Peer Revenue Now accepting positions

Papers

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

Computer Science

cs Watch Computer Science

Thursday 8 October

Artificial Intelligence

Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review

Rachel S.Y. Teo, Yutaro Yamada, Shashank Kotyan et al. (+2 more)

The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality and increasing reviewer workload. Large language models (LLMs) have been proposed as automated review assistants, yet their evaluation has focused largely on imitating human-written reviews rather than supporting the core functions of peer review. Here, we introduce a verification-centric perspective on LLM-assisted peer review, emphasizing error detection as a critical and resource-intensive task. We present a scalable benchmark that evaluates review systems' ability to identify logical contradictions, constructed through synthetic insertion of errors into conference papers, yielding unambiguous evaluation targets and enabling systematic comparison. We further propose a Multi-Layered Review (MLR) framework that prioritizes detailed manuscript comprehension before review generation, aligning more closely with human reviewing practices while improving token efficiency. Across evaluations, our approach demonstrates strong alignment with human review scores, achieves high error detection performance, and provides complementary perspectives on reviewer focus. These improvements can be attributed to both the choice of the underlying LLM and the design of our system. At the same time, we corroborate persistent vulnerabilities to adversarial manipulation, underscoring the need for robustness in automated review systems. Our findings highlight the importance of rigorous, error-focused evaluation to guide responsible deployment of LLM-based tools in peer review and other critical scientific workflows.
Read the full abstract

All authors Rachel S.Y. Teo, Yutaro Yamada, Shashank Kotyan, Yuki Imajuku, Tarin Clanuwat

Computer Vision

Contrast Enhancement or Noise Reduction? On Improving Cervical Cancer Classification

Ach Khozaimi and Ulfatun Nahdhiyah

Purpose: Cervical cancer is one of the leading causes of mortality worldwide. Deep learning has shown promising performance in medical image classification. The influence of image preprocessing algorithms on classification performance remains insufficiently investigated in the literature. This research aims to evaluate the impact of image preprocessing algorithms on the performance of CNNs for Pap smear image classification. Methods: Three CNN architectures (ResNet-34, MobileNet-V2, and DenseNet-121) were trained and evaluated using the SIPaKMeD dataset. Two preprocessing algorithms were applied: the PMD filter for noise reduction and CLAHE for contrast enhancement. The model performance was assessed using a confusion matrix. Results: Preprocessing improved the classification performance of all models. CLAHE significantly increased the accuracy of ResNet-34 from 76.73% to 84.16% and DenseNet-121 from 76.73% to 84.16%. The PMD filter yielded limited improvement and slightly reduced the MobileNet-V2 performance. Novelty: This research provides a systematic comparison of contrast enhancement and noise reduction techniques across CNN architectures. This research demonstrates that contrast enhancement is more effective than noise reduction in improving CNN performance. The research provides new pipelines for improving cervical cancer classification.
Read the full abstract

Machine Learning

DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks

Xinfei Wang, Shanchen Pang, Chenhao Zhang et al. (+5 more)

Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing methods mainly focus on algorithmic optimization, with less emphasis on data-level improvements to enhance learning ability and generalization performance. This paper, from a data perspective, reveals three key bottlenecks that limit Offline MTRL performance:(i) ineffective utilization of prompts length under diverse task complexities, and (ii) semantic irrelevance of randomly sampled prompt segments, (iii) misleading supervision induced by fragmented and discontinuous trajectories. To address these challenges, we propose DaCe-DT, a robust offline MTRL framework designed to be insensitive to heterogeneous task complexities and data quality, featuring length-gated prompt masking (LGPM), retrieval-augmented prompt construction (RAPC), and value-adaptive return calibration (VARC). Together, these mechanisms enable DaCe-DT to deliver data-centric prompt adaptation and trajectory refinement, resulting in robust multi-task generalization and stable policy learning amid heterogeneous offline data and tasks. Experimental results on Meta-World show that DaCe-DT consistently outperforms state-of-the-art methods, achieving an average improvement of 11.73% on optimal datasets and an improvement of 13.34% on suboptimal datasets, demonstrating its effectiveness in learning stably from imperfect data and improving overall multi-task performance.
Read the full abstract

All authors Xinfei Wang, Shanchen Pang, Chenhao Zhang, Shudong Wang, Wenhao Ji, Haiyuan Gui, Meng Han, Xiaojian Liao

Information Theory · Cross-listed from stat.ML

A General $\widetilde{\Omega}(\sqrt{T \gamma_T})$ Lower Bound for Kernel Bandits

Chenkai Ma and Jonathan Scarlett

The kernel bandit problem consists of sequentially optimizing an unknown function with noisy feedback, where the function has bounded norm in a given Reproducing Kernel Hilbert Space (RKHS). A central quantity in the regret analysis of kernel bandits is the maximum information gain $\gamma_T$. In particular, the best existing upper bounds scale as $\sqrt{T\gamma_T}$ up to log factors, and nearly-matching lower bounds have been derived for specific kernels such as squared exponential and Matérn. However, lower bounds for general kernels are lacking, thus making it unclear in what generality the upper bounds are near-optimal. In this paper, we establish a general $\Omega(\sqrt{T\gamma_T/\log T})$ minimax regret lower bound for non-constant continuous kernels on compact domains, establishing near-optimality (within log factors) in a very general sense. We show that the log factor appearing in this bound is unavoidable in general, but that it can be removed under certain conditions. Among other things, our findings imply that the minimax-optimal scaling is exactly $\Theta(\sqrt{T\gamma_T})$ (i.e., within constant factors) for the Matérn-$\nu$ kernel with $\nu \in (0,2)$, $\gamma$-exponential kernel with $\gamma \in (0,2)$, and certain piecewise-polynomial kernels.
Read the full abstract

Machine Learning

Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning

Lingxiang Wang, Hainan Zhang, Liang Pang et al. (+2 more)

Domain-specific continual adaptation of LLMs risks catastrophic forgetting, creating a fundamental tension between acquiring new capabilities and preserving those learned during pretraining. PEFT mitigates this problem by restricting the number of trainable parameters, but existing methods lack a principled unit for deciding where plasticity should be allocated and stability should be preserved. We identify the singular-vector channel as a natural unit for managing this trade-off. Each channel represents an input-output transformation, which can be updated to acquire new knowledge or fixed to preserve pretrained capabilities. Based on this perspective, we introduce SVC, a parameter-efficient continual-learning method that selectively updates Singular-Vector Channels. Before fine-tuning, SVC uses domain-specific data to estimate each channel's adaptation benefit and a fixed public general-domain corpus only as a history activation proxy for estimating forgetting cost. It then adaptively selects trainable channels based on these scores via knee-based cost screening, Pareto-front filtering, and Otsu thresholding. Experimental results across four LLM families and eight downstream tasks show that SVC better preserves pretrained capabilities while achieving strong downstream performance relative to existing PEFT baselines. Further analysis of channel scoring and selection demonstrates that selective plasticity at the singular-vector-channel level enables effective continual LLM adaptation.
Read the full abstract

All authors Lingxiang Wang, Hainan Zhang, Liang Pang, Hongwei Zheng, Zhiming Zheng

Machine Learning

Optimally Pacing Budget Spending and Learning

Mark Braverman, Jingyi Liu, Jieming Mao et al. (+2 more)

We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting. In particular, given any class of $F$ experts and a candidate budget pacing schedule, we provide a full-information algorithm which obtains regret $O(D \sqrt{\log F}+ \sqrt{T\log F})$ against all experts whose cumulative spending stays within distance $D$ of this schedule, matching lower bounds established by Braverman et al. (2025). We additionally show that our technique extends to various problems in online resource allocation, where the learner gets to see the rewards and costs of the current options available to them, and establish $O(D\sqrt{\log F})$ regret bounds when fractional allocation is allowed. This is the first algorithm we are aware of which can achieve $o(\sqrt{T})$ guarantees for such tasks.
Read the full abstract

All authors Mark Braverman, Jingyi Liu, Jieming Mao, Jon Schneider, Eric Xue

Software Engineering

IRONPROOF: COBOL-to-Python Transpilation with SMT-Based Equivalence Checking

Dominik Blain

Translating COBOL to a modern language can change what a program computes, and LLM translations carry no guarantee of equivalence. We present IRONPROOF, which parses COBOL into an intermediate representation, generates Python, encodes both as Z3 formulas over shared inputs, and emits either a machine-checkable equivalence certificate (UNSAT) or a counterexample (SAT). On 2,345 COBOL files (GnuCOBOL tests, NIST CCVS85, open-source collections, and programs we generated or wrote), 782 enter the checking path: 606 (77.5%) are proved equivalent, 101 are partially verified, none is refuted, and 75 fail inside our pipeline and stay in the denominator. On independently authored programs the rate is 52.6% (153 of 291), against 92.3% on programs we wrote. Of the 153 independent proofs, 37 cover a single execution of a program that reads input the encoder does not model, and across all 606 proofs only 14 quantify over an input that a proved output depends on. On two public business-application corpora (AWS CardDemo and IBM GenApp), the encoder models no program end to end. An April 2026 LLM-only baseline failed on 54 of 94 independently authored programs, counting translations our encoder could not verify. PIC-bounded overflow detection flags an out-of-range output in 22.1% of the programs it can analyze, an upper bound. An earlier confrontation with GnuCOBOL 3.2.0 found 24 of 49 executable independent proofs disagreeing with the runtime on a variable in the proof's domain. A proof establishes that the generated Python computes what our intermediate representation says the COBOL computes, not equivalence to a COBOL implementation.
Read the full abstract

Robotics

Towards Path-Creative Navigation: Robot Navigation through Embodied Interaction

Haoyu Xi, Siwei Cheng, Xiangyuan Liu et al. (+2 more)

Autonomous navigation in cluttered and constrained environments typically assumes a fixed environment and searches only for paths within existing free space. However, a route can be blocked by an articulated structure, a movable object, or a pedestrian, and reaching the goal may therefore require appropriate embodied interaction with the environment. This paper formulates Path-Creative Navigation (PCN), a navigation paradigm in which the robot recovers free space by coordinating locomotion and embodied interaction, and addresses one class of PCN tasks with a mapless framework. The vision-LiDAR-odometry framework integrates local observations, obstacle geometry, and robot-state estimates through a unified navigation system, providing stable semantic and geometric information for navigation and interaction. The traversability-aware decision method utilizes visual and LiDAR distance information to determine whether a blockage is actionable and whether it can be safely bypassed, enabling the robot to interact only when necessary while supporting articulated structure pushing, movable object pushing, obstacle avoidance, and pedestrian requests. We design simulation scenarios and evaluate different methods in both simulation and two real-world tasks that cannot be completed by conventional navigation alone without embodied interaction. These results demonstrate that our framework achieves higher task completion than the baseline methods by coordinating navigation and interaction in cluttered and constrained environments.
Read the full abstract

All authors Haoyu Xi, Siwei Cheng, Xiangyuan Liu, Brenda Li, Wei Zhang

Computer Vision

No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping

Yu Han, Dejan Markovic, Alexander Richard et al. (+4 more)

Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents. And it must run online: each frame emitted from audio observed up to the current time, at interactive rates. Recent progress is dominated by diffusion models, which need many network evaluations per sample and are therefore a poor fit for streaming. We argue the cost is unnecessary in this domain. Audio-conditioned facial motion occupies a comparatively low-dimensional manifold, a regime where a single-pass GAN suffices. The obstacle is not capacity but stochastic structure. We show that a causal, time-invariant generator driven by i.i.d. noise cannot suppress its output spectrum over a band without collapsing its per-step innovation. We proposed FaceGAN, which dissolved the limitation by shaping the noise pathway acausally. Because the driving noise is synthetic, its future can be sampled now, so the audio-to-expression path stays causal, and the model supports fully causal operation. FaceGAN emits expression and head pose in a single forward pass per frame and matches or outperforms state-of-art approaches in generation quality. Being feed-forward with bounded attention windows, it generates indefinitely without drift.
Read the full abstract

All authors Yu Han, Dejan Markovic, Alexander Richard, Wojciech Zielonka, Akshay Venkatesh, Cheng-hsin Wuu, Michael Zollhoefer

Computation and Language

Clinician use of language models diverges from how the models are evaluated

Krithik Vishwanath, Haitong Lin, Anton Alyakin et al. (+19 more)

Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchmark scores, most of them derived from examination questions or curated cases. A benchmark predicts performance in deployment only to the extent that its items resemble real use, yet whether benchmarks reflect the work these systems receive has rarely been measured. Here we analyze 127,833 queries sent by 6,342 physicians, advanced practice providers and nurses in 35 specialties to an institutional assistant during an eight-month roll-out. We characterize each query with RCQ-Map, a clinician-validated framework grounded in taxonomies of clinical questions and of LLM evaluation, which records its task, intent, answerability, missing information and potential harm. Documentation and administration (36.2%) and knowledge retrieval (28.9%) made up nearly two-thirds of use, and diagnosis 3.7%; more than a third of queries could not be answered well as posed. Applying RCQ-Map to 58 public benchmarks drawn from major evaluation suites and frontier model reports, which we assemble into the Clinical AI Benchmark Atlas, showed that the median benchmark contained no documentation requests and shared 31% of the task mix of real use, less than an even spread across task categories would. Benchmarks in suites designed to resemble clinical practice were individually no closer to real use than those used in frontier model reports. Benchmark scores therefore say little about how clinical AI performs on most of the work it is actually given, and evaluation should be matched to real clinical use.
Read the full abstract

All authors Krithik Vishwanath, Haitong Lin, Anton Alyakin, Jin Vivian Lee, D. Brock Hewitt, Jie J. Yao, William Robert Small, Hammad A. Khan, Cordelia Orillac, Aakaash Varma, Brandon Ye, Daniel Alexander Alber, Gustavo Stolovitzky, Batia Wiesenfeld, Oded Nov, Wei Wu, Kang Zhang, Yindalon Aphinyanaphongs, Tim Requarth, Eric Karl Oermann, The International Digital Twin Consortium in Healthcare, Medicine

Computer Vision

Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

Deepak Sridhar, Yi Li, Kartikeya Bhardwaj et al. (+7 more)

Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classes, domains, or compositions of tasks. In this paper, we introduce a Diffusion Meta-Prompt (DMP) model , a framework that models the distribution of learned prompts using diffusion models. Given a repository of previously learned prompts, DMP is trained and sampled without access to the original task examples or task losses, and synthesizes new prompts conditioned on natural language task descriptions. To improve the sampling stability, we introduce a test-time steering strategy for DMP, which uses the best training-selected prompt in the repository as a latent anchor during diffusion sampling, without retraining the DMP or accessing test classes. DMP improves generalization across classification, retrieval and text-to-image generation tasks, supports concept composition and negative prompting without explicit training. It reduces storage and inference costs by over 90% compared to prompt retrieval methods. For composite classification, DMP achieves upto 2.0% average gain over prior meta-learning methods across 55 pairs of datasets with gains as high as 8.5% on specific pairs such as Eurosat and Flowers. DMP also enhances cross-task generalization with ~2-9% improvement for hierarchical classification task. We further provide a theoretical guarantee bounding the expected task loss of prompts sampled from a DMP. Code is available: https://github.com/DeepakSridhar/dmp
Read the full abstract

All authors Deepak Sridhar, Yi Li, Kartikeya Bhardwaj, Shuangjun Liu, Taotao Jing, Yuan Li, Shuai Zhang, Jiancheng Lyu, Dashan Gao, Nuno Vasconcelos

Machine Learning

CityDeploy-Bench: Benchmarking Physics-Grounded Spatial Set Planning for Multi-Transmitter Network Deployment

Chenyang Yuan and Xiaoyuan Cheng

Automating city-scale wireless deployment remains challenging under complex urban propagation and network-wide interference. We introduce CityDeploy-Bench, a benchmark that reframes multi-transmitter deployment as physics-grounded spatial set planning under a unified ray-tracing verifier. The benchmark separates utility representation from planning dynamics, enabling controlled comparison between direct scalar rewards, relational models, and higher-order interaction structures across diverse planners. Our experiments reveal a clear transition in planning behavior as physical coupling grows. Deployment quality becomes increasingly dependent on whether the learned utility captures collective transmitter interactions, whereas stronger search alone cannot compensate for missing relational structure. This establishes multi-transmitter deployment as a coordination problem over physically interacting sets rather than a collection of independent spatial decisions. We release CityDeploy-Data and the benchmark framework as a reproducible testbed for research linking decision learning with physically grounded wireless network design.
Read the full abstract

Machine Learning

Measuring and Mitigating Solution Mode Collapse in RLVR

Liv G. d'Aliberti, Marwa Abdulhai, Sofiia Druchyna et al. (+2 more)

A language model (LM) can usually answer the same question in more than one way, but reinforcement learning with verifiable rewards (RLVR) is indifferent to which correct answer a model produces. A solution will earn the same reward whether it is the thousandth copy of a familiar answer or one the model has never produced before. Yet, there is potential value in having the model retain multiple correct solutions as it is trained. For instance, multiple modes may give users a choice and provide problem-solving strategies that improve overall model performance. Here, we introduce ModeBench, a benchmark of multi-solution tasks in which the verifier returns both correctness and mode discovered. We then use ModeBench to measure how solution diversity changes under RLVR post-training. We find that RLVR post-training concentrates probability onto fewer correct modes even as accuracy holds or improves, and moreover, that frontier models are already highly concentrated. We then introduce our solution, Re:Max, which stores one verified example per discovered mode in a replay buffer and trains on those stored modes uniformly. A solution found once is, therefore, practiced as often as one found repeatedly. Across three model scales, two RL objectives, and harder task constructions, replay improves both how often a policy succeeds and how many different ways it can succeed.
Read the full abstract

All authors Liv G. d'Aliberti, Marwa Abdulhai, Sofiia Druchyna, Peter Henderson, Manoel Horta Ribeiro

Machine Learning

Emergent Inverse-Depth Scaling From Nonlinearity In Attention

Zirui Peng, Yizhou Liu, Ziming Liu et al. (+1 more)

Scaling laws describe power-law improvements in model performance with dataset size and parameter count, yet their underlying mechanisms are not fully understood. To explain the parameter count scaling, existing theory posits power-law scaling with model depth. In linear-attention models, this scaling is tied to a power-law data spectrum: unable to selectively attend to relevant tokens, these models learn according to global spectral strength, with stronger directions learned before weaker ones. Large language models, however, can be strongly nonlinear. Here, we show that nonlinear attention yields inverse-depth decay of loss across all tested data spectra. Nonlinearity enables attention to focus selectively on relevant tokens, allowing strong and weak spectral directions to be learned in parallel. Similar focusing across layers motivates a connection to the central limit theorem: shared error across layers sets the loss plateau, while aggregation turns layer-specific differences into continued gains with depth. Our findings suggest that depth scaling may arise from nonlinearity in attention, which allows large language models to focus locally and may make the global covariance structure less relevant.
Read the full abstract

All authors Zirui Peng, Yizhou Liu, Ziming Liu, Jeff Gore

Computer Vision

AffordDrive3D: Affordance-Aware World-Action Modeling with Spatial Understanding

Tianhui Cai, Xinglong Sun, Chao Fang et al. (+6 more)

World-action models have recently improved autonomous driving by jointly learning future scene prediction and trajectory generation. Most existing approaches model the future primarily through RGB appearance, and recent works have begun to incorporate geometric prediction to improve spatial understanding. However, dense geometry describes the spatial layout of the entire scene without indicating which parts are most relevant to the ego vehicle's action. For driving, the model must also identify and anticipate where it can safely move and which regions may pose collision risks. Jointly modeling action-relevant regions and future geometry can provide the policy with both driving-relevant cues and their corresponding spatial structure. We therefore propose AffordDrive3D, an affordance- and geometry-aware world-action model that jointly learns future action-relevant regions and spatial structure. In order to capture the scene semantics and driving context needed for driving affordance prediction, we build AffordDrive3D on a VLM backbone to forecast drivable areas and collision-critical regions that directly affect ego motion, while predicting future geometry from RGB world-model latents. On NAVSIM, AffordDrive3D achieves state-of-the-art performance with 91.3 PDMS and 89.9 EPDMS, demonstrating the effectiveness of jointly modeling future affordances and geometry for trajectory planning. Project Page: https://afforddrive3d.github.io/
Read the full abstract

All authors Tianhui Cai, Xinglong Sun, Chao Fang, Zhenxin Li, Rui Song, Jose M. Alvarez, Yunxiang Mao, Jiaqi Ma, Langechuan Liu

Systems and Control

A Latent Space Optimization Approach for Symbolic Discovery of Dynamical Models

Tongjia Liu and Ilias Mitrai

In this paper, we propose a hybrid latent-space Bayesian Optimization (BO) and global optimization framework for solving symbolic regression tasks to discover dynamical models from data. Symbolic regression can discover equations from data without fixing the functional form of the expression a priori. The proposed framework uses the fact that if the functional form of the expression is fixed, the symbolic regression task reduces to a parameter estimation problem, which must be solved to global optimality. Motivated by this structure, first, we train a VAE to map the discrete space of expression trees into a continuous latent space. Then, we use BO to search this latent space while assessing a candidate expression's prediction error by solving the parameter estimation problem to global optimality. We evaluate our framework across two case studies: static reaction rate law discovery and dynamic concentration identification in a continuous stirred-tank reactor (CSTR). The results show that our framework identifies the true governing equations faster than MINLP formulations without solver timeouts and achieves higher sample efficiency than evolutionary baselines under tight evaluation budgets.
Read the full abstract

Computer Vision

Refine Connections, Close the Gap: A Reliable Enhancement Framework for Driving Scene Topology

Xiaoqi Wang, Dingyi Zhuang, David Paz et al. (+6 more)

In autonomous driving, understanding scene topology - the connectivity between lanes and traffic elements - is critical for safe path planning and motion control. While current methods excel at detecting individual map elements, their connectivity reasoning often falls short of its theoretical potential, leaving a significant performance gap relative to the theoretical upper-bound achievable given the underlying detections. Furthermore, the decision-ready topology graphs passed to downstream tasks often remain unreliable. Current approaches typically derive connectivity by thresholding continuous topology scores; however, these scores often fail to reflect the true logical likelihood of connectivity, resulting in false positives or missing connections. Existing benchmarks further overlook this issue by primarily evaluating continuous metrics, rather than assessing the discrete connectivity required for decision-making. To bridge these gaps, we propose TopoEnhance, a novel topology enhancement framework designed to unlock the latent potential of existing methods and improve the reliability of decision-ready topology. We formulate topology enhancement as a denoising-based reconstruction process, where the model learns to recover structural consistency from stochastically corrupted ground-truth graphs. This formulation enables the model to resolve logical inconsistencies and rectify unreliable connections, producing robust discrete topology graphs that closely approach theoretical maximum performance. Extensive experiments across different baselines show that TopoEnhance consistently improves both continuous topology metrics (TOP score), and discrete connectivity measured by our adapted Topology Jaccard Similarity (TJS) metric. As a flexible, source-agnostic framework, TopoEnhance delivers substantial gains across diverse state-of-the-art baselines without requiring retraining.
Read the full abstract

All authors Xiaoqi Wang, Dingyi Zhuang, David Paz, Wenbin He, Yucai Bai, Peng Zhou, Rui Zhang, Jinhua Zhao, Liu Ren

Computer Vision

Learning What to Trust in Multimodal Learning under Noisy Supervision

Jiashuo Zou and Xiaobo Xia

Multimodal classification processes and relates information from multiple modalities to achieve more accurate predictions. However, existing methods typically rely on high-quality ground-truth labels, which are difficult to obtain in real-world scenarios. While sample-selection methods for learning with noisy labels aim to identify correctly labeled examples from noisy data, traditional methods primarily focus on unimodal settings and fail to exploit multimodal information fully. This motivates us to build a more reliable noise detector in multimodal learning. To this end, we theoretically analyze the relationship between representation structure and noise detection capability. Based on this analysis, we propose REFINE, which is a multimodal label-noise detection framework that jointly uses fused and unimodal representations for label-noise detection. Specifically, REFINE constructs discriminative eigenvectors through discriminative analysis of the target and background classes and selects trusted representation spaces with better noise detection capability for each class. Within each trusted space, REFINE measures the alignment between each instance representation and the discriminative eigenvectors. It then combines the subsets selected from these spaces. The combined set provides cleaner supervision for updating the multimodal classifier, thereby reducing the influence of mislabeled examples during training and improving model generalization. Extensive experiments across diverse tasks demonstrate REFINE's superiority compared to baseline methods. The source code will be publicly available.
Read the full abstract

Robotics

A Reconfigurable Fabric Based Pneumatic Actuator with Button Fastened Constraint Modules for Multi Mode Actuation

Kentaro Kimura, Hiroki Ishizuka, Yusuke Sakaue et al. (+2 more)

Soft pneumatic actuators are widely used in soft robotics. However, their actuation modes are typically fixed by internal chamber designs or reinforcements, making post fabrication reconfiguration difficult. This paper presents a reconfigurable fabric-based pneumatic actuator that enables rapid, tool free, and reusable switching among multiple actuation modes by attaching constraint fabric modules to a buttoned textile sleeve. By rearranging low-stretch constraint parts on a single actuator body, the proposed system realizes four actuation modes isotropic expansion, contraction, bending, and twisting without redesigning or disassembling the actuator.We further introduce an attachable capacitive fabric-based tactile sensor module that can be mounted at arbitrary locations on the actuator surface for task dependent contact sensing. Experiments demonstrated an elongation ratio of 1.2, a maximum bending angle of approximately 60 degrees, and a twisting angle of approximately 90 degrees at 24 kPa, while achieving blocking forces exceeding 10 N across all modes. The tactile sensor exhibited a monotonic, force-dependent increase in capacitance with low hysteresis (approximately 12%) and stable cyclic responses under preload. Finally, we constructed soft robotic arms composed of multiple actuators and demonstrated in situ motion reconfiguration for grasping by changing the attached constraint patterns. These results indicate that the proposed modular constraint and sensing framework improves the functional adaptability of fabric-based soft robots while preserving a simple, robust actuator structure.
Read the full abstract

All authors Kentaro Kimura, Hiroki Ishizuka, Yusuke Sakaue, Sei Ikeda, Osamu Oshiro

Game Theory

Optimal Multi-Item Auctions with I.I.D. Values

Boyu Liu, Zhengyang Liu and Zihe Wang

We study revenue-maximizing multi-item auctions under dominant-strategy incentive compatibility (DSIC) and ex-post individual rationality. Buyers have additive valuations, and all item values are independent draws from a common finite distribution. For every two-point distribution and arbitrary numbers of buyers and items, we give an explicit deterministic mechanism that is optimal among all randomized mechanisms satisfying these requirements, together with a polynomial-time algorithm for computing the optimal expected revenue. For general finite-support distributions, computing the exact optimal revenue is $\#\mathrm P$-hard, both for a single buyer with an arbitrary number of items and for two items with an arbitrary number of buyers. For a single buyer, we also establish hardness of computing an optimal mechanism. Building on prior work, we also obtain exact and approximate algorithms under different parameter restrictions. Exact polynomial-time optimization is possible whenever any two of the buyer count, item count, and support size are fixed. When only the item count is fixed, a polynomial-time approximation scheme constructs a mechanism with expected revenue at least a $1-\varepsilon$ fraction of the optimum for every fixed $0<\varepsilon<1$. All these algorithms satisfy DSIC and ex-post individual rationality.
Read the full abstract

Artificial Intelligence

AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks

Xing Han Lù, Dheeraj Vattikonda, Sina Hajimiri et al. (+7 more)

Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without human involvement. Despite their flexibility, their reliability on long tasks spanning multiple applications remains unclear. A trajectory, composed of long sequences of screenshots and actions, may appear complete, but in reality violates constraints from the instruction or introduces an unwanted side effect. To identify these errors, a judge needs to examine the trajectory with respect to the user's instruction. To this end, we introduce AgentHorizon, a benchmark of 1,373 computer-use tasks (instruction-trajectory pairs) drawn from 166 hours of human-recorded trajectories spanning three operating systems. By recording trajectories for closely related instructions, we can construct negative tasks by swapping the instructions. This paired design evaluates judges on their ability to distinguish a successful trajectory from one that completed a similar (but incompatible) request. We release the benchmark under three splits: a frontier split, AgentHorizon (AH), a simplified split, AgentHorizon-Simple (AH-S), and a development split, AgentHorizon-Development (AH-D). We further evaluate eleven judges by (1) directly passing the full trajectory (with up to 300 screenshots and actions), and (2) using them as coding agents across five agent harnesses. We find that our best agentic judge, GPT-5.5, achieves 80.9% balanced accuracy on the AH subset. We find that tool-use improves certain models but results in worse performance for open-weight models, and that judges differ drastically in their ability to accept a valid trajectory and reject failed ones. Our findings highlight the need for judges that are capable of locating and verifying often hidden evidence that a task was properly completed inside long interaction histories.
Read the full abstract

All authors Xing Han Lù, Dheeraj Vattikonda, Sina Hajimiri, Fatemeh Pesaran Zadeh, Parishad BehnamGhader, Ghazwa Darwiche, Amirhossein Kazemnejad, Christopher Pal, Alexandre Drouin, Siva Reddy

Computer Vision

SatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique Image

Jiarui Zeng, Kun Shi, Chiman Vong et al. (+1 more)

We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from a single oblique image or a short multi-view clip. Existing cross-view geo-localization methods retrieve the most similar satellite tile from a gallery and report Recall@K, but retrieval depends on gallery sampling, provides no heading estimate, and returns a tile index rather than a continuous coordinate. We propose SatFix, a feed-forward UAV–satellite localization framework built on VGGT-$\Omega$. Satellite-grid features act as queries that aggregate UAV visual evidence, and two lightweight heads regress a 3-DoF pose in the satellite-map frame: continuous 2D position and heading. SatFix requires no explicit 3D map, rendered bird's-eye image, auxiliary sensor, or test-time pose alignment. A single model supports both single- and multi-view inputs, with trajectory constraints used during multi-view training. For metric evaluation, we introduce University-Metric, where satellite imagery is re-collected over a region up to 10.7$\times$ longer on a side (about 114$\times$ the ground area) than the original University-1652 tiles, with continuous position and heading labels for the original UAV tours. With one UAV view, SatFix localizes 52.08% of test frames within 50 m and 17.34% within 10 m, with median position and heading errors of 45.66 m and $20.81^\circ$, respectively. Inference takes under 0.1 s per single-view query on an NVIDIA RTX 4090. With nine UAV views, the median position error falls to 21.96 m and the median heading error to $8.73^\circ$. Compared with a fine-tuned VGGT-$\Omega$ baseline, SatFix reduces median position error by 34.0% and nine-view median heading error from $25.43^\circ$ to $8.73^\circ$.
Read the full abstract

All authors Jiarui Zeng, Kun Shi, Chiman Vong, Zhedong Zheng

Information Theory · Cross-listed from cond-mat.stat-mech

A general framework for crystallization in maximal hard-core models

Alexander Barg, Qidong He and Geyang Wang

We study general maximal hard-core models on periodic lattice-type graphs. While for standard models, phase coexistence may arise for high activity, for maximal models this behavior may occur also for sufficiently low activity values. Relying on the concept of volume allocation, we develop a unified set of assumptions that imply the Peierls condition, a convergent cluster expansion for the partition function, and hence the conclusions of Pirogov-Sinai theory for this class of models. We further check these assumptions for a number of examples including standard lattice-type periodic graphs, proving crystallization for both high and low activity. We also derive estimates for the values of activity that bound the phase coexistence regions in the phase diagram, rewriting for this purpose the proof of a technical result in the derivation of Pirogov-Sinai theory.
Read the full abstract

Software Engineering

Following Breadcrumbs in Code: What Accidentally Committed Ad-Hoc Logs Reveal about Developer Comprehension

Yi-Hung Chou, Boyuan Jiang, Vidit Jain et al. (+3 more)

Developers frequently insert temporary print or log statements, known as **ad-hoc logs**, to better understand program behavior at runtime, particularly when facing unexpected issues or complex control flows. Despite being a nearly universal practice, systematic study has been limited because these logs are ephemeral: they usually remain only in local environments and are removed before code is committed, making them difficult to capture. In this work, we addressed this challenge by mining accidental commits where developers unintentionally left ad-hoc logs and later deleted them, and by analyzing live-streamed programming sessions to observe their use in practice. Using these methods, we constructed a large dataset across three major programming languages (Java, JavaScript, and Python), enabling the large-scale investigation of logging practices. Our analysis reveals both common and language-specific patterns in where and how developers rely on ad-hoc logs. Across languages, ad-hoc logs tend to appear in program regions that are harder to reason about at runtime. We also identify distinctive language-level patterns, such as frequent use in asynchronous and callback functions in JavaScript and in thread-related classes in Java. In addition, functions containing ad-hoc logs generally have higher cyclomatic complexity than the overall function population. Production logs show a similar association, consistent with logging serving as a means of observing runtime behavior in structurally complex functions. Together, these findings provide empirical insight into developers' runtime comprehension practices and offer a valuable dataset for researchers and tool builders seeking to better support debugging and logging.
Read the full abstract

All authors Yi-Hung Chou, Boyuan Jiang, Vidit Jain, Yiyang Min, April Yi Wang, James A. Jones

Computer Vision

Rendering-Free Lookahead for Question-Guided Active Vision

Koya Sakamoto, Daichi Azuma, Shuhei Kurita et al. (+4 more)

Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determining what is inside a box may require raising the camera and looking down into it. For viewpoint-dependent question answering, the challenge is to select camera motions that expose the visual evidence needed to answer the question. Although vision-language models (VLMs) can interpret observed images, selecting such motions requires anticipating the usefulness of unseen views. We quantify this usefulness as answerability, a VLM's estimate that a view suffices to answer the question, and present Rendering-Free Lookahead (RFL), a viewpoint-selection policy that ranks candidate camera motions by predicted future answerability. RFL transfers visual lookahead from deployment to offline training. At training, a privileged teacher renders candidate future views in 3D Gaussian Splatting (3DGS) scenes and uses a frozen VLM to compute one- and two-step answerability targets. Through two-stage distillation, a student learns to predict these action values from the question, recent visual observations, and a candidate camera motion. At deployment, RFL uses these predicted values to select camera motions without rendering future views. On 377 E3VS-Bench test episodes in unseen environments, RFL improves the mean judge score by 43% over a direct-action baseline using the same VLM. These results support learning camera-control policies from privileged visual lookahead for viewpoint-dependent question answering.
Read the full abstract

All authors Koya Sakamoto, Daichi Azuma, Shuhei Kurita, Naoya Chiba, Yusuke Iwasawa, Yutaka Matsuo, Taiki Miyanishi

Computer Vision

Transforming Image Editors into Video Editors

Feng Wang, Zijie Li, Ceyuan Yang et al. (+2 more)

Recent image editing systems have achieved impressive semantic understanding, visual fidelity, and instruction-following ability, while video editing remains substantially more difficult and costly. In this paper, we present a simple alternative to end-to-end video editing: instead of training a monolithic video editor, we transform a strong image editor into a video editor through anchor-based generation. Our key insight is that video editing can be decomposed into two subproblems: editing a sparse set of keyframes and propagating those edits across time. Based on this observation, we propose Anchor-based Video Editing (AVE), a two-stage framework in which a powerful image editor first performs composed editing on selected keyframes, and a motion-guided image-to-video diffusion model then generates the final video by treating the edited keyframes as fixed anchors. This design directly inherits the strengths of modern image editors while avoiding expensive end-to-end video editing training. Experiments on IVEBench and VIE-Bench show that AVE achieves strong performance in instruction following, temporal consistency, and content fidelity. Further ablations reveal that final video editing quality is strongly correlated with the quality of the image editor, suggesting that future progress in video editing may come from stronger image editing foundations and lightweight transfer to video. Code is available at https://github.com/wangf3014/AVE.
Read the full abstract

All authors Feng Wang, Zijie Li, Ceyuan Yang, Alan Yuille, Peng Wang

Computation and Language

FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing

Sota Sugawara and Yukihiko Okada

Multiple institutions may each hold their own private knowledge edits and wish to integrate them into a single large language model without sharing raw edit requests. Null-space-constrained editing methods such as AlphaEdit mathematically guarantee that each update leaves unrelated knowledge intact, while collaborative frameworks such as CollabEdit aggregate edits from multiple clients without data sharing. Combining the two appears trivial. However, we show that this naive combination fails structurally, and we identify its cause. Guided by this analysis, we propose FedAlphaEdit. To our knowledge, this is the first collaborative knowledge editing framework that aligns both local editing and the server-side merging rule under a single null-space principle for preserving existing knowledge. FedAlphaEdit builds on null-space-aligned merging, in which clients share projected statistics and the server provably recovers the result of editing everything in one place under a one-shot idealization. Empirically, the proposed method repairs the collapse and brings edit success and preservation simultaneously close to the level of centralized editing across two architecture families. FedAlphaEdit thus lets institutions that cannot share raw edit data, such as hospitals and financial firms, jointly maintain a shared model that closely approximates editing all facts in one place.
Read the full abstract

Information Theory

Language Modeling is Monotone Compression

Noam Mazor, Andrew Morgan and Rafael Pass

A long-standing hypothesis in artificial intelligence and neuroscience posits that intelligence is closely related to compression: the ability to compress information efficiently intuitively reflects capacities associated with intelligence and learning. Indeed, recent experimental works verify this intuition by showing connections between the capabilities of large language models (LLMs) and their ability as compressors: for instance, Deletang et al. (ICLR'24) demonstrate that LLMs can be used as powerful compressors, and Huang et al. (COLM'24) show that the compression ability of LLMs is highly correlated with their performance on benchmarks for knowledge and reasoning. In this work, we initiate a theoretical study of this connection. Our main result is that LLMs (formally modeled as next-token predictors) are equivalent to monotone (a.k.a. order-preserving) compression algorithms—namely, compression algorithms where the encoding process preserves the ordering of the inputs—in the sense that the one can be constructed from the other while preserving the same error up to an additive gap of 2. We next show that the monotonicity is required for this equivalence to hold if and only if cryptographic (infinitely-often) one-way functions exist. As a direct corollary, we get a cryptographic result of independent interest: the notion of next-bit pseudoentropy (a computational analogue of entropy) of a distribution is equivalent to monotone incompressibility of the distribution. (Previously, it was only known (Haitner et al., ITCS'23) that incompressibility implies next-bit pseudoentropy.)
Read the full abstract

Cryptography and Security

NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents

Min-Young Yu, Tony Kim and Jang Won Choi

Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per action, or compile policies through heavyweight formal machinery. Naive compilation fails: extracted rules block the tool satisfying their own precondition, or read arguments their tool lacks. NOMOS, a four-pass compiler, turns a natural-language policy into a deterministic tool-call gate; static verification with tool-schema-level checks alone (no prover, solver, or LLM) repairs or rejects 37% (airline) and 13% (retail) of candidates, without which most shipped rules are inoperable. Replaying compiled rules over undefended transcripts flags bindings that refuse legitimate work (a development binding refused 95.9% of task-passing calls); no evaluation binding is flagged. On $\tau^2$-bench the gate cuts violations of reference-encoded clauses among state-changing calls from 66.3% to 2.6% (airline) and 30.8% to 6.9% (retail), raising airline task success significantly for $2 \le k \le 4$; a 26B on-premise compilation is not significantly worse than hand-written or frontier-compiled rules. Unlike AgentDojo's shipped defenses, it reaches a zero attack success rate (ASR) on banking, where nine attack families collapse onto three structural rules. On the other three suites its ASR is at most 3.6%, from goals with no tool call to govern and one write admitted by a binding weaker than its clause; a second agent model, Llama-3.3-70B, reproduces the effect on both benchmarks. Decisions take microseconds without an LLM call, at a domain-dependent benign-utility cost; compilation runs on-premise on open-weight gemma-4-26B.
Read the full abstract

Computational Engineering

Synchronization Reveals Market Structure That Classical Randomness Tests Cannot Detect

Nam H. Le

Synchronization among coupled oscillators – from neurons to power grids – is a universal signature of collective behavior, classically measured by the Kuramoto order parameter. Applied identically across five asset classes and 61 financial instruments, a Kuramoto-style cross-timeframe coherence measure detects structure that a calibrated, heteroskedasticity-robust variance-ratio test of the random-walk hypothesis does not: the two diagnostics are statistically independent even on the same price windows. Here we explain why, and extract the physics behind it. The four-state regime alphabet underlying the measure is a Z4 clock model whose exact factorization into two Ising sectors is precisely the order parameter's decomposition into a direction channel and a volatility channel, and the sign-flip symmetry of returns acts on the regime circle as a reflection, yielding a parity selection rule: the direction channel is provably independent of the variance ratio and of every statistic built from squared returns – confirmed by controlled simulation on processes with and without genuine persistence. Boltzmann inversion of the regime statistics then yields effective couplings between adjacent timescales, benchmarked against matched random-walk, GARCH, and fractional-Gaussian-noise nulls: the direction sector's coupling never exceeds its random-walk null in a single instrument, and its deficit independently re-measures the panel's Hurst exponent, while the volatility sector's coupling exceeds every null in every instrument and survives across scale separations where GARCH cannot – a volatility cascade. A closed-form mean-field analysis places markets deep below the synchronization transition, with all genuine cross-scale structure confined to the even, volatility sector.
Read the full abstract