-References for MT Evaluation
Diptesh Kanojia, Chi-kiu Lo, Archchana Sindhujan et al. (+3 more)
The WMT26 General MT task evaluates systems on 10
language pairs that have no human references (neither translated from scratch nor post-edited from MT output by humans). We describe how we built the pseudo-references for these pairs and six other
language pairs (in which some forms of human references are available): seven models translate the 3,277 official documents under up to five
prompt conditions, giving a total of 26 system-
prompt combinations; then three reference-free quality estimation (QE) models score every candidate; and a per-document selector picks one translation, which GPT-5.5 post-edits where needed. Working without references exposed a failure mode of QE-guided selection: the metrics rank fluent output in the wrong
language above correct translations. Adding a confidence-scaled
language identification penalty to the score fusion drives the wrong-
language count to zero, and the resulting selector still scores better on MetricX than the rank-fusion baseline it replaces. Since no references were available for these pairs while we were building them, we calibrate every selection decision on last year's WMT25 human judgments. The human evaluation, released after construction, shows the cost of getting selection wrong: our references stand with the strongest participating systems when the selector kept a frontier-model candidate, and fall up to 17 ESA points below them when it did not. We release the selection method and the provenance of every reference (https://github.com/surrey-nlp/PseudoRef)
Read the full abstract ▾
All authors Diptesh Kanojia, Chi-kiu Lo, Archchana Sindhujan, Samuel Larkin, Greg Hanneman, Alon Lavie
Information Theory · Cross-listed from math.CO
A lattice family with kissing numbers $\tau(\mathcal{L}_n) \ge e^{2 \sqrt{n}}$
Thijs Laarhoven and Scott Duke Kominers
For all
prime powers $q\geq5$, we construct
lattices $\mathcal{L}_q\subseteq\mathbb{Z}^q$ with kissing numbers \[ \tau(\mathcal{L}_q)\geq \left(\frac{1}{2\pi e^2}+o(1)\right)\sqrt{q}\,e^{2\sqrt{q}}. \] The same asymptotic bound holds on a set of integer dimensions of natural density $1$, and in every sufficiently large integer dimension $n$ with an additional factor $e^{-\tfrac{1}{2}n^{1/40}}$. The construction is an extension of a previous construction by Bennett-Peikert based on Reed-Solomon codes.
Read the full abstract ▾
Robotics
From Vision to Harvest: Benchmarking Vision-Language Models for Multi-Arm Robotic Fruit Harvesting
Vrishan Inukollu, Adyan Zaman, Anvi Kudaraya et al. (+4 more)
Multi-arm robotic harvesting offers a promising path to improve harvesting efficiency and reduce reliance on manual labor. However, practical deployment remains challenging because the system must generalize across diverse environments while efficiently coordinating multiple arms in a shared workspace. Existing methods often require substantial data collection in target environments or rely on simplifying assumptions that limit planning quality. In this work, we introduce the first comprehensive
benchmark for evaluating pretrained
Vision-
Language Models (VLMs) on zero-shot multi-arm fruit harvesting planning. Our
benchmark uses real-world apple and citrus orchard images and compares a VLM-based planning pipeline with a traditional perception-and-planning pipeline. The VLM pipeline directly generates harvesting sequences and waypoints for each arm, while a lightweight trajectory verifier checks for collisions. Our results show that frontier VLMs can generate effective multi-arm harvesting plans zero-shot, but a practical deployment remains limited by accurate 3D waypoint generation and collision-aware coordination. These results highlight both the promise and current limitations of pretrained VLMs for multi-arm robotic harvesting.
Read the full abstract ▾
All authors Vrishan Inukollu, Adyan Zaman, Anvi Kudaraya, Carlos Lazcano, Yuankai Zhu, Stavros Vougioukas, Xiaofan Yu
Artificial Intelligence
$\tau$-Elicitation: Benchmarking multi-turn entity extraction in voice agents
Soham Ray and Victor Barres
Voice
agents often need to collect names, addresses, identifiers, dates, and times exactly, yet end-to-end
benchmarks obscure where capture fails. We introduce $\tau$-Elicitation, a 200-task voice
benchmark spanning 10 entity types, controlled difficulty, caller realisms, and three environments. A matched text
agent passes all tasks, but four voice configurations achieve robust exact success from 0.14 to 0.41.
Agents increase verification for hard and unfamiliar entities and sometimes for incorrect captures, but not for their weakest caller voice; only 24 to 37 percent of verified errors are repaired. A scaffold that prescribes spelling, read-back, correction, and confirmation raises robust Pass$^3$ by 14 to 31 points, at a cost of 21 to 28 seconds per call. Realisms such as spelling variations and restarts do not detectably affect exact success; mispronunciation increases repair effort. These results identify strategy selection and successful recovery as the central bottlenecks in exact spoken entity collection.
Read the full abstract ▾
Cryptography and Security
Mind the Gap: Detecting Description-Execution Mismatch Attacks in DAO Governance
Bowen Cai, Nanzi Yang, Weiheng Bai et al. (+3 more)
Decentralized autonomous organizations (DAOs) change protocols through a proposal-based process: initiators submit a proposal, members vote on it based on its natural-
language description, and if it passes, the project executes the code behind it. This process is inherently vulnerable to deceptive proposals, where the described intent and the actual code execution mismatch. A malicious proposer can submit a benign-looking description to pass voting while the executed code transfers funds or seizes control of the protocol, which we call a Description-Execution Mismatch (DEMI) attack. We present the first systematic framework for DEMI detection in real DAO governance. First, the diversity of DAO deployments makes a unified, scalable analysis difficult; we address this with a DAO-agnostic simulation framework that builds a per-DAO governance profile from historical on-chain transactions and then drives each new proposal through the full governance lifecycle to obtain its execution behavior. Second, free-form descriptions and structured execution traces are hard to compare; we address this with an evidence-mapping paradigm that requires an LLM to locate explicit per-action textual justifications rather than issue a holistic judgment, substantially improving precision and recall over direct querying. On a large-scale
dataset of real-world Ethereum DAO governance, our simulation derives execution results for 92.7% of active DAOs and 89.3% of executed proposals, far exceeding existing platforms. Our detector reaches 81.7% mean precision and 98.3% mean recall under stratified cross-validation, and evidence mapping generalizes across LLM vendors rather than depending on one model. Under a systematic red-team/blue-team evaluation, the Robustness Guard defends most adaptive attacks even against an adversary that knows the detector, and this robustness generalizes to held-out proposals.
Read the full abstract ▾
All authors Bowen Cai, Nanzi Yang, Weiheng Bai, Youshui Lu, Yajin Zhou, Kangjie Lu
Human-Computer Interaction
Reconceptualizing Age Assurance as a Sociotechnical Problem: Connecting Evidence, Evaluation, Claims, and Decisions
Renkai Ma, Prakriti Dumaru, Thomas Synaepa-Addison et al. (+2 more)
Age verification is often treated as a technical problem: can a system determine a child's age accurately? We argue this framing is too narrow. Age assurance becomes consequential when evidence is evaluated, translated into age-related claims, and used to decide whether a person can access, purchase, or belong. We review 85 publications on children's age assurance published from 2020 through February 2026. We find that shared terms such as age verification describe different processes. Age is represented as threshold eligibility or inferred estimation, and the same eligibility claim can arise from different evidence and components. Rights, access, and
privacy receive more
attention than accuracy, error, and
fairness; yet institutional actors are rarely connected to system failures or user remedies, an accountability gap. We introduce the Age-Assurance Process Framework, which treats age assurance as a sociotechnical process connecting evidence, evaluation, claims, and decisions rather than reducing it to a technical problem.
Read the full abstract ▾
All authors Renkai Ma, Prakriti Dumaru, Thomas Synaepa-Addison, Jess Kropczynski, Pamela J. Wisniewski
Symbolic Computation
Certified local rank and uniqueness barriers for a 48-term matrix-multiplication decomposition
Abhinav Agarwal
We study replacements in fixed bilinear tensor decompositions, counting changes to complete rank-one summands, including output factors. The shortening frontier records the maximum rank defect of a fixed-size subset and determines the minimum length attainable within a change budget. For the rational 48-term Li–Wang–Hu decomposition \(D(2)\) of \(4\times4\)
matrix multiplication over \(\mathbb{C}\), we prove rank radius at least 12, strong radius exactly 11, and border radius at least 8. Every shorter complex decomposition therefore changes at least thirteen original summands. An exact rational twelve-term replacement attains the equal-length barrier. The proofs combine exhaustive support reductions with saturated projected kernels and zero-corner completion arguments controlling arbitrary minimal competitors. A reduced-incidence argument transfers kernel certificates to tensor-space neighborhoods. A Laurent normal form gives strong radius exactly 11 for the sixteen-term core at every nonzero complex parameter. On a nonempty Zariski-open subset of the actual parameter curve, the rank radius is at least 12, the strong radius exactly 11, and the border radius at least 8. We also prove incomparability of the full Kothari–Moitra–Wein sufficient criterion and the Sylvester-equipped kernel criterion. These results describe local decomposition structure rather than a new rank bound for full
matrix multiplication.
Read the full abstract ▾
Sound
Predictive audio representations for early detection and tracking of hidden dynamic objects
Katerina Vinciguerra, Moritz Brandes, Danilo Hollosi et al. (+1 more)
Predicting potential dangers is core to safety.
Forecasting the presence of other traffic
agents is core to danger prediction. Occluded traffic
agents challenge detection systems as they might become visible too late, leaving the autonomous vehicle too little time to identify, plan and act accordingly in a robust and safe way. Previous works proved that auditory perception, being omnidirectional and not constrained by a field-of-view, provides fundamental cues for early spotting of different road users, even when hidden by other vehicles or infrastructures. Yet, those contributions deal with scenarios with only one vehicle present, and they either identify the type of vehicle or estimate its direction of arrival. In this work, we move forward, and propose a multi-task system which, simultaneously, estimates the number of vehicles present, their type, and their direction of arrival. Our methodological contribution is a two-stage pipeline: a self-supervised pre-training stage inspired by the Joint-
Embedding Predictive Architecture (JEPA) applied directly to multichannel raw waveforms, followed by supervised multi-task fine-tuning with a bidirectional LSTM and three classification heads. The pre-training stage trains the encoder without labels, pushing it to predict the latent representation of a future audio segment from its past context. To train and test our framework, since no suitable
dataset was publicly available, we collected an ad-hoc one covering Non-Line-Of-Sight scenarios with multiple traffic
agents simultaneously operating. Experimental evaluation shows that our method outperforms the state of the art; it also proves that our design choice allows the model to learn robust representations, which can be transferred to an unseen driving scenario, maintaining reasonable and stable performance.
Read the full abstract ▾
All authors Katerina Vinciguerra, Moritz Brandes, Danilo Hollosi, Letizia Marchegiani
Distributed Computing
BOOST: Concurrent Access to Host Memory and HBM to Accelerate LLM Inference
Anish Saxena, Jae Hyung Ju, Hritvik Taneja et al. (+4 more)
GPU
memory bandwidth and capacity limit throughput in large
language model (LLM) inference. The GPU
memory system consists of a primary tier of high-bandwidth
memory (HBM) and a secondary tier of host
memory connected via CPU-to-GPU interconnect. Current serving systems treat the tiers hierarchically: they serve exclusively from HBM when data fits, and otherwise prefetch data from host
memory to HBM before use. In both cases, the host
memory bandwidth is never well utilized. Prefetching expands capacity by utilizing host
memory, but consumes HBM bandwidth for writes, reducing the bandwidth available for demand loads. We observe that fully utilizing both host and HBM bandwidth requires each wave of GPU threadblocks to access both tiers concurrently and in proportion to their bandwidth ratio. Existing bandwidth-proportional placement strategies fail to provide concurrency because they are not aware of GPU waves, and the large 2MB GPU page size. This paper presents BOOST, the first runtime system that provides concurrent and proportional access to both GPU
memory tiers, extracting the combined bandwidth of host
memory and HBM for LLM inference without kernel changes. The key insight in BOOST is to use kernel access patterns to make page allocation and runtime data management wave-aware. For static model weights, BOOST applies modulo-based page placement that eliminates access-ratio variance; for dynamically provisioned
attention key-value (KV) pairs, it makes the free KV page pool wave-aware. We integrate BOOST into vLLM and evaluate on a Grace Hopper system. At iso-batch size, BOOST improves Time-per-Output-
Token (TPOT) by 4.3% over HBM-only serving, whereas prefetching degrades TPOT by 6%. In high-throughput serving, BOOST improves throughput by 31% on average, outperforming prefetching by 15%.
Read the full abstract ▾
All authors Anish Saxena, Jae Hyung Ju, Hritvik Taneja, Po-An Tsai, Aamer Jaleel, Christos Kozyrakis, Moinuddin Qureshi
Systems and Control
Predicted-Flow Control Barrier Functions for Non-Control-Affine Systems
Amirsaeid Safari and Jesse B. Hoagg
Control barrier functions (CBFs) enforce safety through conditions imposed pointwise in time without consideration of state
evolution over a future horizon. Thus, CBF-based controls are typically myopic. Predicted-flow CBFs (P-CBFs) generalize CBFs from a function of the current state to a functional of the predicted flow under a parametrized control. P-CBFs can certify safety over the entire prediction horizon while simultaneously allowing for performance optimization over the horizon. However, prior work with P-CBFs only applies to control-affine systems, and suffers from a limitation where the prediction horizon can shrink or even vanish. This article addresses both of these shortcomings by introducing a planning control that smoothly transitions from a parametric plan to a backup control (if needed) and a time-shift parameter that determines if transition is needed. The
evolution of the control-plan and time-shift parameters is determined from a single guaranteed-feasible convex optimization, which reduces to a quadratic program (QP) if the control limits are a convex polyhedron. The real-time executed control is determined from the instantaneous planning control and time shift. This method simultaneously addresses safety certification and performance optimization over the fixed prediction horizon. The approach is compared to nonlinear model predictive control in simulation of an autonomous car navigating a dense obstacle environment.
Read the full abstract ▾
Robotics
Differential Realizability of Static Control Allocation in Multirotors: An Impossibility under Nonredundant Full Actuation and a Pseudoinverse Obstruction under Redundant Actuation
Antonio Franchi and Mirko Mizzoni
Control allocation for multirotors with bidirectional propellers is commonly formulated in signed-thrust variables, where the wrench map is linear. The signed-quadratic map from physical rotor speed to thrust, however, is not a local diffeomorphism at zero speed. This work derives two distinct consequences. Under nonredundant full actuation, a single-propeller reversal removes one instantaneous task direction; hence, no global continuously differentiable exact static allocator exists over the complete task space. Under redundant actuation, the physical task map may remain regular, yet a transverse pseudoinverse zero crossing requires an unbounded rotor-speed derivative. We define differential realizability as regularity of the physical lift of an actuator-output section, derive exact and first-order validity conditions, and distinguish structural rank loss from an allocator- induced rate singularity. A local nullspace deformation repairs isolated pseudoinverse reversals, while a global fixed-orthant construction establishes existence of regular sections at the cost of persistent task-preserving internal actuation.
Read the full abstract ▾
Distributed Computing
mKernel: Fast Multi-GPU, Multi-Node Fused Kernels
Ziming Mao, Yihan Zhang, Shawn Wei Chew et al. (+5 more)
Communication has become a bottleneck in distributed training and inference of large models. Overlapping communication with computation at the granularity of kernels, on separate streams, reduces only part of this communication cost. Fused kernels often have better performance by transmitting each output tile as soon as it is produced, but existing fused kernels are largely confined to a single NVLink domain. We present mKernel, a library of multi-GPU, multi-node fused kernels that overlap computation, intra-node NVLink communication, and inter-node RDMA at tile granularity. mKernel partitions the streaming multiprocessors (SMs) of a persistent kernel into compute and communication roles, and an on-GPU controller tunes the SM partition adaptively at run time, since the best SM partition varies with the kernel and the input shape. It structures data movement hierarchically so that data traversing the inter-node network is minimized. Finally, it drives the network from the GPU through a lightweight command queue and host proxy implemented directly on RDMA verbs, which allows the same kernels to run on any network backend (e.g. InfiniBand and on AWS EFA); we observe, surprisingly, that GPUDirect Async (IBGDA) yields little additional benefit over host-assisted GPU-initiated communication. We implement five kernels spanning tensor, sequence, and expert parallelism. On two 16-GPU H200 clusters, mKernel achieves speedups of up to 1.72x on GEMM+AllReduce and $1.88\times$ on Ring
Attention.
Read the full abstract ▾
All authors Ziming Mao, Yihan Zhang, Shawn Wei Chew, Shuang Ma, Costin Raiciu, Yang Zhou, Scott Shenker, Ion Stoica
Computation and Language
Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs
Rohith Reddy Bellibatlu, Manpreet Singh, Zhoutian Han et al. (+1 more)
A clinical
agent benchmark can report the same verdict on identical inputs while the
agent files a materially different order on each run. Such
agents order tests, request medications and place referrals, yet
benchmarks typically score one run per task and rarely ask whether identical inputs produce identical actions; MedAgentBench, the
benchmark we use, scores a single attempt and says so. To measure this gap we introduce "same-input rerun", which replays a task with every input held fixed and compares the orders rather than the score, with six reliability metrics, and apply it to 1000 MedAgentBench runs across 50 tasks from its five write-capable families, two open-weight models below ten billion parameters quantised to four bits, and two temperatures. The study establishes that action-level divergence exists and can pass unrecorded by the score, not that any rate generalises. Under the 8B model at temperature 0.7, all 43 ordering groups emit a different set of orders across five identical runs, 26 emit the order on some runs and not others, and 28 record a different coded value, dose or analyte. In 22 of those 43 the
benchmark reports the same failing verdict for materially different behaviour, as it does for all 10 divergent groups of the 4B model at 0.7. Orders also reach different endpoints across runs, one of which the record server rejects while the
agent is told it succeeded. These findings motivate repeated-run evaluation, action-level stability reporting and execution-faithful environment feedback in clinical-
agent benchmarks.
Read the full abstract ▾
All authors Rohith Reddy Bellibatlu, Manpreet Singh, Zhoutian Han, Wenbin Zhang
Computation and Language
Toward Complete Hospital Discharge Summarization with Abstract Meaning Representation
Paul Landes, Sitara Rao, Aaron Jeremy Chaise et al. (+1 more)
Discharge summaries are lengthy medical documents that summarize a hospital in-patient visit. Automatically generating them can reduce documentation burden and return clinician time to patient care. Whereas Large
Language Model (LLMs) could be used for this task, their Achilles heel is
hallucinations, which can have drastic consequences for clinical documentation. We present an evidence-driven
alignment framework for discharge summarization at the clinical encounter level, that treats provenance as a first-class constraint, using semantic graphs and deep learning models. Each summary sentence is selected and organized via cross-document semantic
alignment and is accompanied by explicit evidence links to its source spans. We show our results on two corpora: a publicly available corpus (MIMIC-III) and clinical notes written by physicians at the University of Illinois Hospital (UIC Health). Additionally, we make source code and trained models available.
Read the full abstract ▾
All authors Paul Landes, Sitara Rao, Aaron Jeremy Chaise, Barbara Di Eugenio
Artificial Intelligence
FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks
Xinlu Zhang, Na Yan, Yang Su et al. (+2 more)
Large
language models (LLMs) have demonstrated strong capabilities across a wide range of natural
language processing tasks. However, conventional fine-tuning typically relies on centralized data collection, bringing in
privacy concerns.
Federated learning (FL) enables collaborative LLM fine-tuning without sharing raw client data, but its deployment over bandwidth-constrained wireless networks is hindered by the communication overhead of model-parameter transmission. Although Low-Rank Adaptation (LoRA) reduces the number of trainable parameters, its communication cost still increases with model scale. Knowledge
distillation avoids parameter sharing via output logits, but
token-level logits in LLMs incur high communication cost due to sequence length and vocabulary size. Reducing logits lowers the cost but weakens supervision and degrades accuracy. To address these limitations, we propose FLoKD, an adaptive knowledge-
distillation framework for
federated LoRA fine-tuning of LLMs over wireless networks, which communicates intermediate LoRA activations as the
distillation signal rather than logits or full parameters. Since transmitting all blocks over the entire public
dataset remains costly, we further propose a
transformer block importance scoring framework that selectively transmits the most informative blocks, and two
dataset selection strategies that discard public samples deviating from the local data distribution and prioritise those most informative for
distillation. Extensive experiments across multiple generative
language datasets, including WikiText-103, PTB, and Dialog, demonstrate that our proposed framework reduces communication overhead by 50-65% while achieving rapid convergence to competitive perplexity compared to baselines.
Read the full abstract ▾
All authors Xinlu Zhang, Na Yan, Yang Su, Yansha Deng, Toktam Mahmoodi
Artificial Intelligence
How User-AI Mistreatment Occurs and Matters in Conversational Systems?
Fanqi Zeng, Sadid A. Hasan and Chaocheng He
Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and
adversarial pressure at models. Understanding how and when that occurs is essential for accurately interpreting model behaviour,
alignment drift, and real-world deployment risks. In this paper, we audit 777K English LMSYS-Chat-1M conversations with two independent detectors: an eight-category lexicon for hostility directed at the model, and the
dataset's moderation signal; and show that they capture different, weakly overlapping phenomena. The lexicon identifies insults, threats, and jailbreak coercion aimed at the assistant, while moderation flags are dominated by toxic-content solicitation rather than hostility at the model. Together, they mark about 5% of user turns; adjusting the narrower lexicon-harassment union for measured precision puts mistreatment aimed at the assistant at 0.90%. These absolute rates describe arena-style evaluation traffic and should not be read as deployment-wide base rates. We find that user hostility varies 13-fold across models, driven largely by who each model attracts rather than by model behaviour: first-turn hostility spreads far wider than post-response hostility, and more than fifteenfold separates the extremes even after deduplicating opening
prompts. Within conversations, assistant apologies are consistently associated with higher odds of next-turn hostility under both detectors; the effect survives restricting to non-refused prior turns and to jailbreak-free conversations, and is positive in 20 of 23 models. Yet across models, more apologetic models receive less hostility overall. Finally, hostility also shows temporal structure, with coercive openings front-loading the first turn while affective hostility accumulates over a session. We release the lexicon, the detector cross-validation pipeline, and all derived tables.
Read the full abstract ▾
Software Engineering
Comparative Framework Analysis for Enterprise Generative AI Applications: Chatbot, Automation, and Oracle-to-PostgreSQL Migration
Oleg Grynets, Olena Pochernina, Alona Seletska et al. (+4 more)
This study compares framework suitability across three classes of enterprise generative AI applications: a documentation-based development assistant, an email and inquiry automation system, and an Oracle-to-PostgreSQL migration tool. The analysis evaluates component boundaries, orchestration, policy
retrieval or
reasoning, model integration, deterministic validation, persistence, observability, and operational efficiency. Across the three applications, the evidence supports layered architectures in which probabilistic components generate proposals, while deterministic components retain authority over routing, authorization, validation, persistence, idempotency, and final outcomes. The results indicate that framework suitability depends on the application, deployment conditions, and component responsibility: search quality, workflow control, safety behavior, and migration validation cannot be reduced to a single cross-application assessment. Therefore, the study substantiates the need for framework selection at the component level, supported by explicit contracts, application-specific evidence, and independent validation boundaries.
Read the full abstract ▾
All authors Oleg Grynets, Olena Pochernina, Alona Seletska, Daryna Tukalo, Dmytro Kostetskyi, Ivan Fedorchuk, Vasyl Lyashkevych
Robotics
An MRI-Guided Robotic System to Improve Hippocampal Access for Epilepsy Interventions
John E. Peters, Abby M. Grillo, Mahshid Mansouri et al. (+8 more)
This paper presents an MRI-guided robotic system that improves hippocampal access by delivering a curved needle-like
laser ablator through the foramen ovale, a natural opening in the base of the skull. Both the delivery path and the curved nature of the needle improve upon current clinical straight-line
laser interstitial thermal therapy (LITT) as measured by hippocampal cannulation percentage. We describe the design of the robotic system which includes positioning, aiming, and curved needle deployment stages, followed by experimental results assessing cannulation percentages using MRI images in phantoms. In three curvilinear, single-insertion experiments, we achieved cannulation percentages of 93.5%, 96.5%, and 60.4%, exceeding reported clinical averages of 50-60%. Seizure control is believed by physicians to be a function of hippocampal volume treated, and our system provides a means of treating a greater volume of the hippocampus with LITT-based interventions.
Read the full abstract ▾
All authors John E. Peters, Abby M. Grillo, Mahshid Mansouri, Daniel S. Esser, Sarah Garrow, Nithin S. Kumar, Dario J. Englot, Joseph S. Neimat, William A. Grissom, Robert J. Webster III, Eric J. Barth
Distributed Computing
Object Model Analysis of a Supercomputer with Digital Twin
Shilpika Shilpika, George K. Thiruvathukal, Venkatram Vishwanath et al. (+1 more)
Operators and developers need a mental model of both the structure and the live behavior of a large supercomputer, but its physical layout, logical organization, and streams of per-node telemetry are difficult to relate to one another, making it hard to trace a metric or event back to a specific hardware component. We present DAT, an interactive three-dimensional digital analytics twin of a compute cluster built in a real-time game engine, Unreal Engine. DAT expands a compact, parametric description of a supercomputer, a reusable Digital Twin Prototype (DTP), into a navigable Digital Twin Instance (DTI) that mirrors its physical containment hierarchy of racks, chassis, blades, and network links, encoding each node's role and health in its appearance, while a lightweight event-driven simulator animates job and hardware activity over a virtual clock. Our current implementation adds a two-path node-selection mechanism, unifying direct 3D pointing with command-shell queries, that opens an in-world visual-analytics panel beside any selected component showing summary statistics and live, time-varying metrics. We describe this architecture, report qualitative behavior from the working prototype, and outline the path toward driving the panels with recorded telemetry and in-situ anomaly detection.
Read the full abstract ▾
All authors Shilpika Shilpika, George K. Thiruvathukal, Venkatram Vishwanath, Michael E. Papka
Machine Learning · Cross-listed from stat.ML
A pullback-corrected scalar auxiliary variable optimizer with momentum and adaptive mobility
Jiahao Zhang, Shiheng Zhang and Guang Lin
Objectives in scientific machine learning are often prescribed as a sum of several terms, such as the residual, boundary, initial, and data losses of a physics-informed neural network. In the pullback-corrected scalar auxiliary variable (PB–SAV) method, one scalar tracks the shifted objective while the component gradients build a positive semidefinite
curvature correction of rank at most the number of components. We carry that correction into an optimizer with momentum and an adaptive mobility, applying it to the gradient and the stored momentum in a single implicit solve. A mobility that is nonincreasing in the Loewner order yields an exact modified energy law, covering Euclidean and AMSGrad-type choices; the corresponding identity for momentum appended after the solve carries a cross term of indefinite sign. For a fixed mobility we give a necessary and sufficient condition for local stability at a stationary point, depending on the Hessian minus twice the correction, and show that it also gives local
geometric convergence for every scalar relaxation sequence. The implicit solve reduces to a dense system whose order is the number of components. In the forward Burgers comparison, four components reduce the mean tail objective by 64.7% and the final solution error by 50.2% relative to one component at the same learning rate and momentum settings.
Read the full abstract ▾
Artificial Intelligence
Causal multi-modal AI for personalized chemosensitivity prediction
Dhruva Biswas, Jeroen Berrevoets, Alec McClean et al. (+31 more)
Chemotherapy improves survival for some patients with breast cancer, but doctors cannot reliably predict who. Current guidelines rely on recurrence scores as a proxy for treatment benefit, which may contribute to the overprescription of chemotherapy. Here we present a causal multi-modal AI model that predicts personalized chemosensitivity using routinely collected pathology and clinical information. We developed our model on a multi-national
dataset of 9,141 patients (twelve cohorts, nine countries) and evaluated it on another 1,994 patients (five cohorts, three countries). The model generated treatment-specific recurrence probabilities for each patient, with near-perfect calibration and strong prognostic discrimination across both 5- and 10-year follow-up horizons. Moreover, its chemotherapy benefit predictions demonstrated robust predictive performance, and out-performed existing recurrence-score-based tests. Compared to the standard of care, using the model to support personally tailored therapeutic decisions could reduce the number of patients receiving chemotherapy by 30% while achieving the same recurrence-free rate. Tumors predicted to be highly chemosensitive displayed concordant molecular and morphological programs of proliferation,
cell cycle progression, and replication stress. The model's predictive capabilities transferred zero-shot to non-breast cancers, indicating our causal multi-modal AI approach may provide a universal strategy to predict treatment outcomes across cancer types.
Read the full abstract ▾
All authors Dhruva Biswas, Jeroen Berrevoets, Alec McClean, Linus Bao, Jungkyu Park, Ken G. Zeng, Joseph Cappadona, Cerise Tang, Chuwen Liu, Bartosz Machura, Yin Wu, Valerie Speirs, Hatem Soliman, Rohit Bhargava, Sheheryar Kabraji, Thaer Khoury, David Page, Brian Piening, Carlo Bifulco, Claudia Meurs, Pieter Westenend, Sylvie Chabaud, Jerome Lemonnier, Paul H. Cottu, Florence Dalenc, Fabrice Andre, Frederique Madeleine Penault-Llorca, Thomas Bachelot, Frederick Howard, Francisco J. Esteva, Kevin Kalinsky, Lajos Pusztai, Jan Witowski, Krzysztof J. Geras
Artificial Intelligence
Planning or Learning: Reliability and Cost in Multi-Asset Maintenance
Xian Yeow Lee, Chandrasekar Venkatraman and Ahmed Farahat
Industrial maintenance systems involve multiple interacting assets and shared resources, making it challenging to balance reliability and operational cost using a single decision framework. While recent work has focused on reinforcement learning (RL) for maintenance scheduling, direct comparisons with planning approaches under identical settings remain limited. In this work, we empirically compare planning and RL for multi-asset bearing maintenance using run-to-failure data. We examine how these methods behave when balancing preventive maintenance against tolerable failures across a range of failure penalty scenarios. We observed a consistent behavioral difference driven by objective formulation. Planning enforces reliability as a hard constraint and produces zero-failure policies whose total cost is largely insensitive to the magnitude of failure penalties. RL
agents optimize expected cost and often trade off preventive maintenance against occasional failures as penalties vary, resulting in lower costs under low-penalty regimes but persistent non-zero failures even when penalties are high. We also investigate lightweight constraint mechanisms, including reward shaping and action masking, to encourage RL's reliability. From a practical perspective, planning may be more suitable when strict reliability is required and deployment horizons are short, whereas RL may provide cost-efficient policies when limited failures are acceptable and long-run operational efficiency is prioritized. Overall, this study clarifies the trade-offs between reliability and cost in multi-asset maintenance and suggests that planning and RL are complementary approaches. Beyond these findings, the controlled
benchmark protocol itself that unifies environment, cost model, and evaluation across paradigms, offers a reusable template for comparing decision-making approaches in other maintenance settings.
Read the full abstract ▾
Game Theory
Scaling Chance-Constrained Correlated Equilibrium Computation for Exclusive Resource-Assignment Games
Jaehan Im, Ufuk Topcu and David Fridovich-Keil
The chance-constrained correlated
equilibrium concept provides a robust coordination technique for self-interested
agents whose costs are uncertain to a central coordinator, but the number of joint actions considered in its computation grows exponentially with the number of
agents. We propose an exact-one resource-assignment restriction for games in which
agents compete for shared resources and simultaneous use of a resource is undesirable or unsafe. The restriction allows each resource to be assigned to exactly one
agent, reducing the number of joint actions considered from O(2^(nr)) to O(n^r) for n
agents and r resources. The resulting problem is solved over the restricted joint action set while retaining all incentive constraints associated with unilateral deviations. We show that the feasible set of the restricted problem is exactly the convex hull of the chance-constrained pure Nash
equilibria contained in the exact-one assignment set, yielding a necessary and sufficient condition for nonemptiness. We further derive a sufficient condition under which all chance-constrained pure Nash
equilibria of the unrestricted game are retained by the restriction. Numerical experiments in a vertiport departure-corridor coordination scenario demonstrate a 99.81% reduction in median computation time relative to the unrestricted formulation while achieving equivalent coordination performance.
Read the full abstract ▾
Machine Learning
When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence
Zichen Wang, Haoyang Hong and Huazheng Wang
We study KL-regularized contextual bandits under both reward and preference feedback. While existing regret guarantees typically depend on the eluder dimension, we show that simple greedy sampling can achieve polylogarithmic regret without explicit dependence on this complexity measure. For reward feedback, we analyze a greedy
algorithm that samples directly from the Gibbs policy induced by the estimated reward. We extend the result to preference feedback under both general preference and Bradley–Terry models, while also sharpening existing dimension-dependent guarantees. Our analysis reveals a trade-off between greedy sampling and upper confidence bound-style exploration: greedy sampling enjoys stronger regret guarantees when KL regularization is sufficiently strong, whereas additional exploration yields sharper bounds as the regularization weakens.
Read the full abstract ▾
Hardware Architecture
A Unified Interconnection Network for Chiplet-Based Scaling of the BrainScaleS Neuromorphic System
Robin Heinemann and Johannes Schemmel
The BrainScaleS-2 (BSS-2) neuromorphic architecture combines analog emulation of spiking neural network (SNN) primitives with tightly coupled ADCs and digital processing units. These analog SNN primitives are fixed hardware resources that cannot be multiplexed, limiting the emulated network size to the number of physical hardware copies. To overcome the challenges of scaling analog designs, chiplet-based designs offer a promising approach with cost and flexibility advantages over monolithic scaling. Implementing a chiplet-based BSS-2 architecture requires an interconnection network that handles two distinct classes of traffic: error-tolerant traffic such as spikes and error-intolerant traffic like configuration data or data exchanged by the processing units. This work presents the design of a routing chiplet for the BSS-2 architecture that enables interconnection of multiple BSS-2 units in a 2D mesh
topology. Both traffic classes are multiplexed over a single wide parallel die-to-die link. Exploiting the fault tolerance of SNNs, spikes are transmitted unsecured and synchronously, with the arrival time on the receiving side directly determining the pre-synaptic time of the spike. Conversely, error-intolerant data transmission is secured by a point-to-point Automatic Repeat Request protocol and uses credit-based flow control. These design choices are validated in simulation, where the proposed design can sustain $95\,\%$ link bandwidth utilization for the use case of surrogate gradient training across a wide range of spike-to-secured traffic ratios under a $1 \times 10^{-10}$ bit error rate with little impact on spike timing jitter.
Read the full abstract ▾
Artificial Intelligence
A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics
Xian Yeow Lee, Teppei Inoue, Haiyan Wang et al. (+1 more)
Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database querying, key performance indicator (KPI) analysis, demand
forecasting, and performance diagnosis require heterogeneous expertise spanning data engineering, operations research, and domain knowledge. In this work, we propose an agentic system for supply chain analytics that bridges the gap between business decision-making and technical expertise, where a coordinator
agent interprets user intent and delegates sub-tasks to specialized
agents. The system supports both exploratory analysis and deterministic workflows, enabling planners to transition between ad hoc questions and structured processes. Domain logic is encapsulated within specialist
agents and
prompts, yielding a scalable, modular, and auditable design and lowering the cost of functional extension through
prompt-centric development. We evaluate the proposed architecture on a test environment that replicates multi-echelon inventory management operations. Results show that our multi-
agent design achieves a 90% accuracy, which is competitive with a single
agent baseline while reducing input
token usage by roughly fourfold, substantially improving scalability and cost-efficiency. Furthermore, we provide case studies to demonstrate interpretable suboptimality detection and automated forecast optimization, illustrating how agentic architectures can effectively combine open-ended exploratory analysis and deterministic supply chain analytics workflows, and provide a practical pathway toward more accessible and extensible decision-support systems.
Read the full abstract ▾
All authors Xian Yeow Lee, Teppei Inoue, Haiyan Wang, Chetan Gupta
Artificial Intelligence
Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems
Aikaterini Maria Panteleaki, Varatheepan Paramanayakam, Spyros Tragoudas et al. (+1 more)
Large
Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments typically route inferences to powerful cloud-based models, incurring significant energy use and carbon emissions. We address this sustainability challenge with a carbon-aware routing framework that distributes function-calling queries across a three-tier edge-cloud architecture, combining edge and cloud LLMs on heterogeneous hardware. At its core, a lightweight k-NN predictor operating in a unified semantic-lexical
embedding space estimates query-specific accuracy, delay, and power consumption on each edge tier. These predictions are then combined with real-time grid carbon intensity to route every query to the lowest-emission tier capable of executing it successfully. Evaluated on state-of-the-art function-calling
benchmarks and LLM families, our framework matches cloud-level accuracy while reducing operational carbon emissions by $4\times$ on average.
Read the full abstract ▾
All authors Aikaterini Maria Panteleaki, Varatheepan Paramanayakam, Spyros Tragoudas, Iraklis Anagnostopoulos
Computation and Language
Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models
Darin Keng and Zhewei Sun
Large
Language Models (LLMs) have shown remarkable proficiency on general-purpose tasks, yet their performance often degrades in highly-specialized technical domains. Moreover, little is known about how parametric knowledge of domain-specific terms is encoded within these models. We address this gap by contributing two novel medical jargon evaluation
benchmarks and evaluate a general-purpose Llama-3.1 model against a variant fine-tuned on medical-domain data. Surprisingly, the general-purpose model outperforms the medically fine-tuned model on both tasks. Using mechanistic interpretability tools, we find systematic patterns of miscalibration for the medically fine-tuned model. Instead of reorganizing parametric knowledge, the fine-tuned model places greater emphasis on a small subset of model components associated with jargon-favoring predictions. We find that applying component reweighting strategies against the
benchmark tasks successfully suppresses these components and closes the gap with the general-purpose baseline. We also observe that some jargon-sensitive components transfer knowledge to the same tasks involving materials science jargon, suggesting they encode a partially domain-agnostic notion of specialized terminology. Our results provide a case study in which a medically fine-tuned checkpoint does not improve jargon comprehension over its general-purpose counterpart, highlighting that domain adaptation should not be assumed to yield better performance on specialized terminology.
Read the full abstract ▾