Peer Revenue Impact factor: volatile

Papers

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

Computer Science

cs Watch Computer Science

Sunday 11 October

Robotics

SIGN-MAPPO: State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X

Zide Fan, Jiahui Yuan, Kaixin Zhang et al. (+3 more)

Cooperative driving at mixed-traffic unsignalized intersections is challenged by imperfect vehicle-to-everything (V2X) communication, human-driven vehicle (HV) intentions that cannot be directly communicated, and the potential incompatibility of independently generated crossing decisions. This paper proposes State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X (SIGN-MAPPO) to address these challenges through three coordinated mechanisms. Each decision-eligible connected and automated vehicle (CAV) first reconstructs a receiver-specific traffic graph from its ego state and the peer-state records available to it, from which a shared graph-attention policy generates a raw Stop/Go intention augmented with predicted HV-intent features. CAV intentions are then exchanged through timestamped vehicle-to-vehicle (V2V) messages, and a local conflict-aware arbitration layer converts each CAV's intention into a safe executable action despite potentially inconsistent peer information. In the principal Simulation of Urban MObility (SUMO) evaluation, SIGN-MAPPO achieves a 97.53% completion rate, a 0.10% collision rate, and a mean intersection traversal time of 35.28 s. Ablation studies further confirm the complementary contributions of HV-intent prediction and CAV-intent exchange to this performance. The trained policy also remains robust under the evaluated communication-delay and packet-loss ranges, and cross-scenario tests show complete traffic clearance across the tested settings, though safety margins narrow under compound unpredictable HV behavior.
Read the full abstract

All authors Zide Fan, Jiahui Yuan, Kaixin Zhang, Junhao Fan, Xiaohe Li, Yiru Wang

Artificial Intelligence

Self-Representation Alignment in Diffusion Models for Video Background Music Generation

Jincheng Zhang, György Fazekas and Charalampos Saitis

Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned in the diffusion models' denoising process are insufficiently meaningful, which can hinder the generation performance. To address this, we propose a novel diffusion U-Net architecture enhanced by explicitly aligning the weaker representation from the earlier layer conditioned on higher noise with the better representation from the later layer conditioned on lower noise during training, which we use for the challenging multimodal task of video background music generation. Our diffusion U-Net Self-Representation Alignment (U-SRA) employs an alignment loss to effectively guide our diffusion model to learn good internal representations, thereby enabling it to produce higher-quality symbolic music conditioned on video features. We employ a cross-attention mechanism to synchronize music with video segments. Experiments on a benchmark video-music dataset demonstrate that the proposed U-SRA approach for video background music generation surpasses the state-of-the-art across key evaluation metrics, including video-music alignment and overall music quality.
Read the full abstract

Computation and Language

The Fragility and Dynamics of LLM Pruning-Recovery Steps

Luis Frentzen Salim, Komang Rinartha, Chia-Chun Wu et al. (+3 more)

Structural pruning followed by a recovery stage is the standard recipe for compressing large language models (LLMs), yet the two stages are typically designed and tuned in isolation. In this work, we study how their interaction shapes the compressed model, sweeping ordering, the data that drives each stage, and the alignment of their training objectives. We find that instruction-following is the first capability to collapse under pruning, well before knowledge, reasoning, or core language modeling, and that much of the pruning in-domain loss is likely not knowledge loss but a domain-agnostic failure to respond coherently to the prompt. We find in our setting that in-domain data is the strongest pruning signal, whereas instruction-style data recovers the most. Stage order matters little, but only marginally. We further analyze how the importance ranking drifts before and after pruning. Together these results give practitioners a concrete recipe for composing pruning and recovery.
Read the full abstract

All authors Luis Frentzen Salim, Komang Rinartha, Chia-Chun Wu, Tran Van Nhiem, Lun-Wei Ku, Yung-Hui Li

Graphics

Walk-on-Ambient-Patch: Solver-Adapted Isometric Embeddings for Projected Walk on Spheres

Yunfeng Liao and Xiucheng Li

Projected Walk on Spheres (PWoS) solves surface PDEs through ambient sampling and closest-point projection, but tightly folded embeddings can force short steps or ambiguous projections despite simple intrinsic geometry. We introduce Walk-on-Ambient-Patch (WoAP), which treats the embedding as a solver variable. Edge-isometry constraints and tangent-point repulsion separate intrinsically distant regions, optionally in higher codimension; patch states track residual projection branches without introducing PDE boundaries. We analyze the resulting geometry–sampling tradeoff: additional dimensions provide separation freedom but reduce uniform tangent progress, while strong tangent-biased proposals incur large importance-weight moments. Folded-surface experiments demonstrate reduced projection conflicts, a separate hard-constraint pilot verifies metric preservation, and an internal fixed-RMSE comparison favors higher dimensions at stricter accuracy targets. Together, these results motivate choosing the embedding and projection state jointly with the stochastic solver.
Read the full abstract

Robotics

Look Before You Move: Agent-Interface-Aligned Supervision for Open-World Mobile Manipulation

Ronghe Qiu, Teli Ma, Jiaming Zhou et al. (+4 more)

Open-world mobile manipulation requires a robot to find an object, approach it, and move it to a target receptacle from a language instruction. Training vision-language model (VLM) agents for these tasks requires demonstrations of both action selection and active vision. Existing pipelines often convert planned trajectories into high-level action labels, but shortest-path progress provides limited supervision for deciding where to look. We introduce Agent-Interface Data Alignment (AIDA), a data collection pipeline in which a teacher directly selects and executes actions through the deployed agent's skill interface. For mobile manipulation, we design teachers that maintain target visibility, recover lost targets, and approach for picking or placing. We add template-based spatial reasoning supervision and use a shared harness to organize observations, history, and outputs during training and inference. The resulting agent, AIDA-OWMM, achieves 71.76% full-task success on 170 held-out OWMM episodes. Teacher sensitivity analysis shows that active-vision demonstrations improve student success. The simulation-trained agent achieves 38% end-to-end success on a real mobile robot without additional training. Applying AIDA to a navigation subset of EmbodiedBench further demonstrates the pipeline's utility for navigation tasks.
Read the full abstract

All authors Ronghe Qiu, Teli Ma, Jiaming Zhou, Zeying Gong, Yiting He, Qiang Huang, Junwei Liang

Machine Learning · Cross-listed from stat.ML

Latent-Space Importance Weighting under Covariate Shift

Yuling Jiao, Lican Kang, Yang Xiang et al. (+2 more)

In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning. A key feature of our approach is the use of a lower-dimensional latent space for modeling, in contrast to conventional methods that operate directly in the high-dimensional ambient space. Our method estimates the density ratio of learned latent features for downstream weighted prediction. We establish explicit target-domain excess-risk rates with independent data folds for strictly sufficient learned representations with regular learned-space prediction scores and density ratios. We give dimension comparisons under stated smoothness conditions and a variance comparison for true weights and a fixed predictor. General finite-sample inequalities retain representation-quality errors. Experiments on simulated and real-world datasets demonstrate gains from combining learned representations and latent weighting, and reveal sensitivity to initialization and domain choice.
Read the full abstract

All authors Yuling Jiao, Lican Kang, Yang Xiang, Jerry Zhijian Yang, Fusheng Zhou

Machine Learning

Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem

Rasul Khanbayov and Hasan Kurban

Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can be. We observe that almost every deployed truncation rule keeps a prefix of the probability-sorted vocabulary, so any two such rules are nested at every decoding step. Nesting yields a closed-form per-step distance and a coupling under which both samplers emit identical text until they first disagree. Accumulated over a generation, this gives a separation certificate that bounds the difference between two samplers on any bounded outcome, is computable from logs a comparison already produces, and equals their sequence-level total variation distance exactly when neither rule ever overtakes the other. Two consequences follow without measurement: exactness is fragile, and certifying a small difference requires the two retained masses to agree to very high precision at every step. On six open-weight models over four math and science benchmarks, the certificate for every hyperparameter grid we tested is at least 0.998, so a bound alone rarely settles a comparison, although two members of one family can be far closer. What remains useful is the coupling, which gives an unbiased paired estimator that cuts variance $1.2$-$3.8\times$ against prompt-level pairing. Read against benchmark sizes at the default pair's variance and our point estimate of its between-prompt component, resolving a one-point difference needs 8 to 32 samples per prompt on GSM8K, MATH-500 and GPQA-Diamond and about 210 on AIME 2025; at that component's upper confidence bound GPQA-Diamond needs more than 32 and AIME 2025 cannot be resolved at any sample count. Choosing a truncation sampler is a measurement problem at least as much as a design one. The code is available at https://github.com/KurbanIntelligenceLab/truncation-samplers.
Read the full abstract

Software Engineering

Reviewing Beyond the Change: Repository Size and Existing Code Across Agent and Human Pull Requests

Sabry E. Farrag

Reviewers sometimes name existing repository items outside the change under review. We ask whether such references are more common in larger repositories, and whether the pattern differs between agent-authored and human-authored pull requests. An instrument resolves names in inline review comments against the base-commit repository; size-matched negative controls estimate chance matches. Among 92,042 comments on agent pull requests in 2,034 GitHub repositories, 6.5 per cent name an existing item outside the change. An internally pre-specified log-linear model finds an odds ratio of 1.35 per tenfold increase in code files (interval 1.15 to 1.59), and size-matched negative controls indicate that chance matching does not account for the rise. Exploratory analyses suggest that the association is concentrated from small to mid-sized repositories and is imprecise among large ones. Human pull requests in 1,845 of these repositories show a similar association. A pre-specified comparison finds a small agent excess just within the bound set as negligible, but the evidence does not establish a robust agent-specific difference. The instrument misses many references, so reported shares likely understate prevalence, and the validation cannot estimate how recall changes with repository size.
Read the full abstract

Networking

The Evolution of In-Premise Networks In the Era of Immersive Services: From Copper to Fiber-to-The Room [Invited Tutorial]

Elaine Wong and Sourav Mondal

The telecommunications industry is shifting toward an experience-driven era defined by immersive applications that impose stringent network demands. While passive optical network (PON)-based Fiber-To-The-Home (FTTH) architectures have historically delivered high-capacity broadband, a growing performance gap between access and indoor networks necessitates driving fiber deeper into premises. Complementing existing copper and WiFi technologies, Fiber-to-the-Room (FTTR) is emerging as a critical enabler. This article examines the drivers of this architectural shift, specifically focusing on collaborative extended reality (XR). We analyze the multi-modal traffic characteristics and Quality-of-Experience (QoE) requirements of XR, alongside the resulting network performance implications. To address these demands, we propose a novel resource allocation framework integrating coarse-grained traffic forecasting with intelligent in-premise roaming. This framework facilitates the flexible deployment of artificial intelligence models tailored to the computational capabilities of the FTTH, FTTR, and WiFi segments. Numerical evaluations of a representative multi-tier network demonstrate that long-horizon, multi-step-ahead traffic forecasts significantly reduce inference frequency. This approach enables coordinated resource allocation and network-orchestrated seamless mobility across rooms, effectively satisfying collaborative XR QoE requirements. Finally, we highlight strategies to amortize FTTR capital expenditure by extending the optical infrastructure's role beyond basic connectivity. By supporting diverse services over a unified physical layer, FTTR enhances infrastructure utilization, unlocks novel revenue streams, and maximizes the value of in-premise fiber deployments.
Read the full abstract

Computer Vision

Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning

Fan Yang, Lifeng Chen, Yipu Wang et al. (+14 more)

Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchmarks. However, these capabilities degrade under complex real-world scenes. We identify that chain-of-thought reasoning remains largely confined to the linguistic space, rarely anchoring each step in visual evidence. The main cause is the absence of such data during training. In this work, we introduce a training data augmentation pipeline, Visual Augmentation Primitives (VAP), which leverages state-of-the-art vision generative models to synthesize diverse photorealistic training samples and corresponding reasoning text. VAP introduces some basic operators and applies them to a seed image and gets a variant. It also constructs coherent multimodal reasoning chains throughout the generation process. Such training data force models to perceive visual content and perform logical reasoning according to them at every step. We further introduce multimodal chain-of-thought rubric-based reinforcement learning to enhance this. It rewards not only text reasoning but also visual reasoning by scoring intermediate reasoning steps for logical validity, completeness, and consistency. Moreover, we construct the UNREAL benchmark to systematically evaluate visual reasoning on hyperrealistic scenes across controllable difficulty levels. Experiments show that a 4B model built on this framework surpasses 8B baselines, with performance improving consistently as the model scales to 32B, validating the scaling law for visual reasoning.
Read the full abstract

All authors Fan Yang, Lifeng Chen, Yipu Wang, Han Wang, Feilong Chen, Yidong Ma, Zhiyang Chen, Chaoyang Zhao, Lingxiang Wu, Hanqi Jiang, Yibo Chen, Xu Tang, Yao Hu, Ming Tang, Xiaojie Jin, Xiaolong Zheng, Jinqiao Wang

Machine Learning

UNISON: A Unified Framework for Learning from Scored Bags

Ofek Kirshenboim, Or Shkuri, Shani Finkelshtein et al. (+1 more)

We introduce UNISON, a unified framework that bridges multiple instance learning and recommendation systems by treating both as instances of learning from scored bag collections of (item, score) pairs. Unlike traditional approaches that address bag-level classification and personalized recommendation as separate problems, UNISON decomposes learning into three interconnected stages: (1) learning universal item representations, (2) modeling bag-specific preference patterns through lightweight personalized parameters, and (3) inferring bag-level characteristics from learned preferences. We justify the architectural choice of linear bag-specific scoring through a first-order analysis: when item embeddings are sufficiently smooth in the score, a linear function approximates the score up to a Taylor remainder controlled by the curvature of the underlying preference function. For cold-start scenarios, we show that the cold-bag fitting problem reduces to ridge-less linear regression with a closed-form solution, and provide convergence guarantees for the iterative variant. Empirically, UNISON matches or outperforms state-of-the-art approaches across diverse domains: entertainment (books, movies), immunology (T cell receptor (TCR) based classification), and microbiome, offering superior computational efficiency and interpretability. A controlled synthetic experiment further confirms that the bag-specific parameters ($w_j, b_j$) recover the latent factors that drive item scores even when the projection $\phi$ has no access to the original scoring mechanism (AUC > 0.998). UNISON is available at https://github.com/louzounlab/UNISON.
Read the full abstract

All authors Ofek Kirshenboim, Or Shkuri, Shani Finkelshtein, Yoram Louzoun

Robotics

Anticipatory Textile MMG-Strain Sensing for Confirm-Then-Assist Soft Knee Exosuits

Zheng Ma, Xiao Jin and Zhenhua Yu

Soft wearable robots must commit to assistance around movement onset, when the available signals are ambiguous. Surface electromyography (sEMG) detects neuromuscular drive early but degrades under sweat and electrode shift, and kinematic sensors respond only once the limb moves. This letter presents a knitted textile interface that co-samples a three-channel mechanomyography (MMG) array and an anterior strain sensor on a single synchronous 500 Hz clock. Across five participants, MMG activation preceded strain-detected knee motion during sit-to-stand by per-channel medians of 322-344 ms. Sampled on the same clock, the sign of the strain slope resolved movement direction on 649 of 650 completed transitions with no training or per-participant calibration, raising four-class balanced accuracy from 90.3% to 95.6%. The fused signals drove a two-stage confirm-then-assist policy for a soft pneumatic knee. Across 240 trials in four participants, the onboard controller entered the assist state on 78 of 80 sit-to-stand trials and on none of the 80 isometric co-contractions. It also entered the assist state on 27 of 80 stand-to-sit trials and left it at the hold timeout, motivating an antagonistic flexor gauge to resolve this direction at onset. Co-sampling muscle acoustics with textile strain on one clock lets the inflation command be issued around movement onset.
Read the full abstract

Computer Vision

A Plausible Future Is Not a Causal Future: Can Video Models Generate How the World Unfolds?

Jialiang Li, Zhengning Xu, Zongyang Ma et al. (+1 more)

Large-scale video generation models are increasingly viewed as a promising path toward world models, yet their ability to capture causally coherent physical dynamics remains poorly understood. Existing evaluations largely emphasize visual quality, prompt adherence, or broad physical plausibility, leaving open whether a model can faithfully realize a complete causal cascade, in which an initiating event propagates through causally dependent interactions to a terminal outcome. We introduce CausalCascade, a simulator-grounded benchmark centered on 50 event-rich Blender scenes with structured event graphs, graph-grounded diagnostic VQA, three levels of future-event specification, and 2,832 controlled counterfactual variants, and use it to evaluate nine image-to-video models with complementary motion-, event-, and counterfactual-level diagnostics. Across the evaluated models, generated motion is more reliably localized spatially than realized with correct spatiotemporal evolution, while richer future-event specification improves event recovery but leaves physical realization limited. Counterfactual evaluation further reveals weak selective responsiveness to physical interventions, while most audited failures are foundational, arising at scene consistency or event occurrence. Together, these results position causal cascade generation as a process-level test of world modeling and highlight the need to jointly recover the intended future, faithfully realize its physical evolution, selectively respond to physical interventions, and maintain a coherent physical world over time. Code and dataset are available at https://github.com/SJTU-DeepDeltaLab/CausalCascade .
Read the full abstract

All authors Jialiang Li, Zhengning Xu, Zongyang Ma, Shaobo Cui

Robotics

Stereo-Planner: Learning Stereo-to-Trajectory Planning for Zero-Shot Sim-to-Real Quadrotor Navigation

Hongming Shen, Junjie Lu, Xun Chen et al. (+4 more)

Existing navigation systems commonly rely on dedicated depth sensors or explicit depth reconstruction, while learning to generate trajectories directly from RGB images remains challenging due to the sim-to-real domain gap. In this work, we propose Stereo-Planner, an end-to-end vision-to-trajectory framework that enables zero-shot sim-to-real planning from stereo RGB observations. The key idea is to formulate trajectory generation as state- and scale-conditioned querying of latent stereo geometry. A Scene Representor incorporates a pretrained vision grounding foundation model to extract geometric cues shared across simulated and real-world environments, supporting generalization across visual domains. A lightweight Trajectory Decoder then translates these representations into trajectories through interleaved attention, separating trajectory-state interaction from scene-feature retrieval and incorporating the stereo baseline as a metric-scale cue. With these designs, Stereo-Planner is trained entirely on simulated data by minimizing differentiable trajectory costs and deployed directly in real-world environments without fine-tuning. Benchmark results demonstrate strong cross-scene generalization, with a 95% success rate in simulation environments at a commanded speed of 8 m/s, and competitive performance against depth-based planners using only stereo RGB observations for scene perception. Furthermore, deployment on a compact quadrotor equipped with an NVIDIA Orin NX enables autonomous flight at speeds of up to 7 m/s, with a mean onboard vision-to-action inference time of 24.27 ms. The software, simulation environments, and hardware designs will be open-sourced at https://github.com/Stereo-Planner/Stereo-Planner.
Read the full abstract

All authors Hongming Shen, Junjie Lu, Xun Chen, Wei Wang, Xinhang Xu, Bailing Tian, Lihua Xie

Robotics

Analytic Robot Self-Model: Learning Screw-Axis Kinematics for Rendering and Model-Based Control

Chen Xu and Ning Tan

Visual self-modelling lets robots learn body models from observations, but such models usually encode kinematics implicitly rather than exposing metric joint parameters for computation and control. Moreover, a good fit to images does not by itself establish accurate kinematics. Here we present an explicit analytic robot self-model that requires neither deformation networks nor URDF/CAD templates. Multi-view images and joint readings establish Gaussian appearance and provide motion evidence for rigid link assignments, whereas sparse end-effector poses independently identify metric screw axes. The resulting closed-form forward kinematics and analytic Jacobian can be evaluated beyond the fitting ranges. We validate the model on a simulated seven-axis arm, a simulated twelve-joint quadruped and a real six-axis arm. In simulation, it achieves millimetre-level reaching and pick-and-place, as well as closed-loop quadruped walking. On the real arm, it renders held-out configurations, predicts end-effector positions with a median error of 6.4 mm, compared with 11.7 mm for a calibrated nominal model, and supports reaching with external marker feedback. A controlled comparison shows that image fit alone is not enough: two Panda models differing only in their joint axes are 0.54 dB apart in PSNR, yet their end-effector prediction errors differ 13.7-fold.
Read the full abstract

Logic in Computer Science

Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors

Yeonseok Lee

Vision-Language-Action (VLA) models commonly generate robot actions token by token through Large Language Model (LLM) decoders, causing inference latency to grow with action sequence length and limiting closed-loop control frequency. We present Goal-Conditioned Vision-Predictor-Action (VPA), which replaces autoregressive decoders with a lightweight latent control loop. A shared vision encoder and a frozen text encoder embed observations, goal images, and instructions; a neuro-symbolic selector chooses a discrete skill; a Joint-Embedding Predictive Architecture (JEPA) predictor forecasts the next latent state; and a flow-matching solver generates an entire action chunk in a few integration steps, so that sequential network evaluations per decision step do not depend on the action horizon. We analyze inference complexity, regularization against representation collapse, and conditions under which latent sub-goal thresholding limits error accumulation across task phases. As an initial proof of concept, we evaluated VPA on the LIBERO-10 suite. The trainable model has under 20M parameters (checkpoint under 75 MB, excluding a frozen 63.4M-parameter CLIP text encoder); a decision step of a single-camera reference configuration takes 10-14 ms on an Apple M4; and trained only on LIBERO-10 demonstrations in under three hours on a single GPU, a two-camera policy succeeded in 40.0% of 200 evaluation episodes. These preliminary results from a single training run suggest the approach is workable. Code and weights are available at https://github.com/ylee-sling/Vision-Predictor-Action and https://huggingface.co/ylee-sling/vpa-libero10, and archived at https://doi.org/10.5281/zenodo.22960920.
Read the full abstract

Computer Vision

ELECT: Settling Identity Before Rendering for Scalable Story Visualization

Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana et al. (+9 more)

Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain consistency by conditioning each frame on other frames of the same story, coupling generation time, VRAM, or both to story length. We introduce ELECT, which instead settles cross-frame identity before final rendering through a language-guided scene-entity mapping and stationary anchors elected from the model's own drafts. This makes the per-frame cost of the final rendering pass independent of story length. Joint attention exceeds 96 GB of VRAM at 32 scenes, whereas ELECT remains at 8.3 s per frame and under 20 GB VRAM from 10 to 1000 scenes. On the Story50 long-story benchmark, ELECT reaches 0.833 average Character Consistency Similarity (aCCS), compared with 0.826 for ten-round refinement, at one seventh of its generation cost, with lower text alignment (0.327 vs. 0.340). At 1000 scenes, to our knowledge, the first evaluation of training-free story visualization at this length, ELECT exceeds ten-round refinement by 0.017 aCCS and the nearest flat-cost baseline by 0.091, while also surpassing refinement in text alignment at one twenty-fourth of its generation time. These results show that long-horizon consistency need not require increasingly expensive inter-frame conditioning as stories grow.
Read the full abstract

All authors Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Abir Chakraborty Partha, Md. Ahasanul Alam, Redwan Ahmed Rizvee, Md. Fahim Arefin, Md Mahmudur Rahman, Md. Tanvir Alam, Md Mosaddek Khan

Computational Complexity

Unconditional Separation between LL and CLL

Shubham Bhardwaj

Catalytic computation involves the study of Turing machines that are provided an additional catalytic tape (with arbitrary content) that the machine may use while ensuring that the tape contents are restored at the end of the computation. Although it is known that catalytic log-space machines are at least as powerful as non-deterministic log-space (and more), we do not have unconditional asymptotic separations. In this work, we prove an unconditional separation between a deterministic space complexity class and its catalytic counterpart. More precisely, at the doubly logarithmic scale, we show that catalytic Turing machines can provably compute more languages than standard deterministic doubly-logarithmic space machines. The separation is witnessed by the unary language $\mathrm{POW2} = \{1^n : n \text{ is a power of two}\}$. We construct a catalytic Turing machine that uses $O(\log \log n)$ bits of space and $O(\log n)$ bits of catalytic tape to decide $\mathrm{POW2}$, whereas any standard deterministic Turing machine requires $\Omega(\log n)$ space to decide it.
Read the full abstract

Information Theory

Rate-Distortion Theory of Gaussian Mixtures via Posterior Label Sampling

Weichen Wang and Deniz Gündüz

We study the mean-squared error (MSE) rate-distortion function (RDF) of finite Gaussian mixture models (GMMs) in $\mathbb{R}^d$, for which neither the RDF nor an optimal test channel is known in closed form. It can be sandwiched between the genie-aided conditional RDF $R_{\mathbf{X} | T}(D)$, which can be characterized in closed-form for a GMM, and $R_{\mathbf{X} | T}(D)+I(\mathbf{X};T)$, where $T$ denotes the latent component label. We show that the upper bound can be achieved operationally by the proposed Gibbs-relabelling method (GRM), which conveys a label from the posterior $P_{T|\mathbf{X}}$ through channel simulation at rate $I(\mathbf{X};T)$, followed by vector quantization of the resulting exactly Gaussian conditional sources by reverse water-filling. Using the Shannon lower bound (SLB), we prove that GRM attains the SLB, and hence the RDF, of a general finite mixture if and only if every component attains its own SLB. For a GMM this holds throughout the fully active interval $D/d<\min_{k,m}\lambda_{k,m}$, where $\lambda_{k,m}$ are the eigenvalues of the component covariances, and for scalar GMMs the condition is also necessary. Since GRM cannot operate below the label cost $I(\mathbf{X};T)$, we propose a complementary stochastic scalar quantization (SSQ) scheme for low rates, which simulates an $M$-ary reconstruction index. We show that at low rates SSQ with $M\geq 2$ matches the Shannon RDF to first order: $R(D_{\max}-\delta)=\delta/(2\tau^2)+o(\delta)$, where $\tau^2$ is a directional sub-Gaussian proxy of the mixture, and quantify the price of a finite codebook through a strict rate gap at high rates and a distortion floor whose joint scaling in $M$ and number of mixture components is characterized. Numerical results illustrate both regimes and the finite-blocklength cost of channel simulation.
Read the full abstract

Robotics

PointWalker: Mapless Quadruped Locomotion Directly From Raw LiDAR Point Clouds

Sicen Li, Zhen Chu, Chao Li et al. (+3 more)

Quadruped robots deployed for inspection and field missions must cross heterogeneous terrain, from stairs, slopes, and gaps to high platforms, stepping stones, and balance beams, where safe support is sparse or see-through. Existing methods interpose a terrain map or a depth image between sensing and control. Maps are costly to maintain, corrupted by odometry drift and outliers, and misled by see-through gratings, while depth cameras degrade with lighting and surface material. In this paper, we present PointWalker, a mapless framework whose single reinforcement learning policy directly consumes raw point clouds from four light detection and ranging (LiDAR) sensors. Voxelized points are encoded by linear self-attention and fused with proprioception through cross-attention, so terrain geometry reaches the policy without maps or foothold estimation. One proximal policy optimization (PPO) run, with terrain-aware rewards and dual-channel simulation of see-through gratings, yields one policy for all seven terrain classes with a 90.1% mean success rate in simulation. Deployed zero-shot on a Deep Robotics X30 at 50 Hz onboard, it crosses 0.8-m gaps, climbs 0.8-m platforms and 45{\deg} steel-grating stairs, carries a 50-kg payload, and completes a 2.5-km mountain route.
Read the full abstract

All authors Sicen Li, Zhen Chu, Chao Li, Jun Zheng, Qiuguo Zhu, Jun Wu

Numerical Analysis · Cross-listed from math.OC

KKT Residual Sliding Manifolds: A Projection-Free Structured Finite-Time Solver for Nonlinear Constrained Optimisation

Abdelhafid Zenati and Kamal Youcef-Toumi

Nonlinear Constrained Optimisation (NCO) requires simultaneous satisfaction of the Karush-Kuhn-Tucker (KKT) conditions. Existing methods enforce these conditions through projections, penalties, barriers, or sequential approximations, potentially introducing computational complexity and convergence difficulties. For nonconvex problems, a KKT point need not be a local optimum. This paper reformulates NCO as stabilisation of a unified KKT sliding residual manifold and develops SM-KKT, a projection-free solver. Stationarity, equality feasibility, and regularised Fischer-Burmeister complementarity are integrated into a unified residual system, with complementarity encoding inequality feasibility, dual feasibility, and complementary slackness. The manifold's zero set is shown to be equivalent to the KKT conditions. The required Jacobian saddle-point inertia is characterised and shown, under stated assumptions, to be equivalent to the simultaneous satisfaction of the Linear Independence Constraint Qualification (LICQ) and Second-Order Sufficient Condition (SOSC). This characterisation establishes local stability of the structured correction algorithm under these conditions and distinguishes nondegenerate locally optimal KKT solutions from points failing second-order optimality. SM-KKT computes structured primal–dual corrections and applies a discrete sliding reaching law to drive the KKT residual into a prescribed boundary layer in finite time. Four nonlinear benchmarks show recovery of reference constrained optima with KKT residuals below $10^{-6}$, earlier boundary-layer reaching, and favourable KKT accuracy compared with projected primal-dual, augmented-Lagrangian, quadratic-penalty, and log-barrier baselines.
Read the full abstract

Computation and Language

An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays

Uday Bindal, Ishaan Karan, Manan Garg et al. (+3 more)

We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. Does Uniform Information Density (UID) predict salient scenes? 2. What other linguistic properties distinguish salient scenes from non-salient background? We answer both questions through a controlled corpus study on the MENSA corpus, paired with a Linguistically-Grounded Salience Model (LGSM), a dual-stream classifier that fuses a frozen BERT encoder with explicit linguistic features through adaptive gating. The UID picture is layered in long-form discourse. Per-scene UID summaries carry no independent signal once length is controlled, but at the token level salient scenes match non-salient material in the bulk while specifically suppressing the rarest, hardest-to-predict tokens in the upper tail. UID therefore lives at the within-scene token level rather than as a per-scene aggregate. Salient scenes also show a moderate and sustained cast of central characters (following an inverted-U pattern), strong third-person usage, syntactically simpler language, and more abstract vocabulary about motivation and conflict. LGSM exploits this signature and improves recall on salient scenes over a strong semantic baseline while yielding better downstream summaries.
Read the full abstract

All authors Uday Bindal, Ishaan Karan, Manan Garg, Ekansh Goyal, Rahul Mishra, Rajakrishnan Rajkumar

Machine Learning · Cross-listed from math.OC

Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning

Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov et al. (+3 more)

We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and the server must track the minimizer of the clients' weighted average loss. Clients are not alike as they collect data at different rates, with different noise, and change at different speeds. The main question is how much history should each one keep? A single shared window must serve every client at once, and so makes a fast-changing client carry the sampling noise of a slow, nearly stationary one. We give each client a memory of its own, sized to that client's noise, arrival rate, and drift, and refresh it by restarted accelerated method that starts from a common point. The tracking error is then bounded by \[ R\left(\sum_m w_m^{3/2}\,\sigma_m\sqrt{\gamma_m/\lambda_m}\right)^{2/3}, \] for clients with weight $w_m$, noise $\sigma_m$, arrival rate $\lambda_m$, and drift rate $\gamma_m$ on a domain of diameter $R$. This is never worse than what any common window can achieve, and strictly better whenever noise and drift are spread unevenly across clients. A lower bound that puts different groups of clients on different drift clocks shows this quantity is the right one. The two bounds agree up to a constant whenever the clients occupy boundedly many refresh scales, and in general differ only by the sixth root of the number of scales. Experiments show the gain comes from the memory rather than from the solver: it persists across accelerated, stochastic-gradient, and one-step methods, and against a separately tuned common-memory baseline.
Read the full abstract

All authors Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov, Ilya Kuruzov, Darina Dvinskikh, Alexander Gasnikov

Computation and Language

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

Project Apertus: Yixuan Xu, Yassine Turki, Vinko Sabolčec et al. (+128 more)

Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this is viable at scale. Apertus 1.5 extends the fully open Apertus family from text to multimodal reasoning. Continued pretraining of the Apertus 1.0 models, on 4T additional tokens for the 8B and 2T for the 70B, adds image and audio understanding and extends the context window fourfold to 262,144 tokens; multimodality enters through the tokenizer, the language-model head remains restricted to text, and the architecture is unchanged. Supervised finetuning, long-context finetuning, reinforcement learning with verifiable rewards, and preference alignment complete the released models. Thinking is a flag of the chat template rather than a separate model, and lifts mathematical reasoning by up to 20 points on the 8B model. The released models improve over their predecessors on nearly every benchmark; among fully open models of its class, the 8B leads on knowledge, instruction following, and cultural benchmarks, and its instruction following surpasses all compared models, including open-weight ones. On image and audio understanding, a first for the family, the models are competitive with fully open multimodal models, strongest on document understanding and long-form and lower-resource speech recognition, while specialized vision and audio models remain ahead on perception and transcription of English and other high-resource languages. As in Apertus 1.0, we train only on openly available data, respect crawler opt-outs retroactively, and exclude restrictively licensed material. We release the model weights, data preparation and training recipes, and evaluation suites under permissive licenses; openness extends to values, with the Apertus charter guiding alignment stages published alongside the models.
Read the full abstract

All authors Project Apertus: Yixuan Xu, Yassine Turki, Vinko Sabolčec, Valentina Pyatkin, Tommy Chu, Sven Najem-Meyer, Sean F. Carroll, Robert Smith, Raphael Kreft, Oscar Alessandro Tazza, Oleg Lavrovsky, Nicola Irmiger, Matteo Santelmo, Marian Schneider, Juan García Giraldo, Hanna Yukhymenko, Eduard Ďurech, Davit Melikidze, Dani Tamayo, Bettina Messmer, Aryan Ahadinia, Anunay Yadav, Allen Huang, Ahmad Fraij, Alessandro Bombarda, Alex Padula, Alexander Hägele, Alexander Sternfeld, Anna Hedström, Anna Kosovskaia, Arthur Wuhrmann, Arundhati Balasubramaniam, Badr Al Mahouri, Barna Pasztor, Bartosz Szostakiewicz, Bich Ngoc Doan, Bryan Schmid, Burak Sezen, Camille Challier, Clément Charmillot, Dana Shayakhmetova, Daniel Perruchoud, David Brüggemann, David Isztl, Elia Palme, Emma Anastassova, Fabian Bösch, Faruk Zahiragić, Fawzi Roberto Mohamed, Fiona Panicali, Florian Kolly, Flynn Guerra, Francesco Monti, Frederike Lübeck, Gennaro Oliva, Haofeng Yang, Haoliang Shang, Helen El Khoury, Henrique Mendonça, Jannis Vamvas, Jérome Landolt, Jessica Lam, Jingchun Xiao, Jonathan Coles, Joshua Oyebanji, Khanh Nguyen, Konstantinos Pitas, Lasse B. Strand, Li Mi, Loïc Deslarzes, Lorenzo Baggi, Lorenzo Noci, Luca Baumann, Luca Sartori, Lukas Drescher, Marco De Negri, Marco Passerini, Mark Klein, Marko Stojanovic, Martin Majsec, Matin Ansaripour, Mattea Busato, Mauro Pellonara, Max Neuwinger, Michael Graber, Michal Tešnar, Michelle Wastl, Miguel Gila, Mikolaj Boronski, Morgane Magnin, Moritz Reihs, Mukhammadali Sayfiddinov, Nathan Ranchin, Nicolas Cuveillier, Oscar Wohlfahrt, Qianqian Zou, Rada Kamysheva, Rita Sevastjanova, Roman Machacek, Sebastian Keller, Simon Matrenok, Simon Pierre, Stefano Schuppli, Suei-Wen Chen, Szabina Horváth-Mikulas, Taliesin Perez, Thilo Spinner, Thomas Kleine Buening, Tim Robinson, Tymoteusz Kwiecinski, Vilém Zouhar, Vinzenz Thoma, Xiaozhe Yao, Yannick Metz, Yuhei Fukuhara, Yusif Askari, Zixuan Chen, Alexander Ilic, Ana Klimovic, Andreas Krause, Andrei Kucharavy, Elliott Ash, Joost VandeVondele, Martin Rajman, Mennatallah El-Assady, Thomas Schulthess, Timo Kehrer, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag

Cryptography and Security

Fetch Me If You Can: A Comprehensive Analysis of Fetch Metadata

Pedro Bernardo, Alex Ploner, Marco Squarcina et al. (+2 more)

Effective server-side defenses against cross-site attacks depend on understanding the context in which browser requests are generated. However, servers often lack the information needed to distinguish legitimate requests from potentially malicious cross-site interactions. Fetch Metadata, a security mechanism introduced in 2019, addresses this limitation by adding a set of HTTP headers to outgoing browser requests. These headers provide servers with information about a request's context and provenance, enabling them to enforce request isolation policies accordingly. However, the extent of Fetch Metadata's real-world adoption and its interaction with existing security mechanisms remain largely unexplored. In this paper, we present the first large-scale measurement study of Fetch Metadata adoption. We analyze the top 1M websites in the Tranco list to detect deployments of Fetch Metadata isolation policies and identify custom policies used in the wild. We then examine how these policies address cross-site threats and assess their security coverage. Finally, we provide the first systematic comparison of Fetch Metadata with existing client-side security mechanisms, revealing security gaps that arise from differences between client-side and server-side enforcement.
Read the full abstract

All authors Pedro Bernardo, Alex Ploner, Marco Squarcina, Mauro Tempesta, Matteo Maffei

Machine Learning

Sensitivity Fidelity Reveals Physical Dependencies Beyond Forecast Accuracy in Deep-Learning Earth-System Models

Qi Chen, Peng Zhan, Hongxing Cui et al. (+2 more)

Deep-learning models increasingly rival numerical simulation in Earth-system forecasting, yet forecast error alone cannot determine whether their learned input-output dependencies are physically consistent. Here we introduce sensitivity fidelity as an additional criterion: alongside prediction error, model responses to input perturbations should be examined against a trusted reference or established physical knowledge. In an idealized Rayleigh-Bénard convection benchmark, four surrogate architectures achieved low forecast errors yet encoded markedly different sensitivities. Quantitative comparison with a matched adjoint distinguished the models far more sharply than forecast accuracy and showed that predictive skill and sensitivity fidelity need not coincide, while finite-perturbation experiments further linked these differences to the propagation of initial-condition uncertainty. We then applied this strategy to El Niño-Southern Oscillation prediction, where no adjoint reference exists and learned sensitivities showed event-wise robustness, validity under finite perturbations, and consistency with established precursors. These results identify gradient-based evaluation as a discriminating complement to forecast-error metrics, providing a practical test of whether data-driven Earth-system models learn physically credible dependencies.
Read the full abstract

All authors Qi Chen, Peng Zhan, Hongxing Cui, Wenqing Cui, Ibrahim Hoteit

Cryptography and Security

Poisoned into Action: Context Attacks on Typed Decision Workflows

Chenkai Wu, Xing Chang and Jun Yan

Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating context poisoning thus requires connecting model decisions to execution outcomes while accounting for legitimate automation retained by defenses. We introduce an execution-aware protocol tracing poisoned evidence through retrieval, model choice, automated action, and persisted state. We evaluate it with 1,659 fresh calls to Jev-1.13.0 across 20 development tasks in two synthetic workflows, using three repetitions per condition. Under natural retrieval, a standalone payload reaches all 60 trials and produces five security-violating executions, while a carrier-payload pair exposes the payload in 57 trials and produces one violation. An initial source-exclusion gate blocks the pair's observed violation but also withholds ten otherwise correct attacked decisions and sixteen correct clean decisions. Correcting its empty-scope behavior restores twelve clean decisions without additional model calls. Factorial controls show that adding correct evidence reduces wrong executions from 119/120 to 55/120 in the semantic arm and from 60/120 to zero in the neutral arm, suggesting that much of the improvement reflects general evidence value rather than attack-specific protection. Three prespecified contrasts are not statistically supported after Holm correction, so the findings remain exploratory. The protocol provides an auditable framework for studying which poisoning-induced errors reach execution and how much correct automation defenses preserve. Code is available at https://github.com/WuXixiong/jev-poisoning-bench.
Read the full abstract

Information Theory · Cross-listed from math.CO

Hull Variation in Symplectic Linear Codes

Kanat Abdukhalikov, Somi Gupta and Duy Ho

We study the variation of hull dimensions of symplectic linear codes under equivalence transformations preserving the symplectic distance. For a symplectic linear code $C$, we introduce an even-valued invariant $\Delta(C)$, which depends only on the equivalence class of $C$. This invariant can be expressed as the generic rank of an associated space of alternating matrices and, equivalently, as twice a corresponding matroid matching number. If $C$ has dimension $k$, we prove that the minimum symplectic hull dimension among all codes equivalent to $C$ is $k-\Delta(C)$. Consequently, $C$ is equivalent to a symplectic LCD code if and only if $\Delta(C)=k$. We further show that every symplectic MDS code of even dimension is monomially equivalent to a symplectic LCD code. For a symplectic self-orthogonal code $C$, we determine all attainable hull dimensions: for every integer $r$ with $0\le r\le \Delta(C)/2$, there exists a monomially equivalent code whose symplectic hull has dimension $k-2r$. We also refine a standard form for the generator matrix of a symplectic self-orthogonal code and derive the corresponding parity-check matrix and the Gram matrix of the dual code. In the self-dual case, we characterize $\Delta(C)$ through minors of an associated symmetric matrix. Furthermore, we relate hull variation to graph matchings, establish a bound for $\Delta(C)$, and give graph constructions producing symplectic self-dual MDS, optimal, and best-known codes.
Read the full abstract

Computer Vision

UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservation

Xianlin Zeng, Xiaolong Shen, Ruijie Quan et al. (+1 more)

3D editing aims to modify an existing 3D asset according to user intent while preserving geometry and appearance outside the intended edit region. Existing methods often rely on task-specific training, source-3D inversion, or external 3D masks, and lack a unified framework for diverse editing conditions and tasks. We propose UMAS3D, a unified 3D editing framework that is training-free, inversion-free, and free from external 3D masks. UMAS3D converts text, bounding boxes, reference images, and their combinations into common target-view guidance, after which addition, deletion, modification, appearance, and pose editing share the same downstream 3D generation process. Our key insight is to couple online edit-region estimation with region-aware source preservation. Mask-Free Adaptive Region Modeling (MARM) initializes an Edit/Keep prior from source-target visual differences and progressively refines it as the target structure evolves, while Source-Guided Preservation Steering (SGPS) constrains the current Keep-region states to retain source geometry and appearance without suppressing target-driven changes. Experiments show that UMAS3D supports addition, deletion, modification, appearance, and pose editing while effectively preserving unedited source content. These advances make UMAS3D a unified framework for flexible and source-preserving 3D editing across diverse editing conditions.
Read the full abstract

All authors Xianlin Zeng, Xiaolong Shen, Ruijie Quan, Yi Yang

Sound

Sleep Sound Event Detection Powered by Learnable Multi-Resolution Adaptive Line Enhancer

Chanwoo Park and Chanwoo Kim

Sleep-disordered breathing, including snoring, hypopnea, and obstructive apnea, is the hallmark of obstructive sleep apnea, whose severity is quantified by the Apnea-Hypopnea Index (AHI). As conventional polysomnography is costly and clin- ically demanding, microphone-only detection has emerged as a noninvasive alternative for screening. We propose ALE- Confidence Fusion Sound Event Detection (ACF-SED), the first framework that directly injects the per-frame confidence map of an Adaptive Line Enhancer (ALE) into Transformer atten- tion biasing and feature modulation, rather than as mere pre- processing. A Multi-Resolution ALE Bank aggregates three parallel NLMS filters at distinct decorrelation delays, while a Confidence-Guided Cross-Path block couples event and noise streams via gated cross-attention. On the Audio-Polygraphy Dataset for Sleep Apnea Analysis, ACF-SED achieves state- of-the-art detection across Event-F1, Segment-F1, and PSDS, enabling end-to-end AHI estimation.
Read the full abstract