Peer Revenue Play credits. Real papers.

Papers

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

All of arXiv

Tuesday 8 September

Computer Vision

ActionSplice: In-Flight Action Editing for Interactive World Models

Chunk-autoregressive video world models typically generate each chunk under one action. When an action changes during sampling, waiting until the next chunk delays the response, while directly switching the conditioning leaves the intermediate solver state shaped by the previous action. Restarting sampling under the revised action avoids this mismatch but repeats completed computation. We introduce ActionSplice, which edits the interrupted state through Counterfactual State Transport (CST). A lightweight corrector moves the interrupted solver state toward the matched counterfactual solver state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. $\mathrm{CST}_{R}$ retargets the entire active chunk, while $\mathrm{CST}_{T}$ preserves the temporal prefix at the intervention step and corrects only the suffix. On minWM–Wan Action2V and HY-WM1.5, we measure fidelity against matched rollback references. Relative to condition swapping, $\mathrm{CST}_{R}$ reduces LPIPS by 61.5% and 75.9%, and $\mathrm{CST}_{T}$ reduces suffix LPIPS by 56.1% and 77.5%, respectively.
Read the full abstract

All authors Pardis Taghavi, Tingyu Guo, Jonas Lossner, Gaurav Pandey, Reza Langari

Information Theory

Finite-Modal Realization and Operator-Norm Convergence of a Source-to-Observation Electromagnetic Scattering Green Operator

Source-to-observation operators provide reusable environment-level descriptions for multi-query electromagnetic (EM) prediction and communication-mode analysis. However, in practical multiple-scattering models, these operators are represented with finitely many angular modes, and agreement for selected excitations or between successive truncation orders does not establish uniform accuracy of the full map or reliability of its singular channels. To close this gap, we formulate the environment-induced response as a scattering Green operator on fixed continuous source and observation spaces and derive an exact trace-space factorization that reconstructs the Maxwell scattered field. For fixed, pairwise-disjoint enclosing trace spheres and a well-posed collective problem, nested vector spherical wave function (VSWF) realizations converge in operator norm. A structural bound separates external modal tails from collective-resolvent sensitivity, and operator-norm convergence guarantees uniform convergence of the singular values. We further construct a finite metric core that preserves the nonzero singular values of each finite-order operator and reconstructs matched orthonormal source–field channels without introducing external-support discretization degrees of freedom (DoF) into the spectral problem. Full-wave benchmarks verify the finite-order implementation. A controlled near-resonant two-sphere study shows that adjacent-order agreement can precede resolution of the dominant high-order collective direction. It further shows that only part of the internal amplification appears in externally accessible gains and that resonance promotes a distinct high-order channel pair above an otherwise preserved low-order family. The resulting framework provides a convergent, metric-consistent finite-modal representation of multiple-scattering source-to-observation operators and their accessible channels.
Read the full abstract

All authors Zhukang Wang, Da Li, Ruifeng Li, Jinyan Ma, Jiarun Hu, Jiahui Wang, Anqi Xia, Tengjiao Wang, Said Mikki, Er-Ping Li

Artificial Intelligence

SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale

LLM agents use large libraries of reusable skills. At thousands of skill entries, retrieval becomes the bottleneck. Graph-of-Skills (GoS) retrieves dependency-aware bundles from a typed skill graph, and SkillDAG shows that such a graph can accumulate execution-backed structure online. Neither asks whether execution traces can be distilled into a better retrieval graph that generalizes to unseen tasks. We present Self-Evolving Graph-of-Skills (SE-GoS), which treats the retrieval graph as an index rather than a learned representation: the graph is maintained from execution traces while the retrieval pipeline, the skill library, and the model stay fixed. SE-GoS applies three updates: (1) topology, which induces relations from execution evidence and retracts an avoid edge only after repeated successful co-use; (2) edge-weight, which softly attenuates unsupported semantic edges and reinforces incoming edges to used skills; and (3) node-description, which updates retrieval-facing descriptions stored on graph nodes ranked too low. On SkillsBench, one evolution round lifts average reward from 52.4% to 59.4%, above full-library loading, vector retrieval, static GoS, and SkillDAG, and this ordering repeats on all three backbones. Retrieval over the evolved graph spends about two-thirds of the input tokens that loading the full library costs. Repeating the round does not help. The same graph improves a held-out split it never saw from 52.9% to 58.3%, so what it accumulates transfers rather than memorizes traces. Skill graphs can therefore be improved from execution experience without model training, retrieval-algorithm changes, skill-content modifications, or a model judging which skills are related.
Read the full abstract

All authors Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, Zhongkai Hao

Analysis of PDEs

On the singular limit of the Camassa-Holm equation

We study the singular limit of the Camassa–Holm equation as the length scale $\ell$ tends to zero. Although the formal limit is the Burgers equation with flux $3u^2/2$, we show that, for a class of smooth initial data, convergence to entropy solutions fails after the shock formation, even along subsequences in local space-time $L^1$.
Read the full abstract

Artificial Intelligence

TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs

Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing benchmarks primarily emphasize structural evolution via temporal link prediction (TLP), while support for semantic evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture realistic semantic drift. Moreover, commonly used datasets exhibit high link repetition, leading to inflated performance estimates and obscuring true model capability. To address these limitations, we introduce TTGBench, a new benchmark that jointly evaluates structural and semantic evolution. TTGBench comprises six real-world, text-rich datasets characterized by Dual Volatility, enabling rigorous and fair evaluation of existing models. Notably, it is the first benchmark to support both multi-class and multi-label TNC, filling a critical gap in evaluating temporal semantic drift. We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms. The results reveal a clear capability divide between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictors show the opposite trend. Through in-depth analysis, we uncover their fundamental limitations and provide insights for developing more comprehensive temporal graph models.
Read the full abstract

Statistical Methodology

Multi-Objective Composite Longitudinal Biomarker Scores for Improved Cancer Risk Assessment

Repeated blood-based biomarker measurements can improve cancer risk assessment by capturing longitudinal changes missed by single-time-point analyses. Parametric Empirical Bayes (PEB) incorporates prior measurements to estimate individualized reference values, but existing implementations do not account for the time between measurements and rely on predefined panels with fixed combination rules. We developed improved Parametric Empirical Bayes (iPEB), which accounts for the intervals between serial measurements, adjusts for covariates, and performs feature selection and optimized biomarker combination. iPEB optimizes biomarker weights for specific clinical objectives, such as maximizing sensitivity at a prespecified specificity or diagnostic lead time. We evaluated iPEB through simulations and a real-world application using six protein biomarkers (pro-SFTPB, CEA, CA125, CYFRA 21-1, osteopontin, and HE4) from a case-control study nested within the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial. The analysis included 324 lung cancer cases and 1,674 controls with at least two serial measurements; six centers were used for model development and four for independent validation. Optimized for sensitivity at 99% specificity, iPEB achieved 24.2% sensitivity in the independent test set, compared with 18.2% for conventional PEB applied to the same four-marker panel. Optimized instead for lead time, iPEB added approximately 50 days of lead time at that stringent operating point. iPEB improved lung cancer risk assessment in independent PLCO data, supporting objective-driven optimization of longitudinal biomarkers for early detection.
Read the full abstract

All authors Bitan Sarkar, Ana Maria Kenney, James P. Long, Johannes F. Fahrmann, Samir Hanash, Kim-Anh Do, Ehsan Irajizad

Robotics

3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints

Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language models (VLMs). Among these, trajectory-based representations compactly represent motion-relevant cues, yet most existing approaches predict trajectories in 2D image space, resulting in intrinsic 3D ambiguity. Moreover, using 2D trajectories with depth still leaves the free-space waypoints ambiguous, limiting reliable 3D reasoning. To address this, we propose predicting 3D consistent waypoints (3DWay) from multi-view images. By reformulating 3D waypoints prediction as generating multi-view consistent 2D waypoints followed by geometric triangulation, we enable explicit 3D motion specification while preserving the strong priors of pretrained VLMs. The predicted waypoints can guide existing VLA models for better generalization or be directly executed on simple tasks. Extensive experiments show that 3DWay substantially improves 3D spatial grounding and vision-language reasoning, demonstrating strong potential for generalizable robot manipulation. Codes will be released at https://github.com/ziqin-h/3DWay.
Read the full abstract

All authors Ziqin Huang, Yingyue Li, Chenyangguang Zhang, Ruida Zhang, Yuxin Chen, Gu Wang, Xingyu Liu, Masayoshi Tomizuka, Xiangyang Ji

Quantum Gases

Large-Chern-number flat bands, anomalous Dirac cones, and unconventional superfluidity in square-lattice systems with SU(N) non-Abelian gauge fields

We study topological band structures and superfluid phases in two-dimensional square-lattice systems with homogeneous SU($N$) non-Abelian gauge fields. Starting from an SU(4) gauge-field model related to the Hofstadter model with flux $\alpha=1/4$, we show that the lowest and highest bands are isolated Chern bands that carry Chern numbers $C=-4$ and give rise to four chiral edge modes in a strip geometry. Remarkably, although the two middle bands touch and form $16$ gapless Dirac cones, their combined Chern number is $C=8$. We then generalize the construction to SU($N$) systems and reveal an even–odd structure of the band topology: when $N$ is odd, all bands are isolated and carry nonzero Chern numbers; when $N$ is even, the two middle bands touch at $N^{2}$ Dirac points, while all other bands remain isolated and topologically nontrivial. We find that the uppermost and lowermost bands become increasingly flat and their Berry curvature becomes more uniform as $N$ increases, providing a promising platform for realizing fractional Chern insulating phases. We further examine the spin-$3/2$ SU(4) model with on-site attractive Hubbard interactions, exploring its superfluid phases at partial filling. We find that the non-Abelian gauge field breaks the hidden SO(5) degeneracy of the quintet pairing and selects distinct nematic superfluid states. For fillings in the middle-band regime, the resulting spectrum can host topologically protected Bogoliubov Fermi surfaces. Our results provide a starting point for exploring both topological band physics and unconventional superfluidity in synthetic SU($N$) cold-atom systems.
Read the full abstract

Combinatorics

Balanced Spanning Trees for Triangular Strip Lattices

A balanced spanning tree is a spanning tree that contains an edge whose removal partitions the vertices into exactly two connected subtrees of equal size. In this paper, we establish explicit recurrence relations for the number of spanning trees in $2 \times n$ triangular strip lattices- obtained by adding a diagonal edge to each square of a $2 \times n$ grid graph- generalizing combinatorial counting techniques introduced by Raff [Raf08]. We then adapt arguments of Gallagher and Tapp [GT25] to count balanced spanning trees of arbitrary triangular strip lattices. We establish sharp asymptotic bounds for the proportion of balanced spanning trees as $n \rightarrow \infty$. Finally, we determine the probability that a spanning tree of a $2 \times n$ triangular strip lattice chosen uniformly at random is balanced as $n \rightarrow \infty$.
Read the full abstract

Computer Vision

SoftRerank: Hierarchical Soft Fusion with Candidate-Label Reranking for Long-Tailed Micro-Action Recognition

Micro-actions are subtle, low-intensity non-verbal behaviors that provide cues to fine-grained human states, including emotions and intentions. Recognizing them remains difficult because they are brief, contain weak visual changes, and often exhibit similar motion patterns across categories. This paper addresses these challenges with a fine-grained micro-action recognition method that combines full fine-tuning of InternVideo2.5, hierarchical soft fusion, and a lightweight candidate-label reranker. For the long-tailed label distribution in MA-52, we use class-balanced sampling and inverse-frequency reweighting to reduce the effect of frequent classes during training. We fine-tune InternVideo2.5 end to end and attach coarse and group-conditional fine-grained classification heads to the shared video representation, improving the consistency between coarse and fine predictions. For ambiguous samples, the candidate-label reranker uses hard samples and video-label matching to focus on easily confused fine-grained actions. Experiments validate the proposed method, which achieves a 79.99% F1-mean on MA-52 and ranks first in the 3rd Micro-Action Analysis Grand Challenge at ACM Multimedia 2026.
Read the full abstract

All authors Yichi Zhang, Zhichao Xia, Yanjun Chi, Lingsi Zhu, Yuefeng Zou, Jun Yu, Qingsong Liu, Jianqing Sun, Shengping Liu

Robotics

Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models

Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineffective for robots operating under complex physical interactions. This limitation stems from the gap between language-based reasoning and the physical consequences of embodiment, often resulting in designs with low physical validity. In this work, we propose a multi-layered framework, AID-SR, that establishes a closed loop by translating simulator-observed physical states into structured feedback for the LLM designer. Combined with semantic critique, human feedback, and iterative refinement, the framework promotes the generation of physically feasible and functionally meaningful robot designs. We evaluate our approach on tendon-driven continuum robots across a benchmark of 14 tasks spanning reaching, grasping, locomotion, and manipulation. The proposed framework achieves 96.2% rate for passing the simulation feasibility check and by applying a common reinforcement learning training, 26.7% robots can successfully fulfill the corresponding task. We then fabricate three designed robots of AID-SR that successfully complete the task in real-world. These extensive experiments across simulation and real-world environments demonstrate and break the wall of utilizing the LLMs for automated design of continuum robots. The source code and experimental resources are publicly available at https://github.com/UNITES-Lab/AID-SR.
Read the full abstract

All authors Jingyi Chen, Mohan Zhang, Laura Yao, Yingtai Ni, Jianmin Ji, Jie Peng, Song Wang, Tianlong Chen

Statistical Mechanics

Speed limits for information acquisition in stochastic learning dynamics

Neural networks acquire internal representations through learning. In this work, we formulate stochastic gradient descent (SGD) as a Markovian stochastic process and derive a Fisher-information flow speed limit that bounds the rate at which trainable parameters can acquire information about data-generating parameters. The resulting inequality decomposes the upper bound on the information flow into drift and noise contributions, thereby quantifying the roles of deterministic learning forces and SGD-induced fluctuations from an information-theoretic perspective. We verify the bound in analytically tractable basis-function linear regression, where the information budget predicted by the bound reproduces the ordering and characteristic time scales with which different data-generating parameters are encoded in the learned parameters. These results establish Fisher-information speed limits as a quantitative framework for understanding which properties of the data-generating process are acquired, in what order, and how rapidly they can be encoded in the trainable parameters.
Read the full abstract

Systems and Control

Stabilizing Traffic Flow Via Autonomous Vehicles: A Less Conservative Approach

This paper explores stabilizing traffic flow using a minimum number of autonomous vehicles (AVs) under control constraints. In contrast to most studies, we consider a heterogeneous parameter setup scenario for human-driven vehicles (HVs) to reflect real-world differences in driving behavior. While current literature uses an H-Infinity based sufficient condition to ensure the string stability of traffic flow, this often yields a conservative lower bound on the AV penetration rate to stabilize traffic flow. To reduce such conservativeness and obtain a less conservative lower bound, we ensure the string stability of traffic flow by directly imposing the possession of no growing eigenmodes. We also systematically find a minimum number of required AVs and solve for the optimal control parameters via nonlinear optimization. We finally assess the intended conservativeness reduction via numerical simulations. Quantitatively, applying our algorithm to the homogeneous HV baseline in the literature (the result built upon an H-Infinity based sufficient condition) reduces (improves) the AV penetration rate by 17.14% while ensuring the string stability of traffic flow. We observe a trade-off between the stabilization/performance degradation and the number of utilized identical AVs. Quantitatively, our last numerical simulation corroborates that the AV penetration rate can be reduced by 61.54% at the expense of 27.66% higher position difference deviation from the equilibrium and a 92.47% degradation in the real stability radius (RSR)—a metric to measure the stability robustness under the perturbation/uncertainty—associated with the aggregated linearized dynamics while ensuring the string stability of traffic flow. This trade-off helps engineers/operators make better traffic control decisions.
Read the full abstract

Computer Vision

Drive by Hindsight and Foresight: Tool-Grounded Synergistic Reasoning over Hierarchical Memory for Autonomous Driving

VLMs have shown promise for autonomous driving, yet still suffer from hallucination, weak spatio-temporal perception, and limited generalization. Recent methods improve reasoning and decision-making through CoT explanations, retrieval-augmented generation or the static injection of tool outputs. Although these mechanisms enrich the context, the model neither proactively perceives scene information nor accumulates experience after answering. To overcome these limitations, we present, to our knowledge, the first synergistic framework that tightly couples hierarchical memory with proactive tool invocation in a closed reasoning loop. Our contributions are threefold. (i) Hierarchical Driving Memory: a scene-level short-term memory maintains the dynamic scene state, and an evolving long-term memory retrieves reusable experience and tool strategies. (ii) Memory-Tool Synergistic Reasoning Framework: guided by the scene state and retrieved experience, the model adaptively invokes tools to refine its reasoning at inference time and consolidates reusable experience into a long-term memory pool offline. (iii) Data Generation and Two-stage Training Pipeline: verified memory-tool trajectories built by multi-step teacher rollout are used to train with SFT and GRPO. Our 7B model reaches an overall reasoning score of 80.03 and MCQ accuracy of 79.09% on DriveLMM-o1, surpassing the strongest baseline by 7.74 MCQ points and generalizes strongly across benchmarks. Notably, ablation and analysis studies validate the effectiveness of each component and further reveal the complementary roles of hierarchical memory. Short-term memory strengthens spatio-temporal understanding, improving STSBench accuracy by 24.2 points, while offline long-term memory consolidation yields an additional 3.57-point MCQ gain with all parameters frozen, demonstrating continual self-evolution through accumulated driving experience.
Read the full abstract

Artificial Intelligence

Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI

Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.
Read the full abstract

Computer Vision

PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation

Video generation models have recently attracted substantial attention for their ability to generate visually compelling videos, yet ensuring physically consistent and plausible dynamics still remains a fundamental challenge, driving a growing line of research on physical realism in video generation. To address this challenge, motivated by the fact that physical regularities are primarily encoded in motion patterns, we propose PhysFlow, a novel two-stage framework for improving the physical plausibility of generated videos by decomposing video generation into motion-aware optical flow generation followed by motion-conditioned appearance synthesis. Specifically, PhysFlow consists of a physics-aware optical-flow video generator called PA-Flow and a flow-guided video generator called FlowRender. During the first stage, PA-Flow employs a physics-aware attention module to model how motion attributes and material properties influence global motion and local deformation, respectively, and generates an optical flow video as an explicit representation of motion. In the second stage, FlowRender leverages the decoupled motion representation as guidance to synthesize realistic textures and appearances, ultimately producing the final physically plausible video. To further support model training with explicit physical supervision, we construct PhysVideo, a physics-based video dataset generated with a physics engine and 3D-GS rendering, containing 10K foreground objects and 50K realistic video sequences with annotations of motion and material properties. Extensive experiments demonstrate that our proposed PhysFlow generates videos with superior physical plausibility while maintaining high visual fidelity compared with existing methods.
Read the full abstract

All authors Cong Wang, Hanxin Zhu, Yonglin Tian, Jiayi Luo, Ruiqi Song, Boyi Sun, Long Chen, Zhibo Chen

Robotics

TacClip: a clip-on sensor measures dynamic contact forces without covering the fingerpads

TacClip is a minimally encumbering wearable device for recording fingertip deformation caused by contact forces and vibrations. It can be combined with vision- or glove-based hand tracking systems that leave the fingertips uncovered and provides a measure of dynamic contact interactions, while leaving the finger pads exposed so that the user retains natural sensitivity to texture, friction, temperature, and fine surface features. The signal is produced by a Fiber Bragg Grating (FBG) embedded on a small plastic clip mounted over the fingernail. Optionally, for use with vision-based tracking, additional FBGs on polyimide strips can complement camera-based pose estimation. In finger pressing tests, TacClip estimates the force magnitude with typical errors below $0.5~\mathrm{N}$ over a $0$–$8~\mathrm{N}$ range. In tests of cloth handling and tape edge finding, we show that it captures the vibrations and dynamic events generated during exploratory sliding. With no electronics, TacClip can also be used submerged in water, while preserving bare finger contact.
Read the full abstract

All authors Yuqian Ye, Hao Li, Jingxi Xu, Haojun Feng, Seongheon Hong, Mark R. Cutkosky

Cryptography and Security

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conventional pixel-space distortions. Existing removal attacks either regenerate along deterministic trajectories, which often preserve the watermark-bearing latent structure, or optimize every image separately. We identify the reliance on a recoverable generative trajectory as a common attack surface among the schemes we study. Based on this observation, we propose DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling. Forward re-noising limits source information available to a fixed-depth recovery pipeline, while stochastic reversal supplies alternative noise-driven paths whose removal benefit we isolate through matched sampler comparisons. Adaptive DRIFT searches a selected ladder for each image's first verifier-rejected rung and refines fidelity while retaining only updates rejected by the same verifier. At fixed depth, we derive information-theoretic and Wasserstein source-dependence bounds; under realized-ladder monotonicity, the first rejected rung is least distorted among rejected rungs on that ladder, and verifier-gated refinement preserves rejection. Across nine watermarks spanning three paradigms, DRIFT achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.
Read the full abstract

All authors Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

Numerical Analysis

Finite difference methods for three kinds of reaction-diffusion equations with free boundaries

This work considers to numerically solve three kinds of reaction-diffusion equations with free boundaries. First, the popular front-fixing method is used to transform the considered free boundary problems into fixed boundary problems. Then, by employing the finite difference method, numerical schemes with $\mathrm{M}$-matrices as their coefficient matrices are developed for these transformed fixed-boundary problems. Next, for the developed numerical schemes, we establish numerical theory involving positivity preservation, monotonicity preservation, and stability. It is noteworthy that, unlike some existing works that impose tight restrictions on the time step-size to discuss the numerical theory, the proposed numerical schemes require only a mild restriction. Finally, numerical examples are provided to test the developed numerical schemes and to confirm the theoretical results.
Read the full abstract

Artificial Intelligence

A Better Spur Should Start From Each Objective

Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflicts among multiple objectives in real-world deployment scenarios, we propose Multi-Marginal Preference Optimization (MMPO), a fine-grained framework that intervenes at the data, gradient, and constraint levels rather than relying on coarse-grained global scalarization. Specifically, MMPO performs exposure debiasing to mitigate sparse and biased rewards, applies priority-aware orthogonal projection to decouple conflicting gradients, and introduces self-prompted gradient constraints to prevent dominant objectives from overwhelming weaker ones. Experiments on real-world e-commerce datasets show that MMPO improves training stability and consistently achieves better performance across conflicting metrics. Moreover, it generalizes robustly to broader tasks such as ToolRL and code generation, demonstrating its effectiveness as a practical paradigm for multi-objective alignment.
Read the full abstract

All authors Shanwen Mao, Hao Zhang, Guangtao nie, Zhiheng Li, Huimu Wang, Sulong Xu, Gu Simiu

Functional Analysis

Interchanging limits in the mutual information of two intervals separated by one site

In the paper J. Phys. A: Math. Theor. 53 (2020), 345303, the limiting mutual information between two intervals separated by one lattice site in a free-fermion chain was evaluated. The calculation replaces the entropy function by a regularized version depending on $\varepsilon>0$, takes the block lengths to infinity, and only then lets $\varepsilon$ tend to zero. We prove that the opposite order gives the same constant $2\log2-1$. Moreover, we show that the same limit is obtained whenever both block lengths tend to infinity and $\varepsilon$ tends to zero simultaneously, with no restriction on their relative rates. In fact, the error caused by the regularization is bounded by $(1+\varepsilon)\log(1+\varepsilon)-\varepsilon\log\varepsilon$, uniformly in both block lengths.
Read the full abstract

Robotics

Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation

Learning from Observation (LfO) is a fundamental robotic capability that replicates how humans and animals socially learn from each other. Beyond its biological parallels, this modality provides a practical solution for data scaling in sample-inefficient and data-starved domains like robotics. Recent work has demonstrated promising results in learning manipulation skills from human videos, yet progress in this area remains difficult to assess. Existing methods vary widely in assumptions, hardware choices, and environment setups making it difficult to draw meaningful comparisons and identify advances in the field. To address these challenges, we introduce RoboReel: a unified benchmark for evaluating models that learn policies from human videos. RoboReel consists of bundled real-world human demonstration videos, simulated robot trajectories, and evaluation environments on ten manipulation tasks. We develop four test suites to evaluate the models' performance on multiple axes, including the robustness to visual distractors and the ability to complete long-horizon tasks. We further validate RoboReel by recreating a subset of its tasks in the real world, showing that relative performance trends observed in simulation are preserved in the real world. Our benchmark covers learning-from-observation models from different categories, and studies the effectiveness of multiple representation choices in our benchmark evaluation that covers over seven state-of-the-art algorithms (including our VLA based variants) in the field of LfO. Finally, we present an analysis of the different types of algorithms showing that long-horizon tasks and tasks with low tolerances are still challenging for current models. Webpage: https://roboreel.github.io
Read the full abstract

All authors Weiwei Gu, Anmol Gupta, Anant Sah, Ryan Varghese, Lalitha Shreya Vanam, Prabhath Adireddi, Peter Karkus, Nakul Gopalan

Quantum Gases

Increase of Magnetic Trap Loading Efficiency for $^{39}\mathrm{K}$ Bose–Einstein Condensation Experiments

During the experimental sequence, a large atom number is important for the creation of high-quality Bose–Einstein condensates. We report an experimental increase of about 15% in magnetic-trap (MT) loading efficiency by optimizing the MT loading process. The loading time is much shorter than the lifetime of the atoms in the MT, which means atom loss during loading due to the finite trap lifetime can be neglected. We obtain an almost pure $^{39}\mathrm{K}$ condensate with $1.2\times10^{5}$ atoms after evaporative cooling in our optical trap.
Read the full abstract

All authors Yihao Cheng, Xiaoyang Shen, Weixin Li, Hao Du, Hongwu Zhao, Lin Xia

Image and Video Processing

Benchmarking Regularization Methods For 3D Radio Tomographic Imaging

Integrated Sensing and Communication (ISAC) is an important technology for 6G, enabling wireless systems to perceive their physical environment. Radio Tomographic Imaging (RTI) is a potential technique for device-free sensing in ISAC, reconstructing object locations and shapes from Received Signal Strength (RSS) measurements. It can complement other techniques, such as radar and LiDAR, by providing a narrowband modality with wavelength resolution. Recently, an extended version of RTI, known as the extended phaseless Rytov approximation (x3DPRA), has been developed to enhance RTI reconstruction quality, estimate material parameters, and extend RTI from two to three dimensions (3D). However, the 3D formulation is even more ill-posed than the 2D form, as the number of measurements is far fewer than the number of unknown voxels. In this work, we systematically evaluate and compare three distinct regularization approaches (Ridge, Total Variation, and Tensor Nuclear) within the x3DPRA framework. We provide a detailed performance analysis by evaluating both reconstruction quality and computational runtime across the three methods. Our findings show that Total Variation regularization provides the best reconstruction quality but not the fastest runtime, providing guidance for developing high-resolution 3D RTI systems for future ISAC applications.
Read the full abstract

All authors Wanqin Ma, Yijun Chen, Alikhan Umirbayev, Jichen Zhang, Ross Murch

Differential Geometry

The Weyl Law Meets Large-Scale Regularity on Ricci Shrinkers

We prove that the weighted Laplacian, or equivalently its conjugate Schrödinger operator, on every complete gradient Ricci shrinker satisfies the classical Weyl law. The main difficulty is that uniform bounded geometry is not known for general Ricci shrinkers. To overcome this, we establish a large-scale regularity property for complete gradient Ricci shrinkers and apply it to the spectral asymptotics of the weighted Laplacian. We prove that, inside large geodesic balls of radius $R$, the region where the curvature radius is smaller than $R^{-1}$ occupies an asymptotically negligible proportion of the volume. The proof uses the Ricci flow associated with the shrinker, together with the curvature-radius estimates and Sobolev inequalities of Li–Wang.
Read the full abstract

Quantum Algebra

Homological properties of quantum groups governed by small quantum groups

We develop a general characteristic-free framework for studying the homological properties of a broad class of module-finite Hopf algebras. This framework makes it possible to reduce the study of the homological properties of many quantum groups at roots of unity and their multiparameter deformations to the study of the corresponding small quantum groups. For any affine Hopf algebra $H$ admitting a large central Hopf subalgebra $C$, we prove that its left homological integral space, in the sense of Lu-Wu-Zhang, is isomorphic as a bimodule to the left integral space of the identity fiber algebra, which is a finite-dimensional Hopf algebra. Consequently, $H$ is a symmetric Frobenius extension of $C$ if and only if the corresponding identity fiber algebra is unimodular and the square of the antipode of $H$ is inner, thus providing an effective criterion for the Calabi-Yau property of $H$. For a broad class of quantum groups at roots of unity, an appropriate large central Hopf subalgebra can be chosen such that the identity fiber algebra is the corresponding small quantum group. Therefore, some homological properties of these big quantum groups are governed by those of their corresponding small quantum groups. Assuming that the base field is algebraically closed, we prove that $H$ is unimodular if and only if, for some (equivalently, every) maximal ideal $\mathfrak{m}$ of $C$, the category of finite-dimensional representations of the fiber algebra at $\mathfrak{m}$ is unimodular in the sense of Yadav as a module category over the finite tensor category of finite-dimensional representations of the identity fiber algebra. As an application, we prove that all Andruskiewitsch-Angiono-Yakimov large quantum groups are affine noetherian unimodular Artin-Schelter Gorenstein Hopf algebras. We also give a necessary and sufficient condition for these large quantum groups to be Calabi-Yau.
Read the full abstract

All authors Yimin Huang, Tiancheng Qi, Quanshui Wu, Ruipeng Zhu

Sound

Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering

Instruct-TTS systems expand structured style labels into natural-language training instructions through LLM rewriting, yet we find that over 40% of unconstrained rewrites contain semantic drift that corrupts supervision and weakens generalization. We formalize this problem as instruction supervision instability and propose a data-centric stabilization recipe that jointly improves coverage and fidelity through three mechanisms: controllable instruction diversification for systematic expansion, LLM-based drift filtering for quality control, and attribute-aligned supervision that grounds prosody control in acoustic perturbations. On the Chinese split of InstructTTSEval, our recipe raises instruction-following from 34.5% without fine-tuning and 51.0% with naive fine-tuning to 56.4%, while constrained rewriting reduces drift from 40.4% to 15.4%. Ablations confirm the three mechanisms are complementary, and the drift taxonomy may generalize to instruction-driven generation beyond TTS.
Read the full abstract

All authors Yizhong Geng, Kecan Mao, Qifei Li, Cong Wang, Yingming Gao, Ruimin Wang, Chunfeng Wang, Hao Li, Ya Li

Information Theory

Asymptotically good binary triorthogonal codes and higher-level transversal gates

For each level of the Clifford hierarchy from the third level onward, we construct explicit asymptotically good binary CSS codes for which a strongly transversal diagonal rotation, followed by a correction from the preceding level, implements the corresponding logical rotation. We achieve this using algebraic geometry codes over binary extension fields and performing an alphabet reduction that translates orthogonality conditions over the extension field to binary overlap conditions. In particular, we obtain the first asymptotically good family of binary triorthogonal codes. We also give a stronger construction with worse parameters for which the strongly transversal physical rotation implements the desired logical rotation, with no subsequent correction. Finally, adapting an error-correction-based distillation protocol, our binary $T$-gate families yield direct constant-overhead $T$-state block distillation from noisy $T$-state inputs under sufficiently weak input noise and ideal stabilizer operations.
Read the full abstract

Soft Condensed Matter

Viscoelasticity reshapes the frequency response of a rotating magnetic particle

A magnetic particle driven by a rotating magnetic field undergoes a transition from synchronous to asynchronous rotation at a critical driving frequency. The asynchronous dynamics is well understood in Newtonian fluids but remains unclear in viscoelastic media. Here, we develop a theoretical description of the asynchronous rotation of a magnetic particle in a Jeffreys-type viscoelastic fluid. The particle's time-averaged angular velocity exhibits a nontrivial frequency dependence that changes from non-monotonic to monotonic as the polymer relaxation time increases. This behavior is explained by the interplay among magnetic driving, viscoelastic relaxation, and frequency-dependent viscous dissipation. We further derive an asymptotic expression that captures the non-monotonic dependence. These results clarify how solvent and polymer contributions jointly control asynchronous rotation and provide a physical basis for guiding relevant applications in complex fluids.
Read the full abstract

All authors Zhiyuan Zhao, Tingting Sun, Han Gao, Ye Xu, Mingcheng Yang, Masao Doi

Number Theory

A Lang-Trotter Problem for Non-Geometric Quadratic Inductions

Let $K/\mathbb Q$ be an imaginary quadratic extension and $p$ an odd prime. Write $\rho=\operatorname{Ind}_{G_K}^{G_{\mathbb Q}}\chi$, where $E/\mathbb Q_p$ is a finite extension and $\chi:G_K\to\mathcal O_E^\times$ is a continuous character. For a fixed $r\in\mathbb Z\setminus\{0\}$, let $\pi_{\rho,r}(X)$ denote the number of rational primes $\ell\le X$ such that $\rho$ is unramified at $\ell$ and $\operatorname{tr}\rho(\operatorname{Frob}_\ell)=r$. Let $a,b$ be the two weights of $\chi$ at $p$. We prove that if $(a,b)\notin\mathbb Q^2$, then $\pi_{\rho,r}(X)\ll_{\rho,r,\varepsilon}X^\varepsilon$ for every $\varepsilon>0$, while if $(a,b)\in\mathbb Q^2\setminus\mathbb Z^2$, then only finitely many such primes occur. These bounds are substantially sparser than the classical CM Lang–Trotter scale. The main input in the non-rational case is a rigidity theorem for algebraic curves in the \(p\)-adic analytic trace locus, combined with rigid-analytic Pila–Wilkie counting; the rational non-integral case is treated by a local ramification argument.
Read the full abstract