Artificial Intelligence · Cross-listed from cs.CL
Before the Labels: How Dataset Construction Shapes Suicidality Detection in Clinical Text
Priyanshi Garg, Ishita Rao, Jieqiong Ding et al. (+1 more)
Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media. We argue that this framing obscures how EHR-based suicidality
datasets encode a particular operationalization of suicidality, shaped by who authors the data, how episodes are bounded, and how ambiguity is resolved. We ground this argument in a case study of the ScAN
dataset, built over MIMIC-III clinical notes. We show how governance constraints, ICD-based cohort selection, single-annotator labeling, and hospital-stay-level aggregation produce labels that reflect clinician-documented judgments, treat suicidality as a bounded episode, and assume that intent can be reliably inferred from documentation. A linguistic analysis demonstrates that identical labels subsume heterogeneous clinical framings differing in temporality, negation, and uncertainty. We argue that clinical NLP should examine the assumptions embedded in suicidality
datasets before interpreting their labels as ground truth.
Read the full abstract ▾
All authors Priyanshi Garg, Ishita Rao, Jieqiong Ding, Amandalynne Paullada
Artificial Intelligence · Cross-listed from cs.LG
Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation
Luca Zhou, Sajel Shah, Emanuele Rodolà et al. (+1 more)
Math and science
reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with verifiable rewards, math data curation, synthetic curricula, and verifier training. We show this proxy has a persistent blind spot on its hardest stratum: on the eight free-form math
cells we test (GSM8K and MATH across four open-weight models), 10.3-22.9% of the examples that no sampling seed solves in six tries are instead solved at matched compute by a six-chain deterministic regime. These are greedy decoding plus five cheap residual-stream perturbations applied via activation grafting, while greedy alone solves at most 6% on these math
cells. Recovery scales with the additional budget, across perturbations whose mechanistic distinctness we verify across all twelve
cells (cross-kind fix-set Jaccard <= 0.47 in every setup). Activation grafting is used as an intervention on internal representations, not a decoding method; we use it purely as a diagnostic and diversification tool, and our recovered items show that the pass@k= 0 % stratum is structurally identifiable in the residual stream rather than that the unmodified model reaches them under ordinary inference.
Read the full abstract ▾
All authors Luca Zhou, Sajel Shah, Emanuele Rodolà, Roberto Dessì
Artificial Intelligence · Cross-listed from cs.IR
Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
Xilun Chen, Shao-Chuan Wang, Baykal Cakici et al. (+6 more)
Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these
transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that "textualize" these signals directly or create discrete item representations often lead to excessively long
prompts, substantial
memory footprints, and high computational overhead. To overcome these limitations, we propose "
Token Factory", a framework designed to transform traditional signals into "soft
tokens" that can be directly processed by LRMs. This approach enables efficient integration and compression of heterogeneous input features, preventing
prompt length explosion while enhancing model performance. We detail the architecture of
Token Factory and present experimental results validating its effectiveness in a production-scale recommendation environment.
Read the full abstract ▾
All authors Xilun Chen, Shao-Chuan Wang, Baykal Cakici, Lukasz Heldt, Lichan Hong, Raghu Keshavan, Aniruddh Nath, Li Wei, Xinyang Yi
Artificial Intelligence · Cross-listed from cs.RO
Keeping Jerk in Check: Jointly Trained Perception-Gated Experts for Smooth Terrain Transitions
Francisco Affonso, Matheus P. Angarola, Ana Luiza Mineiro et al. (+3 more)
Perceptive legged locomotion across discontinuous terrain requires shared locomotion knowledge, task-specific maneuvers, and smooth transitions between them. Existing approaches train specialized policies independently and either switch among them with a hierarchical selector or distill them into a monolithic policy. Both fix the constituent behaviors before they are composed, and both are assessed through aggregate course outcomes that leave behavior at terrain boundaries uncharacterized. We instead propose CTS-MoE, which formulates multi-terrain locomotion as multi-task reinforcement learning and jointly trains a perception-gated dense mixture-of-experts actor with task-specific critics: soft routing composes expert knowledge into continuously varying behavior, while separated critics isolate heterogeneous objectives so that specialization survives joint optimization. A concurrent teacher-student formulation transfers this composition from privileged terrain information to onboard depth, so that at deployment routing is inferred from perception alone, with no terrain label, selector, or
distillation stage. Against hierarchical and DAgger-distilled baselines, the policy raises connected-course success to 93.3% from 73.3% and 53.3%, lowers mean action jerk by about a third across the course, and avoids the switching transient that hard selection introduces at boundaries. On a Unitree Go1, it completes an extended outdoor course in 10/10 trials and transfers to four outdoor terrain types. Project Website: https://cts-moe.github.io/ .
Read the full abstract ▾
All authors Francisco Affonso, Matheus P. Angarola, Ana Luiza Mineiro, Aditya Potnis, Marcelo Becker, Girish Chowdhary
Artificial Intelligence · Cross-listed from cs.RO
Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation
Ahmad Farooq and Kamran Iqbal
Multi-
agent reinforcement learning (MARL) enables
agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-
agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks. Our four-stage pipeline consists of domain-specific feature extraction from
agent observations, decision tree
distillation achieving 97.9% +/- 1.2% fidelity to neural policies, automated translation to PRISM probabilistic model checker specifications with complete feature-to-state-variable correspondence, and compositional verification of Probabilistic Computation Tree Logic (PCTL) properties via pairwise decomposition with union-bound aggregation and empirical neighbor modeling. Evaluating Vector-Quantized Variational Information Bottleneck (VQ-VIB) policies for multi-drone coordination with 5-7
agents, we verify 18 temporal logic properties across safety, liveness, and cooperation, achieving 88.9% property satisfaction with all five safety thresholds satisfied (0.3% collision probability vs. 1% threshold). Monte Carlo validation of original neural policies confirms that verified safety properties transfer with <=0.6 percentage-point deviation (95% CI). Discrete VQ-VIB messages provide +11.6 to +13.6 percentage-point fidelity advantages over continuous methods, enabling 3-4x faster verification. Our framework provides empirically validated safety verification for distilled policy abstractions, serving as a practical bridge between deep MARL and formal safety workflows for multi-
robot deployment.
Read the full abstract ▾
Artificial Intelligence
AI4SE and SE4AI Exploration: A Decade Looking Back and Forward
H. Sinan Bank, Daniel R. Herber and Thomas Bradley
The March 2020 INCOSE INSIGHT special issue on AI and Systems Engineering (SE) became the most downloaded issue in the publication's history and launched a research community that now draws over 250 registrants to its annual workshop. In this article, we trace the progress in AI and SE across three phases (labeled here foundational, applied, and LLM inflection) based on the authors' reading of the field's core papers, and describe our opinions of where the community has converged and where critical gaps remain. Separately, a human-AI agreement literature review leveraging both human expertise and six AI models was performed to assess the relevance of 1,712 INCOSE INSIGHT articles and 889 SERC publications. The results identify five critical research gaps and offer guidance for practitioners navigating AI adoption, assurance, and workforce transformation in SE. We share the agreement data and the AI4SE/SE4AI Explorer web application so readers can compare their own relevance judgments with the human and AI raters.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
RIVET: Robust Idempotent Voice Attribute Editing
Dareen Alharthi, Bhuvan Koduru, Rita Singh et al. (+1 more)
Voice attribute editing models modify characteristics such as age and gender while preserving speaker identity. In large-scale
speech datasets, however, attribute annotations are often noisy or inconsistent, which can cause conditional generative models to produce unstable edits. In this work, we show that idempotency provides an effective mechanism for improving robustness to noisy labels. An idempotent operator is one for which repeated application does not change the result, i.e., f(f(x)) = f(x). Enforcing this property acts as an implicit regularizer that reduces sensitivity to mislabeled examples. We introduce RIVET, a training framework that incorporates an idempotency objective to improve robustness to label noise. We evaluate RIVET under controlled label noise and on the GLOBE
dataset with naturally noisy annotations. RIVET improves editing success and better preserves speaker identity than standard training, showing that idempotency improves robustness in voice editing models.
Read the full abstract ▾
All authors Dareen Alharthi, Bhuvan Koduru, Rita Singh, Bhiksha Raj
Artificial Intelligence · Cross-listed from cs.IR
VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions
Katya Mirylenka, Egor Malykh, Mahdyar Ravanbakhsh et al. (+10 more)
The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive
video feeds. This transition introduces an “extreme cold-start” problem: unlike traditional items, new short-form
videos lack the dense interaction history required for collaborative filtering. Furthermore, immersive feeds introduce strong position and duration biases that distort standard engagement signals. In this paper, we demonstrate the
Video Candidate Generation (VCG) system, a scalable
multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment. By leveraging a domain-adapted
vision-
language model (based on CLIP), we map users and
videos into a shared semantic space, enabling zero-shot
retrieval based on visual content rather than behavioral history. We detail the system's architecture and present a rigorous evaluation comparing generative (LLM) vs. discriminative (CLIP)
embeddings. Our results show that while generative models excel at attribute prediction, they suffer from
embedding space collapse in
retrieval tasks. Online A/B testing demonstrates that VCG effectively mitigates engagement biases, yielding a 50% uplift in deep
video completion. To showcase the system's capabilities, we present an interactive demonstration featuring three bi-directional
retrieval scenarios: Product-to-
Video,
Video-to-Product, and Zero-Shot Semantic Search.
Read the full abstract ▾
All authors Katya Mirylenka, Egor Malykh, Mahdyar Ravanbakhsh, Michael Gygli, Marco-Andrea Buchmann, Andrew Dzhoha, Svitlana Borzenko, Francesca Catino, Mohamed Gaafar, Maarten Versteegh, Thomas Kober, Dario d'Andrea, Ellie Langhans
Artificial Intelligence
Toten: A Knowledge-Based System For Structure-Preserving Representation Of Physical Quantities And Technical Notation In Brazilian Portuguese
Antonio de Sousa Leitão Filho, Allan Kardec Duailibe Barros Filho, Fabrício Saul Lima. Selby Mykael Lima dos Santos et al. (+1 more)
AI pipelines that reason quantitatively over technical text depend on input where physical quantities, numbers, units, and symbolic expressions arrive intact; when these entities fragment at tokenization, errors propagate downstream. Byte-Pair Encoding, optimized for vocabulary compression, is blind to such entities and fragments them into arbitrary subwords – a problem aggravated in technical Brazilian Portuguese. We present TOTEN, a knowledge-based system whose input representation preserves each technical entity as a whole, typed unit: vocabulary is not derived statistically but classified declaratively under a formal ontology of engineering entities (OEE). The core is the triple <O, classify, {inst_tau}>: types, principles, and invariants; a classifier mapping raw text into typed regions; and instantiators yielding a self-descriptive representation. Integrity rests on deterministic coupling to three external authorities: Pint (dimensional), Unicode Character Database (typographic), and RSLP (Portuguese morphology). We evaluate four properties verifiable by construction – atomicity, dimensional equivalence, typographic robustness, numerical reconstruction – on an internal
benchmark (EngQuant, N=800) and four Brazilian Portuguese external corpora (N=1771 eligible cases), and report detection recall. Against eight state-of-the-art baselines, TOTEN reaches unit atomicity in all contrasts and reconstruction of 0.775-0.904 externally vs. 0.627-0.703 for the best (Quantulum3); on EngQuant, 0.780 vs. 0.340. Differences are significant (McNemar, Holm-corrected). Spearman correlation between internal and external rankings confirms concurrent validity of the control
benchmark. TOTEN shows statistical parity with Pint in dimensional equivalence. The result is a structurally faithful, auditable, low-cost input layer for intelligent systems on technical knowledge, without generative models.
Read the full abstract ▾
All authors Antonio de Sousa Leitão Filho, Allan Kardec Duailibe Barros Filho, Fabrício Saul Lima. Selby Mykael Lima dos Santos, Rejani Bandeira Vieira Sousa
Artificial Intelligence · Cross-listed from cs.SE
Before the Pull Request: Mining Multi-Agent Coordination
Dipankar Sarkar
Autonomous coding
agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that pull-request-level telemetry cannot explain. We argue the missing signal lives before the PR, in how concurrent
agents claim, divide, and collide over shared work. We study this process through grite, our open-source coordination substrate that needs no central server and stores its records inside git itself, so its append-only, signed event log captures the coordination process directly. We show that (i) this shared substrate reduces duplicate and conflicting work at bounded overhead - the share of work that merely re-does a teammate's task falls from 78% to 0% while useful throughput more than triples; (ii) every
agent's copy of the log converges to the same state with no write silently dropped, where a file-based tracker loses concurrent writes; and (iii) the log is a mineable artefact from which concrete failure modes - conflicting edits, lock starvation, redundant rediscovery, race-to-close - are automatically recoverable with provenance, several invisible in pull-request history. We release the
dataset, harness, and mining toolkit.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
Vlad Sobal, Shuo Yang, Yuting Zhang et al. (+2 more)
We introduce StaminaBench, a
benchmark that measures the stamina of coding
agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench,
agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The
agent and the server run in an isolated environment and communicate with the
benchmark through HTTP, making testing fully black-box and
language-agnostic. We evaluate six
agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the
agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the
benchmark and the generated tasks to enable further research into multi-turn coding
agent behavior.
Benchmark code and data: github.com/amazon-science/StaminaBench.
Read the full abstract ▾
All authors Vlad Sobal, Shuo Yang, Yuting Zhang, Wei Xia, Stefano Soatto
Artificial Intelligence · Cross-listed from cs.LG
Latent Confounded Causal Discovery via Lie Bracket Geometry
Sridhar Mahadevan
We study causal discovery from observational and interventional regimes when latent variables may affect the measured system. Our first
algorithm, BRIDGE (Bracket Residuals for Interventional Discovery and
Geometric Estimation), combines a density-ratio or transport engine with a high-recall
geometric screen and passes the retained arrows to a score-based or differentiable discovery method. The main formulation and experiments use known single-node intervention targets; in that regime the screen is designed to retain candidate directed effects, while a downstream learner determines the final graph or equivalence-class representation. Our second
algorithm, Spectral Kernel Flow Matching (SKFM), amortizes the response fields, summarizes residual nonclosure by a spectral visible-footprint subspace, and applies an order-dependent graph extractor. Direct extraction succeeds on calibrated chains and selected motifs, but is unstable on harder random DAGs when the order must be learned. On ten-node nonlinear random DAGs, the more reliable hybrid role of the geometry is as a candidate generator: calibrated SKFM/Bridge fields followed by local BIC scoring achieve mean directed $F_1\simeq0.86$. Sachs
protein signaling provides a real-data stress test and supports a diagnostic, not fully identified, interpretation. The contribution is therefore a practical interventional screening pipeline, explicit guarantees for screen retention and residual-footprint rank under stated assumptions, and a falsifiable account of the boundary between
geometric diagnostics and causal identification.
Read the full abstract ▾
Artificial Intelligence
Which Pairs to Compare for LLM Post-Training?
Jiangze Han, Vineet Goyal and Will Ma
Preference-based post-training has become a central paradigm for aligning
language models. A common data-collection strategy is to generate a small set of completions for each
prompt and label the resulting comparison pairs. However, human preference labels are often much more expensive than generating additional completions, suggesting a different use of the same labeling budget: generate a larger pool of completions, but label only the most informative comparison pairs. This paper studies which pairs should be compared in preference-based post-training. We formulate comparison curation as a sampling-design problem and evaluate designs by the quality of the final policy under the preference-based post-training objective. We instantiate this framework for Direct Preference Optimization (DPO), analyzing how the choice of labeled pairs propagates through DPO training to downstream policy performance. Our main results provide matching upper and lower bounds on the post-training optimality gap of the DPO-trained policy. The bounds show that comparison selection affects downstream performance through a single design-dependent information
matrix, which links label allocation to parameter estimation error and policy suboptimality. This yields an explicit optimization criterion for budgeted comparison curation and motivates practical sampling designs for selecting informative pairs from large generated completion pools. Experiments on synthetic settings and
language-model post-training
benchmarks show that the proposed designs consistently improve sample efficiency over common comparison-selection heuristics.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
Paul Kassianik, Baturay Saglam, Huaibo Zhao et al. (+4 more)
Multi-step LLM pipelines fail through interactions among
retrieval,
reasoning, and formatting steps, so
prompt-only optimization can miss bottlenecks in the chain. We present Fully Automated
Prompt Optimization (FAPO), a framework that lets Claude Code optimize an LLM pipeline inside a standardized codebase. FAPO evaluates a pipeline, inspects intermediate steps, diagnoses failures, proposes scoped changes, and validates variants repeatedly to optimize against a score function. It first tries
prompt edits and, only when
prompt optimization appears insufficient, changes chain structure within the permitted scope when attribution identifies a structural bottleneck. Across six
benchmarks and three task models, FAPO beats the baseline GEPA in 15 of 18 model-
benchmark comparisons. In 11 model-
benchmark comparisons, FAPO wins with non-overlapping mean $\pm$ trial-standard-deviation ranges, and the mean FAPO-GEPA gain is +14.1 pp. In the six HoVer and IFBench comparisons where
prompt-first search escalated to structural changes, FAPO wins all six with a mean gain of +33.8 pp. FAPO also improves performance on security tasks: on CTIBench-RCM, a security CVE-to-CWE task,
prompt-only FAPO lifts test accuracy by +4.0 pp on GPT-5, +7.1 pp on Foundation-Sec-8B-Instruct, and +2.0 pp on Foundation-Sec-8B-
Reasoning. These results position FAPO as a state-of-the-art pipeline optimization technique for both general-purpose and security-focused tasks.
Read the full abstract ▾
All authors Paul Kassianik, Baturay Saglam, Huaibo Zhao, Blaine Nelson, Supriti Vijay, Aman Priyanshu, Amin Karbasi
Artificial Intelligence
Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab et al. (+7 more)
Patient contexts span hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for
retrieval and triage is absent or incomplete. Standard
retrieval-augmented generation fails on this data, mishandling temporal
reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline that reasons over complete patient contexts and grounds every answer in source passages for clinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study, in which
nuclear-medicine physicians verify every extracted value against its cited sources. Across 7,326 judgments, clinicians accepted 96.5% of extractions, with per-type acceptance ranging from 80% to 99%.
Read the full abstract ▾
All authors Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab, Merlin Engelke, Moon Kim, Stephan Settelmeier, Shigeyasu Sugawara, Fabian Freisleben, Felix Nensa, Jens Kleesiek
Artificial Intelligence · Cross-listed from cs.SD
PrefSQA: Pairwise Preference Prediction for Speech Quality Assessment and the Critical Role of High Quality Datasets
Junyi Fan and Donald S. Williamson
Mean opinion scores (MOS) are widely used for
speech quality assessment, yet scalar labels are sensitive to rater variability and listening test differences. This introduces labeling noise, which limits the reliability of MOS prediction. Preference prediction reduces this variability as listeners compare signals directly, producing cleaner labels. We study MOS-free preference prediction and propose PrefSQA, which incorporates uncertainty-aware logits, an impairment
attention head, and a module based on non-matching-reference comparisons. We use and refine five
datasets, including MOS-derived and low-noise simulated sets with matching and non-matching content, experiment with human preference sets, and test on unseen data. Experiments show small improvements on MOS-derived data, while other sets reveal clear improvement over the baselines, highlighting the value of high-quality preference data and demonstrating the effectiveness of the proposed method.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows
Ahmad Salimi, Wentao Ma, Yuzhi Tang et al. (+3 more)
Voice
agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing
benchmarks for
speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interruption: does the
agent resume the workflow at the correct step? Does it address the user's interjection? Does it avoid re-delivering content the user already heard? We introduce IHBench (Interruption Handling
Benchmark), a
benchmark that evaluates post-interruption recovery in voice
agents executing state-machine-driven workflows across 10 enterprise domains. Six interruption types are injected at controlled points mid-utterance, with per-interruption evaluation rubrics generated alongside the data. Each interruption is scored on two axes: task fulfillment and recovery quality. We evaluate 27 audio-
language model configurations from OpenAI, Google, and the open-weight community. Models vary widely, and recovery quality depends strongly on the interruption type. Across our experiments, closed-weight models are consistently more robust to interruptions than open-weight ones: they win far more often on task fulfillment, degrade roughly 3.3x more slowly as conversations grow longer, and show no audio-versus-text modality gap, whereas the open-weight models lose ground on all three. A human study validates the LLM judge against human annotators, and a cross-
benchmark analysis against AudioMultiChallenge indicates that recovery quality is a largely distinct capability axis.
Read the full abstract ▾
All authors Ahmad Salimi, Wentao Ma, Yuzhi Tang, Dongming Shen, Mu Li, Alex Smola
Artificial Intelligence · Cross-listed from cs.CL
A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization
Vu Nguyen Nguyen Xuan and Huy Ngo Quang
In this technical report, we focus on solving the challenge of Vietnamese multi-document abstractive summarization, introduced in the International Workshop on Vietnamese
Language and
Speech Processing (VLSP) 2022. We choose to follow the popular hierarchical approach, i.e. condensing each document followed by aggregation and summarization. We propose a novel yet simple strategy to shorten documents that is driven by the golden summary, thus ensuring high correlation between stages of the hierarchical approach. Our method achieves a ROUGE2-F1 score of 0.2468 on the VLSP's public test set, and can produce fluent and concise summaries. Additionally, we utilize external sources for extra data, which greatly enhances the quantity of data for Vietnamese multi-document summarization. The additional data is made available for the community.
Read the full abstract ▾
Artificial Intelligence
Analyzing the Narration Gap in LLM-Solver Loops
Zunchen Huang and Songgaojun Deng
Formal tools such as SAT and SMT solvers are increasingly embedded in
language model
reasoning pipelines when a safety or security critical question can be formulated in logic. Unlike chain of thought whose steps are sampled from the model distribution without formal guarantee, a solver produces a sound and independently verifiable answer. However, the soundness guarantee can be lost in the interaction between the solver and the model. The hybrid pipeline has three components: formalizing the question, deciding it, and narrating the result. Prior work has studied the formalization and decision, but not narration, which is the step that turns a formal tool's output into the user answer. To fill the narration gap, we first model the LLM-solver loop as a verified decision procedure. We further evaluate five open-sourced models under
prompt injection, and we find certificate gating makes the solver verdict sound, while an adversary can invert a verified conclusion across phrasings and channels. We study the mitigation through hardened
prompt that reduces injection significantly but cannot eliminate it and still suffers under adaptive attack. Combining the formal analysis and empirical studies, we show in the LLM-solver loop, robustness does not reach to the answer that the user finally reads.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
FlowFake: Liquid Networks for Audio Deepfake Detection
Shivaay Dhondiyal, Divyansh Sharma and Dinesh Kumar Vishwakarma
Audio deepfakes generated by neural text-to-
speech and voice-cloning systems threaten speaker verification and public discourse at scale. The core challenge is cross-
dataset generalization: detectors trained on one synthesis pipeline collapse on unseen forgeries. We argue that this failure is primarily because of structural synthetic
speech artifacts which are multi-timescale trajectory anomalies. Though every existing detector aggregates a fixed-window frame statistics, this misaligns the architecture with the signal. We propose FlowFake, a
Liquid Time-Constant (LTC) architecture whose hidden state evolves via a learned ODE, with per-
neuron adaptive time constants simultaneously resolving spectral (10ms) and prosodic (2s) cues. At only 34K parameters FlowFake achieves formal BIBO stability and O(dt^4) integration error. On a four-
dataset cross domain
benchmark (ASVspoof2019-LA, FakeOrReal, InTheWild, MLAAD), FlowFake reaches 75.29% on ASVspoof2019 trained only on FakeOrReal and 79.97% trained only on MLAAD. It outperforms RawGAT-ST and Whisper-DF on every evaluated pair and matching SSL Wav2vec2 (300x larger) at 0.01% of its parameter count. The source code is available on : https://github.com/GhostRider2023/FlowFake
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Exploring Feature Extraction Technique Parameters for Acoustic Gunshot Classification
Sinclair Gurny and Ryan Quinn
Acoustic gunshot detection is a problem with applications across civilian public safety, military operations, and wildlife conservation, yet the field lacks a rigorous exploration of feature extraction techniques with a focus on generalization to realistic data. The mixed effectiveness of commercial gunshot detection and classification systems indicates an open problem that is not adequately addressed by the current literature. In this paper, we present a systematic investigation of common feature extraction techniques using a
dataset of 23,000 gunshot recordings across 85 firearms and 21 calibers. We
benchmark three feature extraction techniques with 12 total unique parameter sets using ResNet-18. Our results demonstrate that using the correct feature extraction technique can improve top-1 accuracy by up to 20%, and utilizing the correct parameters for a given feature extraction technique can improve that value by up to 4.7%.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SY
GDGU: A Gradient Difference-based Graph Unlearning Method for Cyberattack Localization in Electric Vehicle Charging Networks
Nanhong Liu, Mucun Sun and Jie Zhang
Electric vehicle charging stations (EVCSs) can expose distribution feeders to cyberattacks. While machine learning methods, including graph neural networks, can localize which bus is compromised, significant challenges remain in data sharing and model training. For example,
privacy regulations grant EVCS owners the right to delete their training data from a deployed model, yet retraining from scratch on every request is computationally prohibitive. To address this, we study graph unlearning (GU) for EVCS cyberattack localization, formulated as a feature-level unlearning problem on a graph-level multi-label classification task. Specifically, we propose gradient difference-based graph unlearning (GDGU), which removes the influence of the requested deletion data through a first-order parameter correction. The correction is computed from the gradient difference between the original training data and a modified
dataset in which only the charging power features at the requested EVCS buses are unlearned. Then, a batch-normalization recalibration and a brief recovery fine-tuning step are applied to restore localization utility. We
benchmark GDGU against two second-order GU baselines on the IEEE 34-bus, 123-bus, and 8500-node distribution networks across three graph neural network backbones and cumulative unlearning scenarios. GDGU matches the strongest baseline on localization utility and reaches forgetting fidelity close to full-retraining, while unlearning 10 to 12 times faster than retraining from scratch and using far less
memory than the second-order GU baselines.
Read the full abstract ▾
Artificial Intelligence
Uncertainty Decomposition for Clarification Seeking in LLM Agents
Gregory Matsnev
Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insufficient for interactive large
language model (LLM)
agents and call for underspecification-aware, decomposed, and communicable uncertainty representations that can unlock new
agent capabilities such as proactive clarification seeking and shared mental-model building. Practical deployment constraints – black-box APIs, interactive latency budgets, and the absence of labeled trajectories – rule out logprob-based, multi-sampling, and training-based methods, leaving
prompt-based estimation as the most viable family for surfacing such signals at deployment time. We answer this call with a simple
prompt-based decomposition that separates action confidence from request uncertainty (u), enabling the
agent to ask for clarification when the task specification is ambiguous. To evaluate it, we introduce two clarification-augmented
benchmarks (WebShop-Clarification and ALFWorld-Clarification) in which 50% of tasks are deliberately underspecified, and systematically compare the proposed decomposition against ReAct+UE and Uncertainty-Aware
Memory (UAM) across five LLM backbones (GPT-5.1, DeepSeek-v3.2-exp, GLM-4.7, Qwen3.5-35B, GPT-OSS-120B) on these variants together with the standard WebShop, ALFWorld, and REAL
benchmarks for fault detection. Averaged across the five backbones, the proposed decomposition improves clarification F1 on ALFWorld-Clarification by 73% over ReAct+UE and by 36% over UAM, and leads clarification F1 on every backbone on WebShop-Clarification and on four of five backbones on ALFWorld-Clarification, indicating that the gains generalize beyond a single LLM.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from astro-ph.SR
Review of Machine Learning Models for Solar Energetic Particle Prediction
Spiridon Kasapis, Pouya Hosseinzadeh, Kathryn Whitman et al. (+73 more)
Solar energetic particle (SEP) events have attracted increasing
attention due to their significant radiation hazards for aviation, spacecraft electronics, and human missions beyond Earth's magnetosphere. From a scientific perspective, SEP events are intriguing because they arise from a set of physical processes extending from the
solar surface and corona through the heliosphere, offering insight into particle acceleration and transport mechanisms that are widely applicable across astrophysics. Therefore, advancing our ability to understand and predict SEP events is essential both for deepening our knowledge of such mechanisms and for safeguarding space technologies and exploration. Traditionally, researchers have modeled SEPs using physics-based simulations and empirical methods. More recently, machine learning (ML) has emerged as a new tool for understanding and predicting SEP events. The purpose of this manuscript is to review the currently available ML models for SEP prediction, identify the
datasets used for training, compare their architectures, inputs, and outputs, and, based on these insights, outline good practices and recommendations for future research.
Read the full abstract ▾
All authors Spiridon Kasapis, Pouya Hosseinzadeh, Kathryn Whitman, Ricky Egeland, Manolis Georgoulis, Angelos Vourlidas, Athanasios Papaioannou, Eleni Lavasa, Anastasios Anastasiadis, Giorgos Giannopoulos, Andres Munoz-Jaramillo, Bala Poduval, Irina N. Kitiashvili, Alexander G. Kosovichev, Viacheslav Sadykov, Soukaina Filali Boubrahimi, Tate T. Hutchins, Hameedullah A. Farooki, Manuel E. Cuesta, Leng Y. Khoo, Sungmin Pak, Robert Czarnota, Jamie S. Rankin, Jamey Szalay, Mitchell M. Shen, Georgios Livadiotis, Zigong Xu, David J. McComas, Nikolaos Sarlis, Dionissios Hristopulos, Arik Posner, Alec J. Engell, Mohammed AbuBakr Ali, Ali G. A. Abdelkawy, Abdelrazek M. K. Shaltout, M. M. Beheary, Christina O. Lee, Sigiava Aminalragia-Giamini, Constantinos Papadimitriou, Ingmar Sandberg, Savvas Raptis, Shah Muhammad Hamdi, Monica Laurenza, Mirko Stumpo, Sumanth A. Rotti, India Jackson, Aatiya Ali, Atilim Gunes Baydin, Nathan Schwadron, Subhamoy Chatterjee, Maher A. Dayeh, Gelu M. Nita, Patrick M. O'Keefe, Chun Jie Chong, Paul Kosovich, Russell D. Marroquin, Berkay Aydin, Petrus C. Martens, Lulu Zhao, Yang Chen, Yian Yu, Monica G. Bobra, Ward Manchester, Tamas Gombosi, Ming Zhang, Jesse Torres, Philip K. Chan, Mohamed Nedal, Kamen Kozarev, Peijin Zhang, Kimberly Moreland, Hazel M. Bain, Samuel Hart, Michael J. Starkey, Alan G. Ling, Simone Benella
Artificial Intelligence
ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence
Ashim Dhor, Rasel Mondal and Pin-Yu Chen
Convolutional networks, recurrent networks, and
transformers each encode different inductive biases – locality, sequential
memory, and content-dependent pairwise interaction – and have remained mathematically distinct since their inception. We show that this fragmentation reflects not a fundamental diversity in how signals should be processed, but rather incomplete views of a single underlying mathematical object: a learnable integral transform. We introduce the Integral Transform Network (ITNet), a unified architecture built around a learnable kernel that depends jointly on positions and features. This kernel is implemented as a small neural network, specifically an MLP, that models pairwise interactions, enabling the model to adapt its behavior from data. We show that convolution, self-
attention (including multi-head), and autoregressive recurrence (including LSTM, GRU, S4, and Mamba) arise as special cases under appropriate parameterizations, and that ITNet is a universal approximator of continuous operators. To make this practical, we develop tiled kernel fusion, importance-weighted Monte Carlo integration, and learned low-rank factorization, enabling efficient and scalable computation. A single ITNet architecture with a shared operator and lightweight modality-specific encoders matches or exceeds specialized baselines on ImageNet-1K , GLUE, ModelNet40, VQA\,v2 and NLVR2. The results demonstrate that a single learned interaction mechanism can recover the behavior of all three architectural families from data.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
Yueyi Sun, Yuhao Wang, Jason Li et al. (+8 more)
Multimodal large
language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a
multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source
diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured
attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and
token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning
Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of
multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of
diffusion language models. Code, models, and
datasets are released.
Read the full abstract ▾
All authors Yueyi Sun, Yuhao Wang, Jason Li, Ye Tian, Tao Zhang, Jacky Mai, Yihan Wang, Haochen Wang, Jinbin Bai, Ling Yang, Yunhai Tong
Artificial Intelligence · Cross-listed from cs.AR
A Tool for the Synthesis of Adaptive Probabilistic Processors Based on the Ising Model
Jonathan Juracy Carneiro da Silva, Leonardo R. Gobatto and Jose Rodrigo Azambuja
This work presents a tool for the synthesis and simulation of probabilistic architectures for solving combinatorial optimization problems by mapping them to the Ising model. The proposed approach automatically constructs the Ising
Hamiltonian and determines the number of probabilistic elements (p-bits) based on problem characteristics such as size and
topology. Furthermore, the tool introduces an adaptive strategy for selecting the most suitable update
algorithm among Gibbs Sampling, Simulated Annealing (SA), Simulated
Quantum Annealing (SQA), and cluster-based methods. Experimental results using
benchmark problems demonstrate improved convergence behavior and flexibility compared to fixed approaches. The proposed framework enables systematic evaluation of probabilistic computing strategies and supports the development of future hardware implementations based on MTJs and p-bits.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices
Hassan Dbouk, Matthias Reisser, Prathamesh Mandke et al. (+2 more)
Fine-tuning of Large
Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe
memory constraints on consumer hardware. Peak
memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce
memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2)
memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant
token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak
memory, enabling fine-tuning on resource-constrained devices.
Read the full abstract ▾
All authors Hassan Dbouk, Matthias Reisser, Prathamesh Mandke, Likhita Arun Navali, Christos Louizos
Artificial Intelligence
Martin Kolář
Can Large
Language Models (LLMs) discern when their own outputs are misaligned with human ethics? And can they self-correct? We endow an LLM with a conscience step that reviews its own
reasoning and outputs, and we extend the training loss with an
alignment component using Direct Preference Optimization (DPO) to steer the model away from non-ethical outputs. The result is an online technique to align models in a wide range of applications: training, fine-tuning,
adversarial prompting, and zero-shot learning. It does not require a weaker or stronger judge, relying instead on a frozen copy of itself. In previous work, the Emergent Misalignment scenario showed a range of emergent unethical behaviors from fine-tuning the model to hack code. Instead, we empirically show how to achieve Emergent
Alignment: a single high-level introspective question steers training toward an ethical model under the same code hacking scenario.
Read the full abstract ▾
Artificial Intelligence
REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk
Ethan Elio Meidinger, Seowung Leem, Zeyun Zhao et al. (+1 more)
The retina offers a noninvasive window into neurodegenerative disease, capturing subtle structural patterns associated with a risk of future cognitive decline.
Vision-
language alignment frameworks such as REVEAL have shown that pairing retinal fundus images with structured clinical risk narratives improves early prediction of Alzheimer's disease (AD). A key design choice in these approaches is the use of phenotypic grouping, where individuals with similar risk profiles are treated as multi-positive pairs during contrastive learning. However, existing methods operationalize phenotypic similarity as a discrete construct, relying on hard group assignments that impose rigid supervision and decouple group formation from representation learning. We propose a continuous formulation of phenotypic structure within contrastive learning. Rather than assigning samples to fixed clusters, we model inter-subject similarity as a differentiable weighting function derived from intra-modality
embedding similarities in both retinal images and risk profiles. These weights define soft multi-positive relationships through a continuous aggregation operator, enabling graded supervision that reflects the spectrum nature of disease risk. We further introduce a soft-target contrastive objective that jointly learns cross-modal
alignment and phenotypic structure in an end-to-end manner. Evaluated on UK Biobank retinal imaging data for incident AD prediction, the proposed framework consistently outperforms discrete group-based contrastive learning and standard
vision-
language baselines. By treating phenotypic similarity as a learnable, continuous signal rather than a fixed grouping rule, our approach provides a principled and robust foundation for population-scale neurodegenerative risk modeling from multi-modal retinal and clinical data.
Read the full abstract ▾
All authors Ethan Elio Meidinger, Seowung Leem, Zeyun Zhao, Ruogu Fang