Peer Revenue Impact factor: volatile

Papers

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

Computer Science

cs Watch Computer Science

Thursday 8 October

Machine Learning

CausalDreamer: Learning Predictive World Models with Latent Disentanglement

Prince Jha, Nils Lukas, Kun Zhang et al. (+1 more)

World models for control must capture which aspects of the environment respond to the agent's actions and which are relevant to reward. Generative world models such as Dreamer 4 consist of a video tokenizer, which encodes each frame into a latent, and a dynamics model, which is pretrained to predict future latents from past latents and actions. Yet the tokenizer is trained with a reconstruction objective, without action or reward supervision, so its latent provides no explicit mechanism to separate controllable, uncontrollable, reward-relevant, and reward-irrelevant information. We propose CausalDreamer, which keeps the tokenizer frozen and re-encodes its latent into a factored representation of four groups along two axes: controllability, where only the two controllable groups receive the action, and reward relevance, learned by predicting the reward from the two reward-relevant groups. The pretrained dynamics model is then fine-tuned to predict the factored representation. We evaluate CausalDreamer and the pretrained world model it starts from with model-predictive planning on 20 MMBench2 tasks: 10 clean tasks seen during training and 10 unseen tasks, of which 6 are manipulated variants of clean tasks with a changed background, object, or maze layout, and 4 are new environments. We normalize returns so that a policy taking uniformly random actions scores 0 and an expert scores 1. CausalDreamer achieves a 14% higher normalized score than the pretrained world model on the clean tasks (0.199 vs.\ 0.175) and a 25% higher score on the manipulated variants (0.307 vs.\ 0.246), while neither model scores meaningfully above the random policy in the new environments. Additionally, our analysis shows that the factored representation separates reward-irrelevant changes, such as a changed background, from its reward-relevant groups.
Read the full abstract

All authors Prince Jha, Nils Lukas, Kun Zhang, Salem Lahlou

Artificial Intelligence

PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary

Chenyang Xu, Donglin Xie, Xi Xiang et al. (+12 more)

Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transforms, or companion views may depend on withheld samples. We introduce PulseBound, a PPG representation learner combining physiologically structured future-beat prediction with an explicit stored-window information boundary. A content-independent cutoff separates the visible prefix from the prediction target. Prefix-only normalization, suffix replacement before derived-view construction, and aligned masking ensure that encoder inputs depend only on the visible prefix and cutoff. This yields stored-suffix invariance: with fixed model state, randomness, prefix, and cutoff, changing the stored suffix cannot change the forecast context. A shared horizon-conditioned head predicts nine rhythm and morphology descriptors for up to four extractor-valid future beats, using elementwise validity masks; optional ECG-derived pulse-arrival-time supervision is restricted to training. On MIMIC and VitalDB groups held out from PulseBound backbone pretraining, PulseBound reduces nine-state transformed-space MAE relative to last-visible-beat persistence by 28.06% and 22.22%, respectively, with gains in MAE, MAE-Skill, and Spearman correlation across all 40 source-cutoff-horizon cells. In a separate comparison of seven models on 13 downstream tasks, PulseBound achieves the best mean on nine frozen linear-probe and seven full-fine-tuning tasks. Stored-suffix interventions cause zero recorded changes in forecast contexts or predictions, with zero suffix-input gradients at audited precision under the stored-window interface. These findings separate three testable aspects of predictive physiological representation learning: information access, supervised future structure, and transfer.
Read the full abstract

All authors Chenyang Xu, Donglin Xie, Xi Xiang, Xiaoyu Li, Yufan Lu, Jiqiun Gao, Yi Zhao, Xin-Yi Li, Guangpu Zhu, Zijian Wang, Xiwen Yang, Dezhen Wang, Lin Chen, Shenda Hong, Yelei Li

Machine Learning · Cross-listed from physics.comp-ph

Ghost tasking for parametrized Gaussian Processes solving linear differential equations

Johanna Moser, Christopher Albert and Sascha Ranftl

Physics-informed machine learning has gained significant attention in recent years. In regimes of limited data, parametrized Gaussian processes have become popular. Existing approaches, however, often face limitations, such as requiring parametrizable (also called controllable) systems or a large number of output tasks. In this work, we introduce a systematic procedure we call "ghost tasking", using auxiliary tasks to circumvent these limitations. We prove that such ghost tasks can render any non-parametrizable system effectively parametrizable, enabling algorithmic construction of parametrized Gaussian Processes while keeping the number of required tasks (i.e. output dimensions) and latent functions low. We find that ghost tasking performs especially well in an inverse problem setting, even with very few available data. We show the usage and power of ghost tasking in three experiments, providing systematic comparisons to the only other currently available method applicable to all experiments. We provide necessary syntax and explications for two computer algebra programs that compute parametrizations for systems with polynomial or rational coefficients. Our theoretical results extend to systems with meromorphic functions.
Read the full abstract

Artificial Intelligence

Complexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks

Jinfan Xu and Jieting Luo

Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While decision problems for general infinite AFs typically reside at high levels of the analytical hierarchy ($\Sigma_1^1$ or $\Pi_1^1$), restricting the framework to be computably finitary reduces some of the complexity to the arithmetical hierarchy. In this paper, we present a complexity mapping of grounded and preferred semantics in computably finitary AFs across standard decision problems: credulous acceptance ($\Cred$), skeptical acceptance ($\Skep$), extension existence ($\Ex$), uniqueness ($\Uni$), and non-empty existence ($\NE$). For grounded semantics, credulous and skeptical acceptance are already known to be $\Sigma_1^0$-complete. We show that non-empty existence is also $\Sigma_1^0$-complete, whereas existence and uniqueness are trivial. These classifications are understood within the domain of valid computably finitary representations. For preferred semantics, using a computably finitely branching computation tree, $\Cred_{\pref}$ is shown to be in $\Pi_1^0$-c and $\NE_{\pref}$ is $\Sigma_2^0$-c. However, it is insufficient to reduce universal quantification and global uniqueness, leaving $\Skep_{\pref}$ in $\Pi_1^1$ and $\UniPref$ in $\Sigma_2^1$-c. Our results show the precise boundary where finitarity succeeds to bring reasoning down to the arithmetical hierarchy and where second-order quantification forces problems back into the analytical hierarchy.
Read the full abstract

Robotics

REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models

Houlong Xiong, Zhenqi Qiu, Zechen Wang et al. (+8 more)

Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks provide smooth execution, whereas frequent replanning improves reactivity at the cost of action discontinuities. We introduce REACT, a rolling-denoising framework that makes flow-based VLAs more reactive while preserving long-horizon context. Instead of regenerating entire action chunks from scratch, REACT maintains a persistent action buffer with staggered flow timesteps. At each control step, the full horizon is denoised using the latest observation, the cleanest action block is executed, partially refined future blocks are shifted forward, and fresh noise is appended to the tail. As a result, each executed action block is refined across multiple recent observations before deployment. To support real-time control, we further introduce dual decoupling, which separates sensing, VLM encoding, DiT denoising, and action execution, enabling high-frequency observation updates and action streaming under practical compute constraints. Across the RoboTwin 2.0 simulation benchmark and real-world tasks spanning bimanual manipulation and dynamic control on multiple robot platforms, REACT improves task success and reduces reaction latency while producing smoother trajectories than frequent-replanning and asynchronous baselines.
Read the full abstract

All authors Houlong Xiong, Zhenqi Qiu, Zechen Wang, Suohang Zhang, Yiyu Ren, Wanting Xu, Hongfei Niu, Chengyang He, Ge Sun, Ran Cheng, Qian Zhu

Machine Learning

Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits

Kanghui Ning, Marin Biloš, James T. Wilson et al. (+5 more)

Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)? We systematically study this along three axes: adaptation, aggregation, and context construction. Our evaluation spans modern TFMs across the TabArena benchmark, supplemented by experiments on wide and large-scale tables from OpenML. For adaptation, we introduce DiagScale, a diagonal query-key similarity update. It trains only 0.003-0.03% of model parameters and achieves gains comparable to full fine-tuning across three independently pretrained backbones. For aggregation, both pool composition and selection strategy matter. TabPFN-3 already averages predictions from different preprocessing variants of the same data, and adding more such predictions yields diminishing returns. With a broader pool of 96 configurations, greedy selection reduces error by 2.4% relative to the default predictor, but uniform averaging increases error. For context construction, attention-guided retrieval improves TabPFN-3's predictions on some large tables and supports source pools beyond the full context memory limit. The context expansion methods we test yield no consistent improvement. Taken together, our results suggest that adaptation and selective aggregation yield consistent benchmark-level gains. The benefits of context construction depend more on the task and data regime. Adaptation and aggregation over the same backbone yield further gains when combined, but require substantially more computation than default inference. These trade-offs motivate choosing strategies according to the available computation budget. Code is available at https://github.com/kanghui-learning/test-time-compute-for-tabular-foundation-models.
Read the full abstract

All authors Kanghui Ning, Marin Biloš, James T. Wilson, Yilang Zhang, Kashif Rasul, Dongjin Song, Anderson Schneider, Yuriy Nevmyvaka

Machine Learning

The Polytopal Neural Network

A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski et al. (+2 more)

Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on prespecified corpora, or explain models post-hoc. We propose Polytopal Neural Networks (PNNs), a framework that extracts distinct layer-wise aspects by enforcing a polytope-based structure that is used directly in subsequent information processing. We scale our approach using learned corpus representations and an amortized simplex inference procedure and highlight how the framework also gives a direct route to vector quantized (VQ) training. In PNNs, observations are explicitly described by their alignment with layer-specific aspects. Empirical results show that imposing polytopal constraints on neural network representations preserves meaningful structures in the latent space with minimal degradation in performance, favorable compressed representations when compared to VQ representations in unsupervised learning, while also providing a performant new approach to VQ deep learning training. Our findings suggest that deep networks can enforce interpretable polytope-based representations, offering a principled path toward more transparent AI systems with minimal performance compromise.
Read the full abstract

All authors A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski, Kristoffer Wickstrøm, Morten Mørup

Artificial Intelligence

An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation

Yunpeng Gong, Huolong Wu, Can Yang et al. (+1 more)

PDE solution discovery aims to identify explicit symbolic expressions for unknown physical fields from observations under known physical constraints. Existing methods, however, collapse data fidelity and physical consistency into a single terminal score used as the sole feedback signal, providing little information about which subexpressions are responsible for a candidate's final performance. This opaque terminal feedback severely limits the interpretability of the search process itself, offering no insight into why a candidate succeeds or fails. Consequently, reusable structures in otherwise suboptimal candidates are often discarded, whereas incidental syntax along successful search trajectories may be repeatedly reinforced. We propose SED-MCTS, a Monte Carlo tree search approach that distills structural experience from evaluated expressions and reuses it to guide subsequent symbolic solution search. Through counterfactual subtree interventions, SED-MCTS estimates local structural contributions, routes reliable evidence to the responsible construction edges, and preserves useful components in a refined structural archive. The approach naturally extends to coupled multiphysics systems. Across a diverse suite of PDE benchmarks, SED-MCTS achieves strong performance under a fixed evaluation budget and improves search efficiency and robustness under noisy or scarce observations.
Read the full abstract

All authors Yunpeng Gong, Huolong Wu, Can Yang, Min Jiang

Machine Learning

Agentic-TTT: Training test-time policy for test-time training

Jiahao Lu and Mohan Kankanhalli

Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment experience into parameter updates, TTT provides a direct mechanism for model-level self-improvement. Yet TTT is not universally beneficial: each TTT algorithm works in different settings, and applying an ill-suited method could waste test-time compute or even damage model performance. Therefore, such parameter-level self-improvement requires agency: the model must decide when TTT is warranted, which algorithm to invoke, and whether an existing skill can be reused. To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions. Agentic-TTT turns TTT procedures into callable tools, treats accumulated skills as an evolving deployment environment, and trains its policy using the observed utility gains from its decisions. On our benchmark, Agentic-TTT nearly doubles the utility over the backbone model, learns to trade off utility against compute, and generalizes to domains unseen during training. Together, these results point toward autonomous self-improvement: models that can decide how to learn from their own deployment experience.
Read the full abstract

Networking

Decentralized Latency Models and Information Flow for TSN Shapers - A Tutorial

Alexej Grigorjew, Stefan Geissler, Jürgen Schmitt et al. (+1 more)

Recent advancements in the fields of industrial automation and in-vehicle communication have also increased the requirements on their underlying networks. Traditional field bus technologies are being replaced by regular Ethernet devices with features from the IEEE Time-Sensitive Networking working group. Their standards are designed to achieve zero congestion loss and deterministic latency bounds, but the specific guarantees can differ depending on the shapers used and how the bounds are calculated. After several contributions to the standardization efforts, this work presents a number of decentralized latency models that can be applied locally on the switches, without requiring global knowledge from the rest of the network. It includes a formal definition of delay segments that allows to incorporate interoperability between different shapers and latency models in the future. It presents pseudo-code suggestions for the latency bounds computation of Strict Priority, Credit-Based Shaping, Asynchronous Traffic Shaping, and Cyclic Queuing and Forwarding, all of which can be applied locally on the devices. Finally, five models were implemented and evaluated with respect to their efficiency in terms of latency, jitter, and number of accepted streams. The results illustrate how different shapers are suited for different networks and traffic distributions.
Read the full abstract

All authors Alexej Grigorjew, Stefan Geissler, Jürgen Schmitt, Tobias Hossfeld

Information Theory

Exact Second-Order Asymptotics for the Discrete Wyner–Ziv Problem

Lin Zhou

We revisit the discrete Wyner–Ziv problem and establish exact second-order asymptotics. Our main contribution is a second-order converse bound, which is derived using posterior decomposition, concentration inequalities, and a conditional Gaussian approximation for martingales. Furthermore, we extend the previous best known achievability result of Li and Li (arXiv 2025) by allowing the test channel to depend on the type of the observed source sequence. Exact second-order asymptotics are established by combining our achievability and converse bounds. In particular, we show that the achievability bound of Li and Li (arXiv 2025) is not optimal in general. Specifically, we provide two numerical examples to illustrate our results: a binary asymmetric source and a quaternary source. For the first example, the achievability bound of Li and Li (arXiv 2025) achieves the optimal second-order asymptotics. However, in the second example, we show that our achievability result is optimal, which reduces the second-order coding rate of Li and Li (arXiv 2025) by $10.77\%$ at the excess-distortion probability of $0.1$ and by $21.35\%$ at the excess-distortion probability of $0.2$.
Read the full abstract

Cryptography and Security

Moving Target Defense in SDN-enabled EV Charging Network

Roland Plaka, Mikael Asplund and Simin Nadjm-Tehran

Software-Defined Networking (SDN) is emerging as a promis- ing technology for EV Charging infrastructure (EVCI) since it enables flexible, programmable control of EVCI networks, yet its security gain to EVCI remains underexplored. SDN-enabled EVCI faces an increas- ing number of cyber threats arising from the convergence of IT and OT components; in particular, low-rate Denial-of-Service (DoS) attacks. Ear- lier works identify a trend toward low-rate attacks in OT networks that may exhaust SDN switch flow tables and which can result in disabling the entire charging sites without triggering volume-based defenses. In this paper, we propose CS-SHIELD, a Moving Target Defense mecha- nism for SDN-enabled EVCI communication. We showcase the imple- mentation of the proposed mechanism that detects malicious flow table rules via cross-layer identity verification and responds by reassigning virtual IP addresses to all active chargers. Experiments on an emulated SDN testbed with a real charging protocol implementation demonstrate that CS-SHIELD maintains full site availability under attack, responds quickly, adds only a negligible delay under normal conditions. The reas- signing (shuffle) approach at each reaction makes the earlier reconnais- sance knowledge by the attacker rendered worthless.
Read the full abstract

Software Engineering

Neural Network Verification for Deep Joint Source-Channel Coding

Thanh Le, Hai Duong, Takeshi Matsumura et al. (+1 more)

Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharply under adversarial perturbations and channel disturbances; no method formally bounds this degradation for DeepJSCC. We present the first bound-propagation framework for verifying DeepJSCC's decoder, bounding worst-case reconstruction error over a given wireless channel's noise region. Current deep neural network (DNN) verifiers do not support three DeepJSCC decoder components: parametric rectified linear activations (PReLU), transposed convolutions, and Rayleigh fading. We extend state-of-the-art techniques for optimization of linear relaxation in DNN verification for PReLU, replace the transposed convolution with its restricted upsample-then-convolution form, and formulate Rayleigh fading as a structural perturbation prepended directly into the decoder, thereby reducing the dimensionality of the verification problem. We also instantiate Lipschitz-regularized global robustness training, denoted GloRo, improving global robustness and enabling tight certification of DeepJSCC models for the first time. On DeepJSCC model for image transmission, this global robustness training procedure combined with structural encoding lowers the median certified bound by up to 41% and certifies about ten times more safe cases (192 against 19) than GloRo with interval encoding at a 10-degree error in channel estimation. Over-the-air validation with an orthogonal frequency-division multiplexing (OFDM) implementation on software-defined radio devices confirm the certificate holds on real hardware, with a worst observed error on radio link at 0.082 against a certified bound of 0.128.
Read the full abstract

All authors Thanh Le, Hai Duong, Takeshi Matsumura, ThanhVu Nguyen

Computer Vision

DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

Yupeng Xie, Zhenyang Wang, Jiayi Zhu et al. (+4 more)

Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video understanding, data video understanding places greater emphasis on accurately reading data from animated charts, integrating evidence across charts and time, and understanding how narrative organization and visual design communicate information. Yet existing benchmarks target either general videos or static charts, and data video understanding has not been systematically evaluated. We present DataVista, the first benchmark for data video understanding, containing 961 real-world data videos and 6,775 evaluation questions organized under a three-level progressive capability framework (data perception, temporal reasoning, narrative understanding) with 10 fine-grained question types across five topic domains. Systematic evaluation of 19 mainstream MLLMs shows that the best-performing model, Gemini-3.1-Pro, achieves 70.0% overall accuracy, still far below human expert performance, with models performing worst on Causal Reasoning and Narrative Structure. Increasing frame counts and adding subtitles mainly benefit data perception and temporal reasoning, with limited gains in narrative understanding. Further analysis of model responses identifies typical failure modes in chart reading, evidence judgment, and instruction understanding. The benchmark is available at https://github.com/HKUSTDial/DataVista.
Read the full abstract

All authors Yupeng Xie, Zhenyang Wang, Jiayi Zhu, Yinghao Tang, Zhouan Shen, Yiyu Chen, Yuyu Luo

Formal Languages and Automata

Quantitative Verification of Infinite-State Networks

Dhruv Nevatia and David Basin

Many network protocols and distributed systems combine recursion, unbounded local state, and quantitative behaviour such as cost, latency, or reliability. Existing decidability results for networks of pushdown systems are largely qualitative, and do not extend to quantitative analyses, which must jointly track traces and weights. We present a framework for the quantitative verification of acyclic networks of weighted pushdown systems. Finitely summarising a recursive network component requires collapsing the infinite family of runs obtained by pumping its nested loops, and doing so exactly, rather than by over-approximation, is a standing difficulty. We give a class of weight domains where this is possible: pumping semirings, those in which the weights accumulated by such a family collapse to a closed form; informally, the domain must be unable to count iterations. The class admits domains with infinite ascending chains, such as the arctic semiring and downward-closed languages. Over these, we give a terminating saturation algorithm computing quantitative reachability exactly, resting on two ideas: segment tree algebras, a compositional representation of runs, and thermal extensions, which symbolically separate accelerated weights so that further acceleration remains exact. We use this to compute upward and downward closures of context-free languages uniformly, and to lift the algorithm to acyclic networks over "thin" pumping semirings, yielding the first quantitative safety and reachability analyses for networks of pushdown systems.
Read the full abstract

Artificial Intelligence

MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation

Zipeng Wang, Xinpeng Dong, Yuefan Wang et al. (+6 more)

On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision. However, uniform weighting overlooks differences in token learning value, while existing weighting methods rely on predefined mappings from prediction signals to token weights. These mappings are not learned from the effectiveness of the resulting student updates, limiting their ability to adapt to evolving learning needs. In this paper, we propose MetaOPD, a bilevel optimization framework that jointly learns the student model and a lightweight token-weighting network. The inner objective updates the student through weighted OPD, while the outer objective optimizes the weighting network using validation loss on reference solutions after a virtual student update. Differentiating through this update connects weighting decisions to their effects on post-update performance, allowing the mapping from prediction signals to token weights to evolve alongside the student. Experiments on six mathematical reasoning and three out-of-domain datasets, covering two student scales and seven baselines, demonstrate the effectiveness of MetaOPD, with Avg@8/Pass@8 gains over OPD of 1.99/5.97 percentage points for the 0.6B student and 2.25/6.41 points for the 1.7B student.
Read the full abstract

All authors Zipeng Wang, Xinpeng Dong, Yuefan Wang, Pingchen Lu, Xian Wei, Kun Kuang, Fei Wu, Zhongxiang Dai, Min Zhang

Computer Vision

FearCaut-Qwen: Affective Steering in a Vision-Language Model Shifts the Decision Criterion for Hazard Assessment

Xiaoshan Zhou

Vision-language models (VLMs) show great potential for damage assessment after a disaster, but a recurring deficiency is that they are reluctant to declare a hazard; that is, recall is low even when overall accuracy appears adequate. This study examines that deficiency by using signal detection theory to decompose the decision behavior into perceptual capability and decision-criterion placement. We then propose a novel method for correcting the over-conservative decision policy, inspired by the finding that fear makes humans risk-averse, and ask whether an affective representation associated with fear can be causally manipulated to similarly alter a VLM's decision tendency. Using mechanistic interpretability, we localize a causally implicated affective circuit in the model and use activation steering to manipulate it while observing the effect on downstream prediction. The method is tested on a two-stage SeisMLLM pipeline built on Qwen2.5-VL-7B-Instruct, which flags only 27.0% of genuinely unsafe buildings on the SeisMLLM-1K test split and never issues a false Red, an SDT criterion of c = +1.354, despite adequate evidence quality (d' = 1.521). An affective direction is localized on emotion-rich natural scenes, causally validated by sparse-neuron knockout and distributed steering on held-out emotion data, and then injected into the building task. Fear-direction injection raises Red recall to 75.7% (p<0.001), and subtracting the same direction suppresses Red predictions entirely, whereas norm-matched random and matched happiness directions show no significant effect. The mechanism is a shift in criterion (c=-1.515) while discrimination is not improved (d'=-0.493). These results show that VLM decisions can be adjusted at inference time without retraining and demonstrate how mechanistic interpretability can be used to diagnose and control VLM decision behaviors in engineering applications.
Read the full abstract

Machine Learning

Example-driven Parametrisations for Bayesian Shape Optimisation

Gabriel Diaz-Aylwin, Joseph Neighbor, Abiel Malkani Talwar et al. (+2 more)

Bayesian optimisation is the natural tool for shape design when objectives are expensive and non-differentiable, but it needs a compact yet expressive parameterisation of the search space. Hand-crafting one is a complex endeavour requiring domain expertise, and often yields implicit infeasible regions, artificial bounds, and coupled, unordered coordinates. We instead learn the parameterisation from a collection of existing designs, applying principal component analysis to the deformations between shapes. The result is a linear, interpretable search space in which the number of components explicitly trades expressivity against dimensionality. Across aerofoils, wings, and radio-frequency cavities, spanning 2D geometry to 3D aerodynamics and electromagnetics, we show improved sample efficiency and the ability to explore beyond the confines of hand-crafted baselines.
Read the full abstract

All authors Gabriel Diaz-Aylwin, Joseph Neighbor, Abiel Malkani Talwar, Rui-Yang Zhang, Henry B. Moss

Computation and Language

Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks

Xing Li, Qingcheng Chang, Jinzhong Ning et al. (+5 more)

Jev is a "System One" model that returns a choice among given options instead of generating text. We study how such a specialized decision model compares with general-purpose large language models (LLMs). We evaluate Jev on 13 multiple-choice benchmarks covering knowledge, reasoning, and multilingual understanding, and compare it with 19 LLMs in three tiers: frontier, representative, and small. Jev is competitive with frontier LLMs on knowledge and commonsense benchmarks and obtains the best score on MMLU-Redux and ARC-Challenge. Outside mathematics, it also outperforms most representative LLMs and all small LLMs. However, it falls behind on mathematical word problems: on MathQA, it is 17.7 points below the frontier median and scores lower than all 19 LLMs. These results indicate that a specialized decision model can match general-purpose LLMs on decisions that rely mainly on knowledge, but not on decisions that require multi-step calculation.
Read the full abstract

All authors Xing Li, Qingcheng Chang, Jinzhong Ning, Changfeng Xu, Shenlong Zhang, Yijia Zhang, Ling Luo, Hongfei Lin

Machine Learning · Cross-listed from stat.ML

Efficient quadratic entropy with distance sketches

Steve Huntsman

We detail scalable methods for approximating the quadratic entropy $p^T d p$ for arbitrary distributions $p$ and common distances $d$ of negative type. We focus on the Euclidean and spherical geodesic cases, which both use random feature embeddings and projections to dramatically improve computational complexity within a simple framework. Amortization of a single large matrix multiplication and control variates further enable computation at large scale with low memory and runtime in situations where $d$ is held constant while $p$ varies. We demonstrate this with a comparison against direct pair sampling and bibliometric/scientometric examples on Open Graph Benchmark datasets, revealing papers, fields, and institutions with both particularly narrow and broad interdisciplinary reach from their citations and text features alone.
Read the full abstract

Robotics

Predicting Cable Dynamics with Physical Attention Bias

Avihai Giuili, Rotem Atari, Avishai Sintov et al. (+1 more)

Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of their error occurs where the cable touches itself or the floor. Attention over all pairs of cable segments can represent contact between parts of the cable that are far apart along its length, but attention has no notion of geometry. A cable has two pairwise distances, which agree only while it is straight: the arc-length distance along the cable, which governs elastic forces, and the Euclidean distance in space, which governs contact. We add a physical attention bias, an additive term on the attention logits with a learned rate, and ask which distance it should use. We compare no bias, each distance alone, and both distances on disjoint sets of heads, keeping the rest of the model and the training protocol fixed. A physical bias improves prediction on unseen cables. The gain is largest when attention is the only mechanism that connects distant segments: there, the arc-length bias reduces prediction error by 15% and more than halves the drift in segment length. The Euclidean bias alone stays close to unbiased attention, while assigning both distances across heads is best or near-best on every metric we report. Code and per-run records: https://github.com/avihaig/dlogps.
Read the full abstract

All authors Avihai Giuili, Rotem Atari, Avishai Sintov, Maya Bechler-Speicher

Numerical Analysis

Mathematical foundation of symmetric fast Fourier transform

Weifeng Hou, Kai Jiang and Jingfei Tang

In this work, we study the fast Fourier transform (FFT) of discrete data with crystallographic symmetry, for which standard FFT algorithms incur substantial redundant computation. We establish a rigorous mathematical theory of the symmetric fast Fourier transform (SFFT) for $n$-dimensional crystallographic groups and propose the SFFT and symmetric inverse fast Fourier transform (SIFFT) algorithms. We derive symmetry-reduction formulas for both linear and translational symmetries and unify them into a recursive framework. We analyze the arithmetic complexity to obtain theoretical speedup factors relative to the standard FFT, and we confirm the accuracy and efficiency of the proposed methods by numerical experiments on representative three-dimensional space groups.
Read the full abstract

Robotics

CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding

Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu et al. (+6 more)

Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing fault-recovery methods often require task-specific retraining, fault labels, explicit diagnosis, or privileged embodiment information. We introduce CAPABLE, a unified capability-aware adaptation framework for frozen VLAs that integrates self-supervised capability inference with residual reinforcement learning. CAPABLE infers capability, how much of the commanded motion each joint actually realizes and how that motion contributes to end-effector behavior, online from command-response history and kinematics using a temporal encoder shared across joints, Jacobian grounding, cross-joint attention, and self-supervised physical prediction. The resulting representation conditions a residual policy that adds bounded corrections to the VLA arm action without fault labels or faulty-joint identifiers. Across 28 LIBERO tasks, CAPABLE raises success on an actuator excluded from fault training from 24.8% to 59.3%, outperforming a parameter-matched global-history baseline by 17.4 points while preserving healthy performance. Leave-one-actuator-out experiments across six joints show that this transfer is not specific to one actuator, and additional evaluations characterize transfer to unseen fault families and demonstrate recovery on a physical Franka Panda. https://capable-vla.github.io/
Read the full abstract

All authors Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu, Zhiyuan Gao, Yanxiang Zhan, Jeroen Schafer, Andrew Melnik, Qing Yang, Michael Beetz

Formal Languages and Automata

Non-recursive trade-offs for two-way machines

Christos Kapoutsis

If the machines of some type A have enough resources to (i) solve problems that no machine of type B can solve, and (ii) simulate any unary two-way deterministic finite automaton that has access to a linearly-bounded counter, then typically no recursive function can upper bound the increase in the size of description when a machine of type A is replaced by an equivalent machine of type B.
Read the full abstract

Computer Vision

Learning Which Correspondences to Trust: Confidence-Weighted Event-Camera Localization in LiDAR Maps

Panagiotis Kiousis, Kuangyi Chen, Jun Zhang et al. (+1 more)

Localizing an event camera against a pre-built LiDAR map can be cast as dense optical-flow estimation between a rendered depth view and an event image, followed by a Perspective-n-Point (PnP) solver over the induced 3D-2D correspondences. Existing pipelines rely on geometric consensus during pose estimation, but do not explicitly model the reliability or pose informativeness, i.e., how strongly a correspondence constrains the camera pose, of individual correspondences. We show that the natural way to learn it – using the per-correspondence error to constrain the learning of confidence – suffers from a depth-dependent bias: small pixel errors reside predominantly at large depths and do not lead to high pose informativeness. Instead, in our method (CELL), we learn a per-correspondence confidence end-to-end through the pose, using a differentiable probabilistic PnP whose log-partition term encourages weight configurations that yield a better-constrained pose distribution. The learned confidence is used in three ways: (i) it reweights the flow supervision in a decoupled training scheme that keeps pose gradients out of the flow/edge backbone; (ii) it drives a probabilistic correspondence selection at test time; and (iii) together with the network's edge-probability it weights a final edge-matching refinement. We further design a partial-completion depth representation that adds signal without hallucinating across large gaps. On M3ED and DSEC our full system improves over the LEAR baseline on the majority of the evaluated sequences: it reduces the median translation error by up to 26.9% and the median rotation error by up to 15.8%.
Read the full abstract

All authors Panagiotis Kiousis, Kuangyi Chen, Jun Zhang, Friedrich Fraundorfer

Artificial Intelligence

MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation

Mengdi Liu, Wenjue Chen, Wenyue Chen et al. (+10 more)

Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challenge lies in its inherently open-ended and multi-objective nature, where ideas should balance novelty, plausibility and feasibility. While recent LLM-based approaches have made progress through carefully designed prompts or agent pipelines, they are constrained by predefined, static ideation workflows. To address this limitation, we propose MindFlow, a framework that explicitly formulates ideation as a graph-structured Flow in Mind, which is composed of modular thinking operators and modeled by a probabilistic mind supernet. Given a research topic, a controller dynamically samples thinking flows to generate candidate ideas. This open-ended problem is optimized using a tournament-based relative ranking, enabling the controller to progressively favor higher-quality thinking flows. We further introduce an evaluation protocol that jointly assesses problem finding and problem solving, going beyond title- or abstractonly judgments. Across diverse topics, MindFlow shows its superiority as an explicit, controllable and optimizable research idea innovator.
Read the full abstract

All authors Mengdi Liu, Wenjue Chen, Wenyue Chen, Cheng Yang, Fanqi Kong, Zhangyang Gao, Xiaoxue Cheng, Yiheng Li, Yujian Yuan, Keliang Li, Hong Chang, Shiguang Shan, Chenglin Wu

Systems and Control

From Asymptotic to Designer-Assigned-Time Control: A Review of Stability Notions, Design Mechanisms, and Controller Architectures

Özhan Bingöl

Many control tasks require a target to be reached not only eventually but on time. Finite-, fixed-, predefined-, and prescribed-time control address this need, yet the labels are used loosely: a settling time that grows with the initial condition, a bound that holds for all initial conditions, a deadline chosen by the designer, and a limit attained only at the terminal instant often share one name. This review aims to make such claims comparable. It separates three questions that are often conflated: what temporal property is promised, which feature of the Lyapunov analysis produces it, and which controller architecture carries it into the closed loop. A recurring question is whether a guarantee proven for an idealized loop survives once observers, adaptation, disturbances, actuator limits, and digital implementation are included. The examined studies are therefore audited one by one, recording what each claims, which variable is actually certified, and how the result is validated. The audit shows that estimation and approximation errors often reduce an exact guarantee to a practical one, and that experimental evidence comes mostly from fast electromechanical systems. A scalar benchmark with two complementary tunings shows how much of the apparent difference between methods stems from conservative bounds, initial-condition dependence, and numerical tolerance, and how saturation and sampling can delay or remove a deadline. The review closes with open problems, among them deciding which deadlines a given plant can meet, combining certificates across interconnected subsystems, and preserving a guarantee through implementation.
Read the full abstract

Software Engineering

Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes

Utku Boran Torun, Veli Karakaya and Eray Tüzün

A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow. Manually verifying whether a proposed no-code fix resolves the reported bug takes considerable developer time. This study proposes an automated, execution-based pipeline for evaluating the capability of large language models (LLMs) to generate no-code fixes in a real browser environment. We evaluate 322 no-code fixes generated by the 12 configurations released with the benchmark of a previous study, covering bug reports categorized as Faulty Configuration, Wrong Version, or External System & Dependency. An executor agent applies each fix by following its natural-language instructions, and an issue-specific checker determines whether the reported bug persists. We repeat the pipeline with three executors: two Computer-Use Agents, OpenCUA-72B and Claude Sonnet 5, and one multimodal agentic LLM, Meta's Muse Glimmer. Only 17.6% of the candidate issues could be set up and passed both sanity gates. Across the 322 fixes, 14.6% to 49.7% resolved the bug depending on the executor, and the strongest configuration, Claude Opus 4.6 in the Vanilla pipeline, resolved up to 74.1% of its fixes under Claude Sonnet 5. Changing only the executor shifted a configuration's resolution rate by 38.8% on average, and the three executors reached the same verdict on only 46.9% of the fixes. Compared with human execution, the executors matched the human consensus for 66.1% to 88.1% of the sampled fixes. Even under the best executor, fewer than half of the LLM-generated no-code fixes resolve the reported bug, so such fixes need verification before they reach users. Execution-based verification can provide this, but the measured capability depends strongly on the executor, which evaluations must report and control.
Read the full abstract

Information Theory

Estimation with Quantized Parameter Side-Information

Mathis Wetterwald, Ofer Shayevitz and Michèle Wigger

This paper presents upper and lower bounds on the minimax risk of a parameter estimation problem where the estimator not only observes independent and identically distributed observations but also a quantized version of the parameter, where the quantization has a limitation on the number of levels, but can be optimized otherwise. Our upper and lower bounds have similar decay rates for large number of observation samples and quantization levels.
Read the full abstract

Computation and Language

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Xiaomi LLM-Core Team: Zongming Qiao, Ziyue Hua, Zirui Ou et al. (+145 more)

Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute. Prior to RL, we conduct mid-training on a broad multimodal corpus to provide ample exploration space, and build a solid infrastructure on the pretrained hybrid-SWA architecture to support subsequent scale-up. We scale RL compute along three dimensions: (1) larger batches and higher throughput, with an asynchronous training that consumes 1,568 samples and 2.7-3.7B tokens per step at context lengths of up to 1M; (2) more diverse and complex environments, spanning code, general, visual, and cyber domains under a mixture of agent harnesses; and (3) more grader compute, via groupwise agentic grading that yields more accurate reward signals for long-horizon tasks and steers the model towards shorter, more token-efficient solutions. To keep training stable at scale, we freeze the MoE router and establish a multi-layer defense against reward hacking. We further build infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency. We open-source the training dynamics, RL environments, and RL framework to facilitate reproduction and further research on scaled RL and model self-improvement.
Read the full abstract

All authors Xiaomi LLM-Core Team: Zongming Qiao, Ziyue Hua, Zirui Ou, Zihao Yue, Zihan Jiang, Zhuo Huang, Zhiyang Chen, Zhixian Zheng, Zhipeng Xu, Zhengrui Ma, Yuyang Hu, Yuhang Dong, Yuechen Zhang, Yudong Wang, Yuanxin Liu, Yixin Yang, Yishuo Cai, Yikai Zhao, Yihan Yan, Yifan Zhang, Yifan Song, Xiyu Wei, Xing Zhang, Xin Zhang, Xiaoqian Liu, Xiaodong Ji, Xiangwei Deng, Xueyu Guo, Wenhan Ma, Weimin Xiong, Weikun Wang, Weiji Zhuang, Shuo Liu, Shuhuai Ren, Shuhao Gu, Shimao Chen, Shijie Cao, Shihua Yu, Shicheng Li, Shengjie Zhou, Shaolei Zhang, Rang Li, Qiying Wang, Qingkai Fang, Qianli Chen, Minzheng Wang, Liwen Wang, Linli Yao, Linghao Zhang, Liangyu Cheng, Liang Zhao, Lei Li, Jinhao Dong, Jinyu Xiang, Jianyu Wei, Jiangshan Duo, Huaqiu Liu, Huanjie Fan, Hongyi Guan, Hongshen Xu, Hao Tian, Hanyu Li, Hailin Zhang, Gang Wang, Fuli Luo, Feng Wei, Dong Zhang, Dawei Zhu, Chiheng Lou, Chenhong He, Chenhao He, Chenghua Liu, Bowen Ye, Bowen Shen, Boshen Xu, Bo Yang, Bingquan Xia, Bangjun Xiao, Baixuan Xu, Zhouxiang Mao, Zhiyang Zhang, Zhixiang Xu, Zhenru Lin, Zhengju Tang, Zhaojun Huang, Yuzhe Weng, Yuxing Xiang, Yuxiao Li, Yuheng Yang, Yuhang Wang, Yuchen Liu, Yuanyuan Tian, Yuanliang Dong, Yu Cheng, Yongzhe He, Yongshun Liang, Yong Wang, Yiyan Wang, Yitian Gong, Yijie Zhang, Yanshu Xin, Xun Zhang, Xingjian Zhao, Wenyu Yang, Wenshan Huang, Wenhao Li, Tingwei Huang, Tianyu Yu, Tianyang Lu, Taoyu Yang, Sinan Du, Shutong Tian, Shulin Du, Shengfan Wang, Shanchuan Fang, Qihao Zhang, Qibin Yang, Qian Yu, Qian Tu, Pengrong Xie, Peipei Wang, Peidian Li, Minkun Guo, Mingchen Shao, Luohan Gao, Lijie Wang, Liang Shi, Kaiqi Chen, Kaiming Liu, Kaifei Wang, Kai Yang, Jinlong Xue, Jiechen Zhang, Jiaxuan Liu, Hongxu An, Hao Peng, Hanglong Lü, Guonan Wang, Feiyu Yang, Fanyu Cao, Fangyue Liu, Fan Cui, Cong Wang, Chun Chen, Chenxu Bai, Chengxuan Zhu, Chenghua Wang, Boyi Zeng