Peer Revenue Play credits. Real papers.

Papers

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

Computer Science

cs Watch Computer Science

Wednesday 16 September

Robotics

Calibrated Probabilistic Obstruction Reasoning with Vision-Language Models for Grasping in Clutter

Thanh-Tuan Tran, Ngoc-Chien Chu, Thanh Nguyen Canh et al. (+3 more)

Retrieving a target from clutter requires deciding whether to grasp the target, remove a blocker, or defer. Existing methods typically commit to a single obstruction graph or removal strategy, ignoring uncertainty across alternative scene interpretations. They also rely on miscalibrated vision-language model (VLM) predictions and can produce pairwise obstruction relations that are jointly inconsistent. Moreover, current approximations provide no guarantees about the impact of discarded hypotheses on the final decision. We propose CPOR-Grasp, a calibrated probabilistic obstruction-reasoning framework that propagates uncertainty from pairwise evidence to action decisions. CPOR-Grasp calibrates and fuses VLM, depth, and amodal-mask cues to estimate obstruction probabilities, induces a distribution over valid obstruction graphs, and marginalizes over these graphs to compute the likelihood that the target is accessible or that a given blocker should be removed. To make inference tractable, it retains only the highest-probability graphs and derives a total-variation bound on the discarded probability mass, enabling certified decisions, adaptive stopping, and principled deferral. On synthetic and real UNOBench scenes, CPOR-Grasp outperforms state-of-the-art baselines. Calibration error decreases from 0.1416 to 0.0185 on the Gemini Robotics backbone, while graph truncation matches exact inference on 99.74% of decisions using 56 times fewer graphs. In real-world experiments, CPOR-Grasp achieves a 77.8% average success rate, surpassing SOTA baselines.
Read the full abstract

All authors Thanh-Tuan Tran, Ngoc-Chien Chu, Thanh Nguyen Canh, Nak Young Chong, Nguyen-Viet Ha, Xiem HoangVan

Computer Vision

Mask IPL: Noise-Free Intrinsic Position Learning via Computation Graph Clipping for Event-Based Spike-Driven Tracking

Yimeng Shan and Malu Zhang

Spiking Neural Networks (SNNs) match the event-driven nature of event cameras and naturally extract spatiotemporal features. These properties have motivated a series of recent studies on event-based tracking with SNNs. Intrinsic Position Learning (IPL) acquires strong position information without introducing additional parameters, making it a mainstream approach for position encoding in event-based spike-driven tracking. However, the mechanism behind its effectiveness lacks systematic theoretical analysis. Moreover, our analysis reveals that IPL introduces noise in both forward and backward propagation. The former increases inference error, while the latter prevents parameters from converging to better solutions. This paper presents a systematic analysis of IPL and demonstrates that its effectiveness stems from the synergy between IPL and multi-stage convolution. The zero blocks in the joint tensor act as zero padding for convolution, and the resulting boundary effect propagates layer by layer through multi-stage convolution. Every parameter update is therefore driven by a gradient that perceives the relative displacement between template and search frames. Positional encoding added after the convolutional stage cannot provide this information. We further propose a simple Computation Graph Clipping method that applies a validity mask determined by the layout to the operations of every layer, making invalid regions equivalent to zero padding in both forward and backward propagation. This eliminates the noise without introducing additional parameters and makes the actual gradient coincide with the ideal gradient. We name the improved method Mask IPL. Without increasing parameters or computational cost, Mask IPL improves the AUC of the Tiny-scale tracker on FE108, FELT, and VisEvent, and consistently improves the Base-scale tracker as well.
Read the full abstract

Data Structures and Algorithms

A sampling Lovász Local Lemma

Dimitris Achlioptas

We give an approximately uniform sampler for satisfying assignments of constraint satisfaction problems that satisfy $4\mathrm e p(\Delta+1)^2\le1$, where $p$ is the largest constraint-violation probability under the uniform product distribution, and $\Delta$ is the maximum degree of the dependency graph. The algorithm invokes the recent efficient approximate counting algorithm of Liu, Wang, Yin, Zhang, and Zhou~\cite{CountingLLL} as a subroutine and returns a satisfying assignment sampled within total-variation distance $\varepsilon$ of the uniform distribution in $(n+m/\varepsilon)^{O(k\Delta\log D)}$ time, where $n$ and $m$ are the numbers of variables and constraints, $D$ is the common domain size, and $k$ bounds the constraint arity. We also give an asymmetric product-form condition under which both counting and sampling are efficient. To supply the counts needed in the additional regime, we extend the marginal-expansion proof of Liu et al.
Read the full abstract

Human-Computer Interaction

"Okay, I've Actually Softened My Take on This": How People in Decentralized Social Media Reason about the Appropriateness of Generative AI

Romina Mahinpei, Manoel Horta Ribeiro, Andrés Monroy-Hernández et al. (+1 more)

Generative AI (GenAI) is increasingly integrated into social media, raising questions about whether, where, and how it belongs. In decentralized social media (DSM), these decisions are distributed across users, developers, moderators, and administrators, making GenAI a collective governance challenge. At the same time, public discourse often flattens arguments to broad pro- or anti-AI positions that offer little insight into what people actually find (in)appropriate and why. Through 20 semi-structured interviews with people from Mastodon and Bluesky, structured around seven GenAI scenarios, we examine how people reason about GenAI's appropriateness in DSM. We find that participants drew conditional boundaries around particular GenAI configurations through distinct, salient, and weighted considerations spanning technology, integration, and use. We conceptualize this as boundary drawing and show how making such boundaries visible can support more grounded design, policy, and collective deliberation around GenAI in DSM.
Read the full abstract

All authors Romina Mahinpei, Manoel Horta Ribeiro, Andrés Monroy-Hernández, Sohyeon Hwang

Machine Learning

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Yizhuo Li, Jianhao Yan, Yun Luo et al. (+9 more)

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo continuations, change sharply across intermediate states while critic predictions remain comparatively flat. We further observe this phenomenon in a controlled FrozenLake environment and find that it becomes more pronounced as the state space grows. Our theoretical and empirical analyses relate Value Flattening to an implicit variance penalty in the critic loss and redundant updates from temporally correlated states with similar gradients. Motivated by these findings, we introduce SParse Proximal Policy Optimization (SP$^3$O), which applies the value loss to only a few well-separated states in each response to mitigate both effects. Experiments on Qwen3-Base show that SP$^3$O with only three states supervised per response can mitigate Value Flattening and consistently improve the learned policy across model sizes and evaluation suites. Together, our results identify Value Flattening as an important yet overlooked failure mode of critic learning in standard PPO and show that a simple sparse supervision strategy can mitigate it.
Read the full abstract

All authors Yizhuo Li, Jianhao Yan, Yun Luo, Zhi Wang, Futing Wang, Rong-Xi Tan, Kanghui Tian, Ganqu Cui, Ning Ding, Peilin Zhao, Yafu Li, Yu Cheng

Data Structures and Algorithms

Total Variation Distance Estimation through Domain Reduction

Arnab Bhattacharyya, Graham Cormode, Yucheng Fu et al. (+1 more)

Computing the total variation (TV) distance between succinctly represented high-dimensional distributions is generally intractable. We give an FPRAS for TV distance between mixtures of product distributions and, more generally, for a natural class of structured probabilistic circuits. Our main technique is a novel application of domain reduction: Given a family of feature vectors indexed by assignments, we use Lewis-weight sampling to replace the assignment domain by a polynomial-size weighted subset that simultaneously approximates the sum of absolute values of every linear projection. For mixtures of product distributions, we construct such reduced domains incrementally over the coordinates, obtaining the first FPRAS with running time polynomial in both the dimension and the number of mixture components. We then extend the approach to smooth, structured-decomposable probabilistic circuits with a common structured architecture.
Read the full abstract

All authors Arnab Bhattacharyya, Graham Cormode, Yucheng Fu, Kuldeep S. Meel

Cryptography and Security

Echo: Learning-based Matching Decompilation using Trusted Back Translation

Jun Bi, Xiangxin Fang, Aarsh Chaube et al. (+3 more)

Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompilation addresses this problem by searching for source code whose recompiled assembly exactly matches the target, providing stronger evidence of correctness. However, exact matching remains challenging for optimized binaries under unknown compilation configurations. We present Echo, a matching decompilation system based on trusted back-translation. Our key insight is to use compilation not only for verification, but also as trusted feedback to guide iterative search. Echo first uses a domain-specific model to generate candidate programs and compilation configurations. It recompiles these candidates, measures assembly-level similarity, and synthesizes promising code-configuration pairs. Remaining mismatches are then progressively repaired using rule-based rewriting, neural refinement, and reasoning-based refinement. We evaluate Echo on function-level benchmarks and the Mirai malware binary. Compared with the strongest baseline, Echo produces 2.43x more exact matches on average and achieves the highest structural similarity to ground-truth source code. On Mirai, Echo matches 2.75x and 7.4x as many functions as GPT-5.6 and Codex, respectively.
Read the full abstract

All authors Jun Bi, Xiangxin Fang, Aarsh Chaube, José Wesley De Souza Magalhães, Rodrigo C. O. Rocha, Michael O'Boyle

Networking

Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study

Shenjia Ding, David Flynn, Paul Harvey et al. (+2 more)

Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely on entire topology representations, which are inherently monolithic and lack reusability under topological or traffic changes in the network. This paper introduces a composable NDT approach that decomposes networks into subgraphs represented by reusable unit twins that capture subgraph structure, configuration and traffic behaviours. A lightweight composer aggregates unit twin combinations to create NDTs that predict per-route end-to-end latency through an overall topology. Evaluation across controlled synthetic topologies and diverse traffic scenarios, real-world Topology Zoo topologies, and a public NDT challenge dataset demonstrates that the composable NDTs achieve high in-distribution accuracy while remaining stable under out-of-distribution scenarios. Comparison with monolithic full topology NDTs demonstrates that our composable approach achieves reusability, while achieving comparable or superior accuracy.
Read the full abstract

All authors Shenjia Ding, David Flynn, Paul Harvey, Takamichi Miyata, Sumiko Miyata

Distributed Computing

RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

Xiaochen Ma, Zimo Meng, Junzhu Liang et al. (+13 more)

Preparing high quality training data for foundation models requires scalable pipelines that transform heterogeneous documents and videos into structured records. Such pipelines expand each parent item into an ordered and input dependent sequence of children, whose counts may be long tailed. GPUs should batch children across parents while preserving parent relationships, child order, completion status, and result routing. Existing systems either hide parallelism behind coarse grained jobs or expose flat records that force applications to manage lineage and regrouping. We present RayOrch, a programming model and distributed execution engine that preserves parent child relations throughout execution. Programs declare ordered variable cardinality expansions and matching gathers. The compiler validates each pair, while the runtime records child membership, immediate parents, immutable ordinals, and terminal states. Per Call FIFO Ready Queues batch ready children across parents. Gathers reconstruct results from declared membership and ordinals rather than batch boundaries or completion order. Parents can advance as soon as all required children become terminal. Typed parent scoped failures suppress undispatched siblings of the failed parent while allowing unrelated parents to continue. On NVIDIA H20 GPUs, RayOrch achieves 15.14 times speedup when scaling MinerU from 4 to 64 GPUs and 7.82 times speedup when scaling a video pipeline from 8 to 64 GPUs. It reduces end to end time by 13.1 percent versus Ray Data and 29.0 percent versus Daft on MinerU, and by 16.0 percent versus Ray Data on Docling. Code available at https://github.com/OpenDCAI/RayOrch .
Read the full abstract

All authors Xiaochen Ma, Zimo Meng, Junzhu Liang, Youhe Jiang, Yue Cheng, Hao Liang, Bohan Zeng, Dengchun Li, Lu Ma, Zhengyang Zhao, Zhen Hao Wong, Runming He, Meiyi Qiang, Jiangtao Guan, Binhang Yuan, Wentao Zhang

Neural and Evolutionary Computing

A Metaheuristic Optimization Framework for Discrete Optimization under Strict Time Limits

Umut Çal{\i}ky{\i}lmaz, Nitin Nayak and Sven Groppe

Real-time applications often rely on optimization approaches that can find high-quality solutions to hard problems on the order of milliseconds. Metaheuristic optimization frameworks (MOFs) are useful tools for such tasks, as they provide large sets of general-purpose search mechanisms that can return solutions under different computational budgets. However, existing work largely overlooks the available computation time as an explicit dimension of analysis. In this work, we introduce STILO, a MOF specifically designed for optimization under strict time limits. STILO integrates fine-grained configuration spaces for ant colony optimization (ACO), genetic algorithm (GA), and simulated annealing (SA), combining existing and novel operators. We performed experiments using both synthetic and benchmark instances of various discrete optimization problems. The results indicate that the proposed discrete distance calculation mechanism for SA is useful for optimization under strict time limits. They also show that the relative effectiveness of the proposed problem-independent graph structures for ACO can vary across time limits, even for the same instance characteristics. More generally, the results demonstrate that the effectiveness of algorithm families and operators depends not only on the problem type, but also on the characteristics of the instance and the available computational budget.
Read the full abstract

Robotics

Toward 3D Printable Non-Planar Electroadhesive Structures for Active Anchoring

Mostafa A. Atalla, Carol R. Derla, Pep Canyelles Pericàs et al. (+1 more)

This paper investigates multi-material 3D printing as a method to fabricate non-planar structures with 3D-printed electrode patterns for electroadhesion. We printed flat electroadhesion pads as a planar benchmark and cylindrical pads as a non-planar demonstration, with conductive interdigitated electrodes 3D printed as part of the structure. Normal-force measurements showed voltage-controlled modulation in both geometries. At 3 kV, the flat pads generated approximately 0.11-0.13 N, while the cylindrical pads reached approximately 0.16 N at 5 N preload. These results demonstrate a step toward printed parts with built-in, electrically controlled adhesion and friction, beyond conventional planar electroadhesion pads.
Read the full abstract

All authors Mostafa A. Atalla, Carol R. Derla, Pep Canyelles Pericàs, Gijs Krijnen

Computation and Language

Tracing individual knowledge trajectories in a changing field: the case of general relativity and gravitation

Raphael Schlattmann and Malte Vogl

Historians have reconstructed the twentieth-century transformation of general relativity and gravitation (GRG) at the field level and through individual careers, but connecting these scales requires a way to compare researchers with the changing field over time. We develop such a comparison, setting a researcher's publications and references against GRG field literature from the same, earlier, and later two-year periods. Building on Own Vocabulary and Embedding Density Estimation from our earlier two-case study (arXiv:2501.00391), we extend the analysis to the fifty most-published authors in a NASA/ADS corpus of about 180,000 GRG records (1911 to 2000) and add two citation-based measures, Referenced Vocabulary and Citation Identity. The four measures compare an author's written language, cited literature, semantic neighbourhood, and cited-authority configuration with the surrounding field. The earlier cases suggested that closer field-vocabulary alignment accompanies a denser semantic neighbourhood. Across the fifty authors this holds only partially. Written and cited vocabularies tend to move together, usually resembling later GRG literature as the field turned towards astrophysical and cosmological research. Semantic neighbourhoods more often lie where the field's publications were concentrated in earlier periods, while co-citation patterns follow no single temporal direction, and the two citation measures frequently place the same researcher differently despite drawing on identical reference lists. Individual trajectories can thus combine vocabulary tied to later field states with older semantic or citation structures, and these divergent cases mark patterns for closer historical investigation. The approach transfers to other fields with defensible corpus boundaries and adequate coverage of texts, references, and disambiguated author identities.
Read the full abstract

Information Retrieval

SURF: Subtractive Updates for Recommender Forgetting

Filippo Betello, Antonio Purificato, Nicola Tonellotto et al. (+1 more)

The increasing demand for user privacy and compliance with regulations such as GDPR has made machine unlearning a fundamental requirement for modern recommender systems. However, Sequential Recommender Systems (SRS) pose unique challenges for unlearning due to their reliance on temporal interaction patterns. Existing approaches either require computationally prohibitive full retraining or fail to account for the sequential nature of user behavior. We propose SURF (Subtractive Updates for Recommender Forgetting), a lightweight framework for approximate machine unlearning in SRS. SURF operates in three stages: (i) identifying the neighborhood of the item to forget in the embedding space, (ii) training an auxiliary model on this compact local subset, and (iii) subtracting the auxiliary model's scores from the original model at inference time. Experiments against five baselines on 7 datasets show that SURF achieves unlearning effectiveness comparable to full retraining while substantially reducing computational cost, yielding up to a 32% improvement in NDCG@20 while requiring just 2% of the original retraining baseline time budget. We share our code at https://github.com/FilippoBetello/SURF.
Read the full abstract

All authors Filippo Betello, Antonio Purificato, Nicola Tonellotto, Fabrizio Silvestri

Computational Complexity

An Operator Approach to Register Programs for Catalytic Computing

Antoine Vinciguerra

In a seminal work, Buhrman et al.\ (STOC 2014) introduced catalytic computation and proved that uniform $TC^1$ circuits are computable in catalytic logspace, the class of problems solvable in space $s$ with an additional catalytic tape of size $c$, a tape whose initial content must be restored at the end of the computation. A central ingredient of their proof is the register program model. Namely, they constructed a uniform family of register programs that computes $x^n$ using $n$ registers and four accesses to $x$. Since then, determining the number of registers and input accesses required to compute a polynomial of a given degree has become a central question in the study of catalytic computation. On one hand, we prove that the four-access bound of Buhrman et al.\ is optimal: every passive-output register program computing a polynomial of degree greater than three requires at least four input accesses, independently of the number of registers. On the other hand, we show that their register bound is not optimal. For every $t\geq2$ and every field $K$ of characteristic $0$ or greater than $2t-1$, we construct a register program for $x^{2t-1}$ with four input accesses and $t$ registers. Our proofs rely on derivations and their exponential operators. This approach represents a register program as a series of exponential derivation operators, reducing register restoration to an operator identity. Finally, we use the uniform family of register programs to improve known trade-offs for catalytic streaming algorithms and register programs for matrix powering. The generalization of the lower-bound methods and the construction of the uniform family of register programs were developed with assistance from ChatGPT 5.6.
Read the full abstract

Computer Vision

RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection

Liyang Fan, Xinping Bi, Yitai Li et al. (+3 more)

Graphical User Interface (GUI) grounding is a fundamental perception task for multimodal agents, enabling them to interpret natural language instructions and interact with digital interfaces. Existing methods face a fundamental trade-off between accuracy and efficiency: direct full-image inference often fails to capture small or visually similar UI elements, while multi-crop strategies improve localization at the cost of multiple expensive Vision-Language Model (VLM) calls per query. To address this challenge, we propose RankGround, a two-stage framework that achieves accurate GUI grounding with a single VLM call per query. Central to our approach is GroundRanker, a lightweight multimodal reranker that identifies the most promising crop from a dense candidate set. Because no off-the-shelf ranking dataset is available, we construct ranking supervision data from existing grounding datasets. A strict containment criterion and boundary-aware positive augmentation improve alignment and spatial coverage in cluttered layouts. GroundRanker is then trained with a two-stage curriculum: a pointwise objective first learns coarse containment, and a listwise objective refines subtle semantic and spatial distinctions among visually similar crops. Experimental results show that RankGround consistently outperforms strong baselines while reducing computational cost. It achieves 1.4 times faster inference and improves localization accuracy by 5.5% on average over the second-best method across all backbones and screen scales, establishing a new state of the art in both efficiency and precision for GUI grounding.
Read the full abstract

All authors Liyang Fan, Xinping Bi, Yitai Li, Shuaimin Li, Hui Li, Min Yang

Information Theory · Cross-listed from math.PR

Zeros of the Spectrogram of Colored Noise

Luis Alberto Escudero, Günther Koliander and José Luis Romero

We study the expected number of zeros of the Short-Time Fourier Transform (STFT) with a Gaussian window for signals degraded by complex Gaussian colored noise. We provide an exact formula for this quantity and investigate its asymptotic behavior. From a computational perspective, we propose an algorithmic method to recover a smoothed power spectral density (PSD) directly from the spatial distribution of the transform's zeros. Our results formalize the commonly-held heuristic that detection algorithms based on spectrogram zeros, though designed for white noise, also perform adequately under moderately colored noise.
Read the full abstract

Computer Vision

Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging

Johannes Kaiser, Florian Braunmiller, Daniel Rückert et al. (+1 more)

AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (MoE) architectures currently fail to satisfy. Expert-based routing improves in-domain learning but may sacrifice cross-modal signals, which appear particularly important for rare (low-prevalence) pathologies in our experiments. To resolve this, we introduce Generalist-Specialist-MoE (GS-MoE), a two-branch (MoE) architecture that couples a cross-modal generalist model with distinct modality-specific specialists (experts) via domain-constrained feature fusion. On RadImageNet (1.35M images, 165 pathologies, three modalities), GS-MoE recovers detection of six low-prevalence pathologies on which every baseline scores F1 $=$ 0, with per-class gains up to +0.60 F1. It attains this while even slightly exceeding dense and specialist-only MoE aggregate baselines (MCC 0.770), while using ${\sim}53\%$ fewer active parameters at inference than the strongest investigated dense model.
Read the full abstract

All authors Johannes Kaiser, Florian Braunmiller, Daniel Rückert, Georgios Kaissis

Sound

Multi-Teacher Distillation for Cross-Domain Streaming Electrolaryngeal Speech Encoding

Benedikt Mayrhofer, Enrique Orozco Olivares, Franz Pernkopf et al. (+2 more)

Self-supervised learning (SSL) has improved speech representations, yet performance degrades in pathological domains such as electrolaryngeal (EL) speech, and the computational footprint of SSL models limits their applicability in real-time, on-device deployment. We propose a multi-teacher knowledge distillation framework to train a lightweight, streaming content encoder that generalizes across healthy (HE) and EL speech. Two teachers are distilled progressively: a frozen SSL model providing discrete phonetic cluster targets from HE speech, and an EL-fine-tuned speech recognition model supplying continuous bottleneck feature targets. Evaluated via downstream speech recognition, our approach reduces the EL word error rate to 21.2%, compared to 39.3% for the strongest zero-shot SSL baseline. Among causal convolutional, Transformer, Conformer, and Mamba-based student architectures, a Mel-Conformer achieves the best combination of EL accuracy and computational efficiency. The final encoder contains 21.9,M parameters and runs at a real-time factor of 0.30 under ONNX Runtime on a single CPU core.
Read the full abstract

All authors Benedikt Mayrhofer, Enrique Orozco Olivares, Franz Pernkopf, Philipp Aichinger, Martin Hagmüller

Robotics

WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning

Remo Steiner, Vikram Ramasamy, David Tingdahl et al. (+7 more)

Reinforcement learning allows robots to acquire complex skills, but producing policies for geometrically complex manipulation remains difficult. A promising approach is to learn on top of collision-avoidant controllers, such as geometric fabrics. However, these approaches have relied on static, hand-specified representations of the scene. Integrating active, online 3D perception into massively parallel RL training has so far been inaccessible. We introduce a GPU-accelerated method that reconstructs the scene as a collection of surfels across thousands of parallel simulation instances during active rollouts. This lets policies operate over sensor-derived, rather than hand-specified, geometry. On a suite of collision-dense manipulation tasks, our surfel fabrics enable policies to tackle geometrically complex scenes where primitive-based baselines fail, while maintaining sim-to-real transfer. Furthermore, policies learned with a scene-aware fabric are more robust to the introduction of novel geometry at test time, improving collision-free task completion under unseen obstacles from 35% to 61%. We release our reconstruction system, training code and test dataset to spur research in this direction.
Read the full abstract

All authors Remo Steiner, Vikram Ramasamy, David Tingdahl, Sam Mady, Karl Van Wyk, Nathan Ratliff, David Recasens, Soha Pouya, Tuur Stuyck, Alexander Millane

Machine Learning · Cross-listed from stat.ML

Rank and computation of the pathlifting Jacobian of a DAG ReLU network

Manon Verbockhaven

This paper provides a self-contained proof of the rank of the pathlifting Jacobian of a DAG ReLU network by performing an induction on the network's number of hidden nodes. In fact, the induction is elementary, and the key recipe is to consider the skeleton matrix of the network, a sparse matrix encoding the network paths, and transform the representation of one of its hidden neurons into an output node. The proof relies on intermediate propositions which link the pathlifting, its Jacobian, the network parameters, and its skeleton matrix, which, on top of permitting to conclude on the rank of the pathlifting Jacobian, also provide a way to compute it without backpropagation and whose computation cost is super efficient in practice compare to usual backpropagation. The paper is provided with a Python module that implements the different propositions of the paper for feed forward networks and is used to experimentally quantifies the computational gain of computing the pathlifting Jacobian with the proposed theory.
Read the full abstract

Computation and Language

HearInContext: A Benchmark for Implicit Context in Speech Recognition

Yifan Gao, Yao Tian and Hongbin Suo

Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin-English benchmark that pairs shared synthetic speech with assistant replies supporting different interpretations. The benchmark comprises 3,764 semantic test cases built around homophones. Implicit contexts exclude candidate words; explicit contexts name the target. No-context and unrelated-context controls measure the benefit of relevant history and sensitivity to irrelevant history. Context-capable models benefit from implicit cues but achieve higher target recall with explicit hints. Fine-tuning Qwen3-ASR-1.7B improves implicit-context target recall by 11.4 percentage points in both Mandarin and English, while absolute CER/WER changes on AISHELL-1 and LibriSpeech remain below 0.1 percentage points. Gains extend to explicit conditions excluded from fine-tuning and to Mandarin hotword recognition on real recordings. Code and data are available at https://github.com/OPPO-Mente-Lab/HearInContext
Read the full abstract

Systems and Control

GNN-Accelerated Mixed-Integer Dual MPC for Interactive Driving

Yidan Zhu, Shuhao Qi, Luyao Zhang et al. (+2 more)

In interactions with uncertain opponents, dual model predictive control (MPC) can improve performance through information-seeking actions that reduce uncertainty about opponents' behavior. Its recent applications to autonomous driving, however, are limited to scenarios involving a single opponent on a single lane. This paper presents a mixed-integer dual MPC for multiple reactive opponents on multi-lane roads, jointly optimizing integer-valued maneuver decisions (lane changes and safe-region selections), and continuous motion over a scenario tree that samples plausible interactions with the opponents. As interaction complexity increases, solving the resulting mixed-integer nonlinear program becomes increasingly expensive. To reduce this computational burden, a graph neural network (GNN) predicts the optimal maneuver decisions, and high-confidence predictions are fixed before the reduced problem is solved. Simulations show that active probing behavior emerges in complex interactive scenarios, and that GNN guidance fixes $76.3\%$ of the integer decisions and reduces the solve time by $2.5\times$ on average, with negligible degradation of optimality.
Read the full abstract

All authors Yidan Zhu, Shuhao Qi, Luyao Zhang, Sofie Haesaert, Jonas Mårtensson

Computation and Language

Voice of Reason: Reinforcement Learning for Spoken Math

Timothée Weisselberger, Edouard Graves and Alexandre Défossez

Speech language models enable richer spoken interactions between humans and machines than cascaded systems, allowing access to paralinguistic information and lower latency. However, their accuracy on mathematical reasoning benchmarks has lagged behind those of text models. Reinforcement learning (RL) with verifiable rewards has been instrumental in extending text models' capabilities for solving complex problems and limiting hallucinations. In this work, we explore applying RL to the GLM-4-Voice speech model (Zeng et al., 2024) to bridge the gap between textual and spoken mathematical problem solving. We first adapt the model to the domain using supervised fine-tuning on synthesized spoken question-answering data. We then show that, even without extra reasoning tokens, RL improves the accuracy on GSM8K beyond levels previously achieved for speech models only with supplementary reasoning traces. When combined with existing streaming reasoning techniques, we show further gains to 74.8% free-form accuracy. This establishes a new state-of-the-art for mathematical spoken abilities with speech-native models.
Read the full abstract

Artificial Intelligence

The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses

Lydia Manikonda, Mei Si, Sirajam Munira et al. (+2 more)

Generative artificial intelligence (GenAI) is changing how students learn, yet the roles of course context, cognitive reliance, evaluation literacy, and early reliance remain underexplored. Using survey responses from 118 students across 12 AI-related courses at our institution, we examined differences in GenAI use and perceived learning experiences. We identified four user clusters: high-use students reporting many benefits, light users reporting less reliance and fewer benefits, and two moderate-use groups reporting different levels of benefit. We also found significant differences between free- and premium-version users, single- and multiple-tool users, and students experiencing different instructor policies. In multivariable regression models, academic benefit was associated with early reliance and academic task support; positive impact was associated with cognitive reliance, academic task support, confidence in GenAI reliability, and instructor policy; and negative impact was associated with early reliance and attitudinal change. The association between early reliance and negative impact became stronger as evaluation literacy increased. Finally, perceptions of GenAI-enhanced learning appear to reflect cognitive, performance, and self-efficacy benefits, while concerns about stress and diminished critical thinking are associated with lower perceived learning benefits. These findings suggest that institutions need better policies to address such inequities so that institutions can enable students to benefit from increasingly capable AI systems.
Read the full abstract

All authors Lydia Manikonda, Mei Si, Sirajam Munira, Oshani Seneviratne, Kristin Bennett

Hardware Architecture

HBFlex: A Flexible Memory System for Bridging Fine-Grained LLM States and Coarse-Grained HBF Parallel Execution

Shuzhang Zhong, Weikai Xu, Yifan Zhou et al. (+7 more)

Large language models (LLMs) require increasing memory capacity to accommodate growing model weights and KV caches. High-Bandwidth Flash (HBF) offers high memory density and aggregate read bandwidth through massive plane-level parallelism, making it an attractive option for LLM serving. However, serving LLMs entirely from HBF introduces three challenges: fine-grained KV reads create placement and access imbalance, incremental writes interfere with foreground reads, and mixed KV lifetimes amplify garbage collection. Hybrid HBM/HBF designs retain HBM to support dynamic KV management, but this allocation reduces the HBF resources available under a fixed packaging budget, limiting aggregate HBF bandwidth. We present HBFlex, a full-HBF memory system with coordinated optimizations for KV reads, writes, and reclamation. HBFlex balances KV placement and attention accesses to improve plane utilization. It aggregates incremental updates and schedules writeback within sufficiently long compute windows to reduce write–read interference. It also combines lifetime-guided block packing with deferred reclamation to reduce valid-page migration. We evaluate HBFlex through trace-driven simulation across different configurations. HBFlex achieves average throughput speedups of up to 1.58$\times$ over FlashAccel and 3.30$\times$ over H3, benefiting from higher HBF bandwidth and more efficient management of dynamic KV-cache reads, writes, and erases.
Read the full abstract

All authors Shuzhang Zhong, Weikai Xu, Yifan Zhou, Tongbin Zhao, Tenghao Zhao, Yifei Kang, Cunyin Chang, Shu Li, Guangyu Sun, Meng Li

Cryptography and Security

CaMeLoT: CaMeL orchestrated with Temporal logic for static verification and liveness

Elia Nikolaou, Magnus Wiik Eckhoff, Robert Flood et al. (+3 more)

LLM-based agents generate and execute multi-step plans that invoke external tools which can access private data or execute commands. In this setting, security is a property of the entire execution that a plan creates, not just any single step. The plan itself is a critical artefact that captures the tool calls, control flow, and data dependencies. We present CaMeLoT, a complement to CaMeL, an existing defence against prompt injection in tool-using LLM agents. CaMeLoT extends CaMeL by adding a static verification layer that checks an agent's plan before any tool is invoked. CaMeLoT translates a generated plan into a finite-state transition system, labels it with tool calls, provenance and taint information, and checks it against temporal policies expressed in CTL using the nuXmv model checker. Because verification happens before execution, unsafe plans are rejected without using LLM calls or tool calls, saving tokens that runtime could have cost, as well as the need to unwind changes or teardown temporary sandboxes. When a verification fails, the model checker returns a counterexample to give feedback to the agent to repair the plan. We evaluate CaMeLoT on policies derived from the AgentDojo benchmark, SOC workflows, and prompt-extraction experiments, showing that it verifies a broad class of temporal properties before execution while preserving CaMeL's runtime-checkable coverage.
Read the full abstract

All authors Elia Nikolaou, Magnus Wiik Eckhoff, Robert Flood, Gudmund Grov, Vasileios Mavroeidis, David Aspinall

Sound

Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification

Seungmin Seo, Oleg Aulov, P. Jonathon Phillips et al. (+2 more)

Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce privacy to a single dimension - biometric verification performance - typically measured by Equal Error Rate (EER). This narrow focus ignores critical leakage channels, such as soft biometric inference, embedding-level re-identification, and structural template similarity, which threaten the unlinkability and irreversibility of biometric references. We propose a holistic evaluation framework across five complementary metrics: (i) EER, (ii) soft biometric leakage score , (iii) cumulative match characteristic re-identification analysis, (iv) canonical correlation analysis and Procrustes embedding alignment, and (v) intelligibility via word error rate and semantic similarity. Evaluating five SDID systems from the IARPA ARTS program, we demonstrate that these metrics capture independent dimensions of information leakage. Our results indicate that reliance on a single metric can misrepresent the privacy properties of an SDID system.
Read the full abstract

All authors Seungmin Seo, Oleg Aulov, P. Jonathon Phillips, Kevin Mangold, Jonathan Eskin

Computation and Language

Selection Is Retrieval, Abstention Is Not: On-Device Tool Routing over 70 Korean-English Actions

Janghoon Lee

An AI assistant that calls tools makes two decisions on every request: which tool to invoke, and whether any available tool applies. In the usual design a single language model makes both, by emitting a call or by declining to emit one. On a device that has to answer without a server, the language model is what makes that design expensive, dominating both the latency and the memory of the router. The common alternative is to remove the model completely and rank the catalog of local actions with a retriever instead. That substitution is not symmetric across the two decisions. A retriever returns its highest-scoring candidate for every input and cannot signal that the catalog holds no valid action. Our earlier study found that constraining a decoder to a tool grammar repairs malformed output without improving the choice. What the substitution costs in each decision has not been measured. We evaluate the two decisions separately over 600 Korean and English requests and a catalog of 70 local actions. The router may also ask for a missing slot, reply, or delegate. Half the in-catalog requests reuse catalog vocabulary and half paraphrase it, separating lexical overlap from the action requested. Character 3-gram BM25 selects 162 of 164 lexically matched requests and 85 of 166 paraphrases. Restricting the candidate set to seven raises the paraphrase figure to a mean of 0.825 over five trials. No classifier over its score features separates in-catalog from out-of-catalog above 0.697 area under the curve, where the frozen encoder multilingual-e5-base reaches 0.806. Using that encoder for abstention alone keeps 376 of the requests local and misroutes 9 of the 150 needing delegation. Abstention, not selection, is where a neural component is required. A neural ranker improves every quality metric and is rejected on latency and memory rather than accuracy.
Read the full abstract

Robotics

M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation

Xingpeng Sun, Zherong Pan, Kai Cheng et al. (+3 more)

Multi-Modal Motion Planning (M$^3$P) requires joint reasoning over continuous motions and discrete mode transitions, making it difficult to solve efficiently. For instance, a bipedal robot may walk to a target location and then use its arms to grasp an object. This scenario captures both mode transitions and continuous dynamics, yielding feasible paths that neither purely discrete nor continuous planners can handle. While Mixed-Integer Programming (MIP) offers a principled framework, constructing tractable formulations for non-convex problems is typically manual and domain-specific, especially in the approximate, discretization-based MIP regime needed for non-convex robotic tasks. We propose M$^3$P-R1, a reinforcement learning method that fine-tunes large language models (LLMs) to decompose M$^3$P tasks into MIP variables, constraints, and objectives. Instead of directly outputting answers, which are often prone to hallucination, the model generates executable Python code using MIP optimization libraries and constraint interfaces. This enables solver-backed execution for robust and verifiable solutions. Trained with an outcome-driven reward against the solver, M$^3$P-R1 learns to compose modality-level discretization primitives and synthesize cross-modal coupling constraints, producing executable MIP programs for complex M$^3$P tasks.
Read the full abstract

All authors Xingpeng Sun, Zherong Pan, Kai Cheng, Xindi Tang, Syed Talha Bukhari, Aniket Bera

Computer Vision

Video-Based Markerless Motion Capture for Clinical and Rehabilitation Biomechanics: A PRISMA-ScR Scoping Review of Validated Architectures, Clinical Readiness, and Emerging Methods

Florian Delaplace, Elodie Piche, Frédéric Chorin et al. (+1 more)

Background.. Video-based markerless motion capture promises movement analysis without the cost, space and skin-marker constraints of optoelectronic systems, with particular potential for clinical and rehabilitation settings. Whether validated pipelines yet deliver clinically acceptable biomechanics, and how they relate to the underlying computer-vision research, remains unclear. Methods. We conducted a scoping review following the PRISMA extension for Scoping Reviews, with a registered protocol and searches of PubMed, Scopus and IEEE Xplore (January 2015 to February 2026; the computer-vision scan was updated to July 2026). A dual-tier design paired a primary corpus of validated biomechanical studies with a complementary, curated and deliberately non-exhaustive corpus of emerging computer-vision work, used qualitatively. We charted study characteristics, pipeline architecture, validation methods and joint-angle accuracy. Results. We included 117 studies, most published from 2024 onward and conducted on healthy adults walking in a laboratory. Pipelines formed five architectural families across monocular and multi-camera modalities; most reported raw joint angles without biomechanical refinement. Sagittal lower-limb agreement clustered around 5 to 6{\textdegree}, generally short of clinical acceptability, while out-of-plane kinematics, kinetics, and pathological or older populations were rarely validated. Emerging computer-vision building blocks (foundation-model mesh recovery, differentiable inverse kinematics, video-based kinetics) were almost absent from validated studies. Conclusions. Video-based markerless capture is not yet interchangeable with marker-based systems for clinical joint kinematics, and it remains barely validated where rehabilitation needs it most: older and pathological populations, out-of-plane kinematics, and kinetics. Mapping this evidence gap onto emerging computer-vision advances, we propose hypothesis-generating design guidelines, not a validated method, to steer the next generation of pipelines toward accessible, clinically meaningful movement analysis.
Read the full abstract

All authors Florian Delaplace, Elodie Piche, Frédéric Chorin, Raphael Zory