Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Wednesday 12 August

Computer Vision

Draw This First

We invert the typical formulation of sketch generation: instead of drawing strokes in order, we predict a 2D field that defines the order in which strokes are drawn. We use a pretrained latent flow-matching transformer to supply the image prior to predict an intermediate representation, while training the VAE's decoder to predict the order field, stroke mask, and stroke segmentation. We vectorize the predicted segmentation into polylines and sort them by the field, producing an ordered vector sketch. Our model can predict an ordered vector sketch from a text description or derender an image into ordered vectors; for either, it follows text instructions specifying the order of drawing.
Read the full abstract

Robotics

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets. Because this data solves the fundamental exploration problem, we can train an off-policy RL agent using purely sparse task rewards, drastically reducing the time required to learn new skills and eliminating the need for manual tuning. Integrating this high-level agent with a low-level dynamic stability controller yields more optimal behaviors that strictly align with true task objectives, ultimately allowing the learned policies to surpass the original optimal control teacher. We validate the robustness of this sim-to-real framework by successfully deploying complex loco-manipulation skills across different morphologies, including an arm-equipped Spot quadruped and a G1 humanoid.
Read the full abstract

All authors Martin Schuck, Maks Sorokin, Simone Manni, Duy Ta, Angela P. Schoellig, Marco Hutter, Simon Le Cleac'H, Jan Brüdigam

Computation and Language

Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

Developing dialogue systems capable of engaging in multi-turn, goal-oriented conversations remains a significant challenge, especially in specialized domains with limited data. This research proposes a novel framework called Preference Tree Optimization (PTO), designed to iteratively improve agent models in such dialogue systems, by generating preference data using a method called Preference Tree with Look-Ahead. Focusing on Motivational Interviewing (MI) – a counseling technique aimed at facilitating behavioral change – we leverage virtual patients and an oracle evaluator to simulate conversations and generate rich preference datasets. By combining this method with Direct Preference Optimization (DPO), we aim to enhance the agent's decision-making capabilities over iterative training cycles. The proposed framework addresses data scarcity and advances the development of more nuanced and effective dialogue systems in goal-oriented domains. Experimental evaluations demonstrate that the PTO framework enhances dialogue agents' performance in goal-oriented conversations within the domain of Motivational Interviewing (MI). Models trained with PTO consistently outperformed the baseline in key metrics such as session satisfaction and working alliance. Additionally, incorporating look-ahead simulations led to improved long-term planning and more effective conversational strategies, with deeper look-ahead configurations yielding the most stable and high-scoring results.
Read the full abstract

All authors Lior Baruch, Moshe Butman, Kfir Bar, Doron Friedman

Computers and Society

Reconfiguring Geovisualization in the Age of Generative AI: Insights from Domain Experts

GenAI is increasingly integrated into geovisualization, yet its broader implications for professional practice are insufficiently understood. To examine these implications, we conducted semi-structured interviews with 20 geovisualization experts. The interviews were structured around four broad analytical domains: Data, Ideation, Prototyping, and Iteration, while also encouraging participants to reflect on issues that extend beyond these activities. Our findings show that GenAI expands the capabilities of geovisualization, particularly in terms of data handling, creative exploration, and rapid prototyping, but does not simply remove existing constraints. Instead, key bottlenecks are shifting from production to judgment and verification. As routine technical tasks become more automated, professional value increasingly depends on spatial reasoning, contextual interpretation, aesthetic and ethical judgment, and the ability to assess whether AI-generated outputs are appropriate for use. At the same time, GenAI introduces new challenges regarding provenance, interpretability, and accountability, raising questions about how responsibility should be distributed across models, developers, practitioners, institutions, and users. These shifts are particularly significant in geovisualization because spatial representations are constrained by geographic reality and must balance scientific validity, visual expression, and technical implementation. We therefore argue that responsible GenAI in geovisualization requires domain-specific approaches to spatial validation, provenance, uncertainty communication, human oversight, and accountable use. This study provides an expert-grounded perspective on how GenAI is reconfiguring geovisualization as a practice of spatial knowledge production. It also identifies implications for future professional practice, education, system design, and governance.
Read the full abstract

All authors Mengyi Wei, Chenyu Zuo, Jiaying Xue, Nianhua Liu, Dongsheng Chen, Shengkai Wang, Yu Feng, Liqiu Meng

Numerical Analysis

Numerical methods for the simulation of quantum walks and quantum annealing

It is known that Chebyshev based polynomial approximation gives a near-optimal rate of convergence for calculating a function of a Hermitian matrix. However, previous work has not discussed the option of true minimax approximation, nor the specifics of writing a high performance implementation with a rigorous analysis of errors. This work provides such an analysis and an open-source implementation of three approximation methods in C++.
Read the full abstract

Machine Learning

Towards Truly Unsupervised Evaluation of Feature Selection – Extended Version

Feature selection is one of the most important and fundamental tasks in data mining, tackled by a family of methods with an established set of evaluation techniques to measure the quality of a specific method. Most of the methods commonly used for the unsupervised evaluation of feature selection algorithms suffer from critical design flaws which question their unsupervised nature. In this paper, we provide a critical discussion on the established allegedly unsupervised evaluation techniques, and shed light on the reasons why they are not truly unsupervised but, at best, supervised evaluation under an unsupervised downstream task. We also propose a novel, truly unsupervised evaluation framework to measure the quality of the feature selection algorithms without any form of information about the labels. The proposed framework utilizes unsupervised Principal Component Analysis, and optimal transport to measure the quality of the feature selection methods in a truly unsupervised manner.
Read the full abstract

Discrete Mathematics

Greedy approaches for Gold Grabbing on subclasses of split graphs

The Gold Grabbing Game is a combinatorial game on vertex-weighted graphs in which two players alternately remove vertices while maintaining graph connectivity, aiming to maximize the total collected weight. Although the literature has primarily focused on strategies that guarantee victory, the question of optimality — i.e., maximizing total gain — remains less explored. In this work, we investigate the behavior of the greedy strategy in this setting. We show that this approach is not optimal for general split graphs, highlighting structural limitations of this class. On the other hand, we prove that for complete split graphs $CS_{(2,n)}$, the greedy strategy yields a sequence of moves that maximizes the game value. As a consequence, the first player does not lose when the number of vertices is even. These results contribute to a better understanding of the structural conditions that ensure the optimality of simple strategies in graph-based combinatorial games.
Read the full abstract

Computer Vision

Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving

Aggregate metrics may not fully reflect performance in insufficiently examined high-risk driving conditions. We propose RISC (Risk-Informed Slice Coverage), a practical protocol for risk-guided stress testing and coverage-qualified evaluation. Risk-guided stress testing directs a finite audit budget toward risk-relevant sub-datasets, called risk slices, while coverage-qualified evaluation reports results together with explicit statements about which slices are sufficiently or insufficiently covered. The protocol translates safety concerns into machine-readable risk slices, uses lightweight signals to tag candidate data, selects a compact audit set by risk, and qualifies the results using coverage evidence. An LLM can optionally support this process by surfacing relevant but potentially overlooked conditions during test planning, thereby helping engineers not to forget the obvious. RISC is model-agnostic and can be applied to perception modules, driving models, and other autonomous-driving subsystems. We instantiate the protocol for monocular pedestrian perception using 1,000 frames from the Zenseact Open Dataset, image statistics, and a YOLO-based detector proxy. In this proof-of-concept study, risk-guided selection increases critical failure discovery from 34.0% under random sampling to 98.5%. RISC provides a lightweight, assurance-oriented evaluation layer that complements scenario categorization, coverage assessment, and broader testing-and-verification workflows.
Read the full abstract

Computer Vision

Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation

Kolmogorov–Arnold Networks (KANs) introduce explicit functional representations by parameterizing each network edge as a learnable univariate function. However, existing KAN-based segmentation models optimize edge functions only through objectives defined after edge aggregation, leaving individual functions without an explicit pre-aggregation learning target. To address this limitation, we propose Function-Space Joint-Embedding Predictive Learning (FS-JEPA) for medical image segmentation. Our FS-JEPA framework moves predictive learning into the pre-aggregation function space of KANs. A masked online branch predicts structured signatures of sampled KAN edge functions generated by a full-context exponential moving average target branch, while shared edge indices preserve correspondence between predictions and targets. Rather than predicting an isolated edge response, we represent each sampled edge function using a multi-radius signature composed of function evaluations around its input anchor. This structured representation captures local functional variations that cannot be characterized by a single response and provides a more informative predictive target. The function-space objective is jointly optimized with the segmentation loss during training, while the predictive branch is removed at inference. Experiments on five medical image segmentation benchmarks show that our FS-JEPA achieves the best average Dice and outperforms the strongest competing KAN-based method by +2.25 percentage points.
Read the full abstract

All authors Yungeng Liu, Xuanzi Fang, Yuge Zhang, Shuqi Ren, Haijin Zeng, Yongyong Chen

Information Retrieval

Token-Level Credit Assignment Optimization for Generative Document Retrieval

Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, i.e., the model makes a sequence of token-level decisions, selecting a DocID token at each decoding step, with the resulting complete sequence identifying the retrieved document. However, relevance feedback is available only after the complete DocID has been generated and mapped to a document, resulting in a granularity mismatch between token-level generation decisions and document-level retrieval supervision. Consequently, existing reinforcement learning methods for generative retrieval rely on sequence-level rewards, assigning the same document-level relevance signal to every decoding step. Such uniform credit assignment obscures the contribution of individual token decisions, making it difficult to identify which decisions contribute to retrieval success or failure. In this paper, we propose Token-Level Credit Assignment for Generative Retrieval (TCA), a fine-grained reinforcement learning framework that aligns the granularity of credit assignment with that of autoregressive DocID generation. Unlike assigning a single reward to an entire generated DocID, TCA derives fine-grained rewards by comparing the hidden-state trajectory of each generated DocID with the gold DocID trajectory obtained from a frozen reference model. These trajectory-based rewards provide differentiated feedback across decoding steps, allowing the policy to reinforce generation paths that remain aligned with the target DocID. Moreover, TCA decouples token-level credit assignment from policy optimization and can be instantiated with both GRPO and PPO. Experiments on benchmarks show that our method consistently outperforms baselines, demonstrating the effectiveness of fine-grained supervision for aligning DocID generation.
Read the full abstract

All authors Xinpeng Zhao, Yang Liu, Ran Chen, Xinyu Ma, Daiting Shi, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Xin Xin

Systems and Control

Network Topology Reconfiguration: Optimal Transition Planning

Network topology reconfiguration (NTR) can reduce power system operating costs by co-optimizing generation dispatch and substation switching, but the reported savings describe a target operating point rather than a way to reach it. Reaching this operating point requires a sequence of intermediate operating points, each satisfying the AC power flow equations and thermal limits; because each topology admits its own feasible dispatch region, a naive transition that switches or redispatches first can drive intermediate flows past their thermal limits. Existing methods leave this gap open: snapshot NTR identifies a target but not a route. We formulate the Optimal Transition Planning (OTP) problem, co-optimizing the switching sequence and dispatch trajectory subject to AC feasibility at every intermediate point. We solve this problem with a receding-horizon framework: a DC planner proposes a trajectory that is certified against an AC feasibility filter, and infeasible topologies are excluded using reusable combinatorial cuts. Case studies on congested PGLib-OPF systems up to 1354-bus show that the method produces AC-feasible transitions that reduce operating cost by up to 18.4% compared to the no-switching ACOPF solution on commodity hardware.
Read the full abstract

All authors Basel Morsy, Jochen Stiasny, Adolfo Anta, Jochen Cremer

Information Theory

Secure Coverage Enhancement in Aerial Reconfigurable Intelligent Surface-Assisted High-Speed Train Communication Systems

High-speed trains (HSTs) have become a prominent means of transportation, requiring high data rates and reliable communication services for HST passengers. However, the wireless channels in HST communication systems are susceptible to various security threats, including eavesdropping. Addressing these security concerns is therefore of critical importance. One promising technology for enhancing security is the integration of a reconfigurable intelligent surface (RIS) on an unmanned aerial vehicle, referred to as an aerial reconfigurable intelligent surface (ARIS). This technology offers significant potential for improving wireless network performance, though it also introduces unique challenges in terms of physical layer security (PLS). This paper investigates the PLS of ARIS-aided HST communication systems. A problem of maximizing the weighted sum secrecy rate is formulated by jointly optimizing the active beamforming at the base station (BS) and the phase shift at the ARIS, subject to constrains on the BS transmit power and the unit modulus of the ARIS reflecting coefficient. To address this problem, a joint optimization algorithm is proposed using the block coordinate descent method. Specifically, the problem is decomposed into two subproblems: active beamforming design and ARIS phase shift optimization. The active beamforming is optimally designed via the successive convex approximation technique, while the ARIS phase shift is efficiently updated using the alternating direction method of multipliers technique. Simulation results demonstrate the rapid convergence of the proposed algorithm, which achieves a higher secrecy rate compared to existing methods in the literature.
Read the full abstract

All authors Changzhu Liu, Ruisi He, Bo Ai, Yong Niu, Zhu Han, Gongpu Wang, Haoxiang Zhang, Jiahui Han, Zhangdui Zhong

Computer Vision

Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection

Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal supervision and fine-grained spatial reasoning. A key obstacle is the tendency of temporal detectors to latch onto background and scene-level cues rather than truly discriminative anomaly evidence. This background bias raises ethical concerns: models may inadvertently associate anomalies with societal or environmental context rather than authentic crime-related cues. Without spatial grounding, such biases remain hidden and unauditable. To address this, we propose SST-WSVADL, a sparse spatio-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization. Rather than processing all spatial regions indiscriminately, SST-WSVADL progressively focuses on the most anomaly-relevant spatio-temporal regions through dynamic sparsification, naturally suppressing background dominant content while preserving discriminative evidence. The temporal and spatial branches are coupled end-to-end via motion-aware regularization that guides sparsification toward dynamically informative regions, without relying on external detectors or vision-language prompts. We publicly release frame-level spatial annotations and a method-agnostic evaluation protocol for three public datasets: UCF-Crime, XD-Violence, and MSAD. These resources enable the community to audit spatial biases in WSVAD predictions, supporting progress toward more ethical and accountable anomaly detection. Experiments demonstrate that SST-WSVADL is competitive with prior methods across benchmarks while enabling localization and patch-level auditability of scene bias, providing a reproducible foundation for interpretability-oriented evaluation of WSVAD models.
Read the full abstract

All authors Sara Abdulaziz, Abdulrahman Al-Abri, Giacomo D'Amicantonio, Egor Bondarev

Numerical Analysis · Cross-listed from math-ph

Model-Consistent Structured-Hankel Matrix Completion for 3D Sparse Multi-frequency Electromagnetic Source Reconstruction

Reconstruction of 3D electromagnetic currents from sparse, multi-frequency, far-field radiation data is severely ill-posed because sparse sampling masks specific current Fourier modes and the missing spectrum enlarges the null space of the forward operator. Although structured-Hankel completion can recover missing spectrum by exploiting the finite rate of innovations structure of a compactly supported geometrically sparse source, it treats current components independently without guaranteeing compatibility with the model. This often renders non-physical solutions that violate model consistency. To resolve this, we propose a training-free Maxwell-model-consistent 3D structured-Hankel framework (MC-Hankel) that alternates joint low-rank Hankel completion with an exact, closed-form projection onto the true Maxwell synthesis subspace while enforcing conjugate symmetry and noise-aware data fidelity. Across tests on two source models, three sparse sampling rates (30%, 40%, and 50% of a Nyquist-sampled grid), and clean versus noisy (10 dB SNR additive white Gaussian noise) conditions, MC-Hankel consistently outperforms sub-sampled Fourier inversion, scale-normalized $\ell_1$-compressed sensing baseline, and the standard joint 3D annihilating filter-based low-rank Hankel matrix completion approach (ALOHA). Across all considered source-noise-sampling configurations, MC-Hankel improves mean peak SNR (PSNR) by 0.65-4.22 dB and tri-planer structural similarity (3D SSIM) by $0.0266$-$0.0703$, reduces relative full-volume $\ell_2$ reconstruction error by $7.4\%$-$38.9\%$, and brings non-physical model residuals down to machine precision over standard joint 3D ALOHA with merely 17% computational overhead. Exact signed-rank tests are underpowered for five paired trials, so statistical conclusions are reported together with paired bootstrap intervals, effect sizes, and small-sample limitations.
Read the full abstract

Machine Learning · Cross-listed from math.OC

Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization

Acceleration for deterministic root-finding problems has been extensively studied in recent years; specifically, the anchor-based, or Halpern-type methods achieve optimal convergence rates with respect to the operator norm. However, acceleration via these methods does not directly carry over to stochastic setting due to accumulation of errors, unless one enforces diminishing variance via increasing batch sizes or variance reduction techniques. In this work, we show that another class of acceleration, namely the dual-anchor mechanism, extends to the stochastic setting without such error accumulation, in contrast to anchor-based algorithms. Consequently, we cleanly achieve $O(\epsilon^{-3})$ complexity with iteration-independent batch size, without any variance reduction or double-loop recursive regularization, for stochastic root-finding (resp. fixed-point) problems with cocoercivity (resp. square-nonexpansivity) in expectation. For strongly monotone operators, the same algorithm attains a sharper $\widetilde{O} (\epsilon^{-2})$ complexity, nearly matching the lower bound in terms of $\epsilon$-dependence.
Read the full abstract

Discrete Mathematics

Search and Rescue on the Plane

We study a planar variant of the search and rescue problem whereby an agent starting at an arbitrary position $P_{\theta,r} = (r\cos\theta, r\sin\theta)$ in the plane must locate an object at an unknown position on the positive $x$-axis and deliver it to the origin. Our main contribution is to characterize the optimal form of any competitive algorithm, derive closed-form expressions for the competitive ratio, and identify a critical angle $\theta^* \approx 15.6^\circ$ which yields a phase transition to optimal competitive search and delivery in the following sense. For each angle $-\pi \leq \theta \leq \pi$ we compute a checkpoint (landing position on the $x$-axis) where the agent must go first prior to initiating a search on the $x$-axis in order to optimize the competitive ratio of search and delivery. We show that if $|\theta| \geq \theta^*$ then the checkpoint is at the origin, while if $|\theta| < \theta^*$ then the agent should land at the checkpoint $(r \cdot k_{|\theta|}, 0)$ on the $x$-axis, where $k_{|\theta|}$ is a real number given by an explicit formula we present.
Read the full abstract

All authors Jared Coleman, Evangelos Kranakis, Danny Krizanc, Oscar Morales-Ponce

Machine Learning

Clustered Randomized Smoothing for Stochastic Prediction Functions

Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularly against adversarial perturbations. Yet, in stochastic multi-modal regression settings, randomized smoothing often fails due to mode collapse, yielding averaged predictions that do not reflect the underlying distribution. To address this limitation, we propose clustered $\alpha$-smoothing, a framework that (1) partitions noisy samples using an arbitrary clustering algorithm, (2) applies $\alpha$-smoothing locally within each cluster, and (3) combines the resulting predictions into a mixture distribution. By interpreting the smoothing distribution as a mixture of $\alpha$-smoothers, we derive a lower bound on the probability that the smoothed prediction lies within a union of compact regions corresponding to distinct modes. We empirically evaluate our framework on two benchmarks, demonstrating substantial improvements over state-of-the-art methods. In stochastic trajectory prediction on a driving simulator dataset, our approach achieves, on average, a $27\%$ lower Wasserstein distance to the ground-truth distribution compared to $\alpha$-smoothing. In quadrotor control, where modes correspond to distinct feasible paths to a target, our method reduces the collision rate by $90\%$ relative to the state-of-the-art randomized smoothing.
Read the full abstract

All authors Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann, Jens Kober, Arkady Zgonnikov, Luca Laurenti

Artificial Intelligence

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becomes faster and more automated, research on the mechanisms underlying AI remains largely manual. To bridge this gap, we introduce Mechanist, an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI. To ground novel mechanism hypotheses, we construct a scientific knowledge graph of 13,000 studies on AI mechanisms, alongside a multidisciplinary database of 43 million papers spanning 26 fields. For reliable experiment execution, we curate a library of 32 foundational methods for mechanism analysis. Compared with Claude Code and existing AI-scientist systems, Mechanist generates higher-quality mechanism hypotheses and executes experiments more reliably. Across four case studies, Mechanist autonomously discovers new model behaviors and their underlying mechanisms, and translates these discoveries into mechanism-guided interventions and interdisciplinary design. Specifically, Mechanist first uncovers a counterintuitive safety risk in scientific laboratories, showing that unsafe traits can transfer to fine-tuned student models through apparently safe training data and emerge across modalities. Mechanist then develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining. Building on this theory, Mechanist develops targeted interventions that improve model performance across diverse scenarios. Finally, Mechanist can also advance interdisciplinary discovery through mechanistic design, providing an alternative to the computationally intensive generate-and-rerank paradigm.
Read the full abstract

All authors Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Xin Xu, Yunzhi Yao, Dan Zhang, Fei Shen, Zhixiang Cui, Buqiang Xu, Haozhe Luo, Yunxiang Wei, Ningyu Zhang, Julian McAuley, Tat Seng Chua, Huajun Chen

Computer Vision

How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging

Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection together. Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators), evaluating over 80,000 trained models in total. By this, we find that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable. Towards closing it, we explore two strategies, ensembling and a small target-labeling budget; both narrow this gap but do not close it entirely. Overall, deployable UDA depends on the complete pipeline; addressing the less explored selection step could bring much of current UDA closer to clinical use. Our code is open sourced at \href{https://xiongyiheng.github.io/complete-uda-pipeline-site/}{Project Page}.
Read the full abstract

All authors Yiheng Xiong, Luisa Gallée, Daniel Santak Wolf, Heiko Hillenhagen, Michael Götz

Sound · Cross-listed from eess.AS

The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models

Recent advances in large language models (LLMs) and multimodal LLMs (MLLMs) have created new opportunities for wearable speech interfaces, with smart glasses providing an egocentric platform for continuous audio sensing and assistance. However, speech recognition and understanding in this setting remain challenging because of dynamic acoustic conditions, speaker overlap, and the spatial ambiguity introduced by wearer-centered recording geometry. To support systematic evaluation in this setting, we introduce the IEEE SLT 2026 SmartGlasses Challenge for egocentric multi-speaker speech processing. The challenge consists of two tracks, Dyadic Dialogue Understanding and Multi-party Meeting Understanding, and jointly evaluates Time-Stamped Speaker-Attributed Automatic Speech Recognition (TSA-ASR) and Spoken Language Understanding (SLU). It is built on a 106-hour four-channel egocentric speech dataset containing 714 sessions collected in real-world scenarios. This paper describes challenge tasks, dataset construction, submissions, and summarizes the main findings from the shared evaluation. The results show that heavy speaker overlap remains a major factor affecting TSA-ASR performance, while paralinguistic acoustic understanding continues to be difficult for current audio-language models in complex SLU settings. Further details can be found on the official challenge website.
Read the full abstract

All authors Dehui Gao, Zhixian Zhao, Zhennan Lin, Yujie Liao, Yuhang Dai, Yike Zhu, Longshuai Xiao, Hui Bu, Xin Xu, Xie Chen, Shuai Wang, Liumeng Xue, Zhonghua Fu, Jun Du, Eng-Siong Chng, Jun Zhou, Lei Xie

Computer Vision

LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration

Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow. Sparse attention reduces this cost without retraining, but existing methods pursue aggressive sparsity, where further speedup costs disproportionately more attention fidelity. We target the opposite end of this trade-off: fix near-lossless fidelity by construction, and remove as much computation as this constraint permits. Two observations make this regime practical: roughly 40% of block interactions can be removed while retaining 99% of the attention mass, and the high-mass support remains stable across denoising steps. We propose LoSA, a training-free sparse-attention method that fixes a retained-mass threshold of 99% rather than a sparsity ratio: it measures exact block attention masses at one early dense step, keeps, for each head and query block, the smallest key/value block set meeting the threshold, and reuses the frozen block indices for all remaining steps. On Wan2.1-1.3B, LoSA alone gives a $1.36\times$ speedup with a 0.06-point VBench Overall drop. The benefit is largest under composition: combined with feature caching, LoSA reaches a $3.2\times$ speedup on HunyuanVideo at a 0.02-point drop, versus 0.32 points for the strongest sparse baseline at comparable speed. Across three video diffusion transformers and speedups up to $3.2\times$, LoSA consistently achieves the best training-free speed-quality trade-off.
Read the full abstract

All authors Enhuai Liu, Yunke Wang, Yutong Wang, Changming Sun, Chang Xu

Machine Learning

Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision

Pairwise constrained clustering typically relies on hard must-link/cannot-link labels, whereas realistic pairwise supervision may be real-valued and entangle intrinsic ambiguity, expert judgment, and stochastic corruption. Existing deep constrained clustering (DCC) methods mainly target hard, expert-agnostic constraints, treating soft labels mostly numerically rather than semantically. We formalize this setting as uncertainty-aware probabilistic constrained clustering (UPCC), defining a canonical aleatoric relation through a heterogeneous observation process and analyzing its conditional identifiability. We introduce ProbPair, an angular pairwise objective for probabilistic relations, and build ECI-PP, an estimator–corrector–integrator framework that refines imperfect supervision via belief estimation, correction, and reliability-aware integration. Across challenging probabilistic supervision settings, experiments on diverse benchmarks show that ECI-PP outperforms state-of-the-art DCC methods and remains robust with a shared default configuration.
Read the full abstract

Machine Learning

SoftWater: Class-Aware Rate Allocation for Softmax Quantization

Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head holds 15–30% of all parameters, so a nominal “2-bit” model with an fp16 head can store several times as many bits per weight. We pose softmax-layer quantization as a rate-distortion problem under the KL divergence between the original and quantized output distributions. A second-order analysis reveals a class-aware geometry: quantization error is weighted jointly by feature covariance and class-specific softmax curvature. A separability approximation replaces the $Kn\times Kn$ Cholesky with one $n\times n$ factorization rescaled per class, making the lattice encodable by successive interference cancellation, with both statistics from a single forward pass. The resulting method, SoftWater, gives fine grids to frequent, low-variance classes and coarse grids to rare ones, a large gap under Zipfian token distributions. Across five models from 1B to 32B, SoftWater outperforms the released WaterSIC quantizer (near-optimal under linear-layer WMSE but not output KL) at matched head rates on 59 of 60 test points, using none of that pipeline's refinements and cutting head-induced KL by $6.5\times$–$8.3\times$ at 2 bits. On Llama-3.2-1B-Instruct with quantized bodies, a 2-bit head removes 45–60% of stored bytes for a $2.9$–$3.7\%$ perplexity increase. Because the class-side statistic comes from calibration data, matching calibration to the deployment domain gives the lowest KL on that domain throughout. On a tied model, a 4-bit head is near-lossless and a 2-bit head costs under 4% perplexity, making head quantization of such models practical.
Read the full abstract

Software Engineering

From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices

Medical devices are becoming more software-intensive, connected, and AI-enabled. Their development requires risk-management evidence aligned with ISO 14971 and, for software, IEC 62304. This evidence must be kept consistent across requirements, design decisions, software changes, verification results, complaints, and post-market data. These tasks are costly and depend on scarce safety and domain experts. Large language models (LLMs) may reduce parts of this effort because medical-device safety work is highly document-based. However, current LLM-based safety-engineering studies often address isolated methods, rely on generic prompting or public examples, and provide limited support for source links, traceability, uncertainty handling, lifecycle updates, and recorded expert review. This limits their use in regulated medical-device development. This paper argues that the central research problem is not safety-text generation, but source-linked safety-knowledge support. We propose an evidence-grounded framework that connects device artifacts, controlled knowledge storage and retrieval, method-specific generation of candidate safety items, critique and uncertainty checks, and recorded expert review. The framework prepares, links, checks, and updates candidate safety artifacts for expert decision-making. It does not decide whether a device is safe and does not provide regulatory approval. We also outline an evaluation strategy using non-public or newly built medical-device case studies and expert reference analyses to assess coverage, correctness, relevance, traceability, duplicate rate, unsupported claims, and review effort.
Read the full abstract

All authors Tuhinangshu Gangopadhyay, Rasmus Adler, Peter Liggesmeyer, Jan Reich

Systems and Control

Distributed Nash Equilibrium Seeking with Logarithmic Bit Rates over Digital Channels

This paper introduces quantization techniques to reduce the communication complexity in the distributed Nash equilibrium (NE) seeking problem, achieving an exponential reduction in bit rates over digital channels. The goal of distributed NE seeking algorithms is to coordinate agents in a network game toward equilibrium through iterative message exchanges among them via a communication network. The computational complexity of this distributed algorithm critically depends on network communication overhead in the digital channel, motivating the development of communication reduction mechanism. Regarding this, we proposed some quantizers based on sparsification and uniform quantization through a general class of ultimate-boundedness-based quantizers. Based on this, we propose a Passivity-Based NE seeking Algorithm with Time-varying scaling Error state Quantization (PBA-TEQ), and show that the linear convergence can be achieved under a sufficient condition. Moreover, when employing either the scalarization quantizer or the greedy quantizer, both belonging to the ultimate-boundedness-based quantizers, within the PBA-TEQ framework, we establish a lower bound on communication complexity of $\log_2(\mathcal{O}(nd))$ bit rates per transmission to achieve unbiased linear convergence, with $n$ being the number of agents and $d$ being the dimension of the decision state of the network game. Numerical simulation examples are provided to validate our theoretical results.
Read the full abstract

All authors Zihao Ren, Chengyang Jiang, Lei Wang, Yang Liu, Kemi Ding

Computation and Language

Unified Multi-Dialectal Neural Machine Translation for Bangla Using the Dwadash Benchmark Corpus

Neural Machine Translation (NMT) and Large Language Models (LLMs) excel at cross-lingual tasks but often fail to capture intra-lingual morphological variation, marginalizing dialectal speakers. In Bangla, existing translation frameworks commonly rely on Standard Colloquial Bangla (SCB) as an intermediate pivot, which can compound errors and reduce cross-dialectal nuance. To address this gap, we introduce a unified, multi-directional NMT system for direct translation between SCB and eleven regional variants. We first review prior dialectal NLP resources to identify existing technological gaps. As a foundational contribution, we construct and release a large multi-dialect parallel corpus for Bangla, comprising 14,562 aligned rows and 51,541 non-null sentence pairs through the integration of seven prior datasets and native-speaker-verified manual augmentation. Using this corpus, we benchmark state-of-the-art sequence-to-sequence architectures with parameter-efficient Weight-Decomposed Low-Rank Adaptation (DoRA). Results show that deep monolingual pre-training is more effective than large multilingual capacity for this task. The compact BanglaT5 model outperforms NLLB-200 and mBART-50 by up to 13.96 BLEU, achieving 29.26 BLEU, 57.26 chrF++, and 49.68 METEOR. A dataset scaling study shows diminishing returns beyond 3,000 parallel pairs and indicates that linguistic proximity to Standard Bangla is more important than raw data volume for translation quality. Finally, we deploy the optimized model as an INT8-quantized web application, providing a scalable, open-source framework for inclusive language technology and equitable digital access.
Read the full abstract

All authors Rakib Ullah, Md. Ruhul Islam, Tanbir Ahmed, Nayan Kumar Nath

Machine Learning

Reducing Symmetry Increase in Equivariant Neural Networks

Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields. Despite their remarkable capacity for representing geometric structures, ENNs suffer from degraded expressivity when processing symmetric inputs: the output representations are invariant to transformations that extend beyond the input's symmetries. The mathematical essence of this phenomenon is that a symmetric input, after being processed by an equivariant map, experiences an increase in symmetry. While prior research has documented symmetry increase in specific cases, a rigorous understanding of its underlying causes and general reduction strategies remains lacking. In this paper, we provide a detailed and in-depth characterization of symmetry increase together with a principled framework for its reduction: (i) For any given feature space and input symmetry group, we prove that the increased symmetry admits an infimum determined by the structure of the feature space; (ii) Building on this foundation, we develop a computable algorithm to derive this infimum, and propose practical guidelines for feature design to prevent harmful symmetry increases. (iii) Under standard regularity assumptions, we demonstrate that for most equivariant maps, our guidelines effectively reduce symmetry increase. To complement our theoretical findings, we provide visualizations and experiments on both synthetic datasets and the real-world QM9 dataset. The results validate our theoretical predictions.
Read the full abstract

All authors Ning Lin, Jiacheng Cen, Anyi Li, Wenbing Huang, Hao Sun

Machine Learning · Cross-listed from math.OC

Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai–Borwein Step Size

Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness. Their performance, however, remains sensitive to the step size: raw stochastic curvature estimates can fluctuate sharply, whereas line searches add repeated proximal evaluations. We introduce Ada-BPSG, a line-search-free BPSG method that couples the SAGA gradient table with a stabilized Barzilai–Borwein (BB) candidate. A mediant aggregates incremental secant information so that nearly singular local ratios receive little weight, and an explicit safeguard translates the resulting curvature estimate into the bounded step-size sequence required for convergence. This design yields a direct analytical chain from relative smoothness and component-wise variance control to convergence in finite-dimensional normed spaces. We prove an $O(n/K)$ ergodic rate for convex objectives, a restarted linear rate under relative quadratic growth, and an $O(1/K)$ bound for a Bregman proximal residual in the nonconvex setting. On logistic regression and sparse nonnegative matrix factorization, Ada-BPSG combines low objective values with substantially less sensitivity to the initial step size than standard variance-reduced baselines, while avoiding line search.
Read the full abstract

All authors Chenhan Jin, Shengze Xu, Binghui Xie, Kaiwen Zhou, Fan Jia, James Cheng, Tieyong Zeng

Computation and Language

Asymptotic Risk Calibration for Selective Question Answering

Large language models (LLMs) may generate fluent but incorrect answers, making uncertainty quantification important for reliable question answering. However, heuristic uncertainty scores cannot perfectly distinguish correct predictions from incorrect ones, and directly applying a fixed uncertainty threshold provides no statistical control over the error rate among accepted answers. To address this limitation, we propose A-CRC-QA, a post-hoc calibration framework for uncertainty-aware selective question answering. The proposed method reformulates selection-conditioned error control as a linear expectation constraint and applies a monotonized empirical-risk calibration procedure inspired by conformal risk control. Since the resulting instance-wise loss is generally non-monotone with respect to the acceptance threshold, our framework targets asymptotic rather than finite-sample risk control. A-CRC-QA is model-agnostic, requires no additional training, and can be combined with different uncertainty estimators. Experiments on CoQA and MedMCQA demonstrate its applicability to both open-ended and closed-ended question answering, achieving a favorable trade-off between accepted-answer reliability and answer retention compared with uncalibrated and confidence-bound-based baselines.
Read the full abstract

Machine Learning

Dual-Model Sentiment Analysis of Consumer Reviews in the Retail Coffee Sector Using Machine Learning and Deep Learning Approaches

Consumer reviews play an important role in shaping brand perception and business strategies, particularly in service-driven industries such as retail coffee. This study presents a comparative sentiment analysis framework for Starbucks customer reviews using classical machine learning and deep learning approaches. The dataset, collected from ConsumerAffairs, contains more than 700 reviews and was analyzed through preprocessing and exploratory data analysis to identify temporal and geographic patterns. Sentiment labels were generated by binarizing star ratings, with ratings of 4 and 5 classified as positive and ratings of 1 to 3 as negative. The resulting dataset was substantially imbalanced toward negative sentiment. Five machine learning classifiers, including Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and Naive Bayes, were evaluated alongside five deep learning models: LSTM, RNN, Bidirectional LSTM, GRU, and CNN. Model performance was assessed using accuracy, precision, recall, and F1-score. SVM achieved the highest accuracy among the machine learning models at 91.0 percent, while Bidirectional LSTM showed the strongest performance among the deep learning models and demonstrated good generalization on unseen data. The findings also show that class imbalance negatively affected positive sentiment recall across several models. Overall, this study provides a comparative evaluation of machine learning and deep learning approaches for real-world consumer sentiment analysis and highlights the importance of appropriate model selection and preprocessing for customer experience analytics in the retail coffee sector.
Read the full abstract

All authors Muntasir Hasan Kanchan, Md. Alamgir Hossain, Md. Samiul Islam, Muhammad Masud Tarek