Artificial Intelligence
ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces
Jerry Wang, Haibo Jin, Xiaopeng Yuan et al. (+2 more)
Information-seeking
agents increasingly operate over information spaces that are too large to process exhaustively. Yet many multi-
agent systems organize computation around static partitions of the available space, causing coordination to grow with how information is segmented rather than with what the query still requires. We introduce ANTMAN, an adaptive coordination framework that treats evolving unresolved information needs as the unit of runtime coordination. ANTMAN maintains a revisable Need Graph that tracks unresolved requirements, accumulated evidence, prior attempts, and search progress, and uses this state to control worker selection, routing, and task-local recovery as new evidence is discovered. By separating the coordination policy from substrate-specific search interfaces, the same need-conditioned mechanism can operate across different information spaces. Experiments across multi-document question answering, controlled long-context scaling, and realistic structured
navigation show that ANTMAN remains effective across settings, including when execution is delegated to substantially smaller worker models. Under a 16x increase in searchable context, ANTMAN increases active coordination by only 1.23x, compared with more than 15x for partition-driven baselines, while preserving strong answer quality.
Read the full abstract ▾
All authors Jerry Wang, Haibo Jin, Xiaopeng Yuan, Peng Kuang, Haohan Wang
Computer Vision
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems
Siran Peng, Tianshuo Zhang, Tianyu Fu et al. (+8 more)
Visual backbones have evolved from Convolutional Neural Networks (CNNs) with local aggregation to
Vision Transformers (ViTs) with global interactions, State-Space Models (SSMs) with input-dependent state transitions, and Test-Time Training (TTT) layers that adapt an inner learner while processing an image. Across this progression, visual computation has become increasingly adaptive to each input, yet the rules governing that adaptation remain largely prescribed by the trained backbone. We introduce VisionHOPE, the first generic visual backbone formulated as a self-modifying learning system, in which what the model remembers and how it learns co-evolve within an image. Building on the self-referential construction of Nested Learning (NL), VisionHOPE realizes this co-
evolution through five coupled
memories that store content, generate key and value representations, and govern learning rate and retention. These
memories evolve jointly as visual context accumulates along each scan. However, directly applying the unconstrained self-referential update to a visual backbone leads to instability. We therefore derive a stability-matched step-size control scheme that combines a soft cap on self-referential injection with a spectral clamp on the retained
memory transition, and prove that the resulting
memory dynamics are non-expansive along each scan. For two-dimensional feature maps, we adapt NL's chunk formulation by aligning chunks with image rows and columns across four directional scans. The proposed VisionHOPE achieves competitive results on ImageNet-1K, COCO, and ADE20K, establishing self-modifying learning systems as a practical foundation for general-purpose visual backbones. The code is available at https://github.com/PSRben/VisionHOPE.
Read the full abstract ▾
All authors Siran Peng, Tianshuo Zhang, Tianyu Fu, Weisong Zhao, Haoyuan Zhang, Jiankuo Zhao, Minghui Wu, Ping Jiang, Xiangyu Zhu, Chenxu Zhao, Zhen Lei
Number Theory
On the distribution of the zeros of the Euler double zeta-function $\zeta_2(s,s)$
Kohji Matsumoto, Tomokazu Onozuka and Isao Wakabayashi
We investigate the distribution of zeros of the function $\zeta_2(s,s)$, namely the function defined by putting $s_1=s_2=s$ in the Euler double
zeta-function $\zeta_2(s_1,s_2)$. Our
theorems provide refinements of observations, obtained numerically in a previous paper by the first author and M. Shōji, with rigorous theoretical proofs.
Read the full abstract ▾
Artificial Intelligence
Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill et al. (+3 more)
Recent advances in Large
Language Models (LLMs) have enabled agentic systems capable of solving complex tasks through multi-turn planning, tool use, verification, and
memory updates. However, learning agentic systems remains difficult due to two fundamental challenges, i.e., (1) long-horizon credit assignment, where supervision is available only at the final outcome, and (2) imbalanced data distributions, where dominant data patterns bias optimization and weaken adaptation to rare but informative
reasoning behaviors. In this paper, we propose Fair Multi-Level Preference Optimization (Fair-MPO or $\Phi$-MPO), a new preference optimization framework for agentic learning. We first show that Multi-Level Preference Optimization provides a principled and more computationally efficient framework for long-horizon
reasoning. Then, we introduce a Fair Multi-Level Objective that addresses imbalance in agentic learning. We provide a comprehensive theoretical analysis demonstrating that our approach addresses both long-horizon
reasoning and data imbalance. Our experiments on agentic
reasoning benchmarks demonstrate that our approach achieves State-of-the-Art (SOTA) performance.
Read the full abstract ▾
All authors Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill, Jackson Cothren, Marios Savvides, Khoa Luu
Databases
Robust Hierarchical Structures for Agentic Document Analysis
Ruiying Ma, Yiming Lin and Aditya G. Parameswaran
Large
Language Models (LLMs) enable us to better understand text documents, including PDFs and Word documents. However, LLMs, as well as more modern LLM
agents, i.e., those with tool-calling abilities, typically treat such documents as plain text, ignoring the fact that they are often organized hierarchically into sections and subsections. Extracting this structure, while difficult, can improve efficiency and effectiveness for
agents (and humans)—since only sections relevant to a given task need to be processed. Unfortunately, prior work on structure extraction provides no formal guarantees on how well the inferred structure matches the true one. Instead, we target a robust and compact variant that is feasible to infer and useful in practice. Robustness ensures that the text under each subsection header is a superset of the text under the same header in the true structure. Compactness seeks to minimize this superset, reducing agentic cost (or human cognitive load). We propose SHED, a two-stage workflow for inferring a robust and compact structure. The first stage is pluggable with an infinite family of approaches, each guaranteeing robustness for a specific document class. We theoretically characterize the document space using these classes and their hierarchical relationships. Empirically, SHED improves F-1 scores (measuring the robustness–compactness trade-off) by 13%–68% over non-LLM baselines and 9%–15% over expensive LLM-based approaches. Finally, we show how SHED-inferred structures are valuable for agentic document analysis:
agents using SHED outperform baselines, achieving 3%–23% higher accuracy while being up to 10x cheaper.
Read the full abstract ▾
Human-Computer Interaction
Separating Memory and Workflow Effects in Predicting Individual Answers
Tianzhu Qin, Leo Yang Yang, Ramit Debnath et al. (+1 more)
Language agents choose what to remember about a person and how to use that
memory. We separate these choices when predicting a person's unseen answer to an interview question. On 1,768 tasks from 188 people, a concrete
memory from a verified interview prefix outscores a trait description by 0.0158 (95% interval [0.0044, 0.0271]). Crossing both
memories with one-shot generation and three-answer fusion, fusion lowers concrete-
memory scores by 0.0123 ([-0.0189, -0.0056]); prompted and trained selectors do not detectably beat a random candidate, and one call on the longer, unrewritten record outscores every
memory condition. At matched context budgets, OwnWords, one call on the person's BM25-ranked sentences, outperforms the written
memory on 500 people outside the
benchmark (+0.0127, [+0.0037, +0.0217]; an earlier held-out test was inconclusive) and across four budgets on 300 people (mean +0.0218, [+0.0138, +0.0298]), but does not detectably outperform recency truncation; these comparisons do not isolate verbatim wording. On a survey
benchmark it predicts ordinal answers more closely than the
memory but is not more accurate on exact choices (less accurate in one of two screener samples). Interview scores use a model-based content rubric without human ratings, and all
benchmark and some confirmation participants were seen during development.
Read the full abstract ▾
All authors Tianzhu Qin, Leo Yang Yang, Ramit Debnath, Davin Youchao Dong
Optics
Propagation of pulse fluctuations of multimode sources in optical fibers and waveguides with arbitrary chromatic dispersion
José Capmany
We extend Marcuse analysis of pulse fluctuations of randomly phased multimode sources to arbitrary chromatic dispersion, chirp, finite mode linewidth, mode partition noise and finite receiver bandwidth. On long fibers the fluctuations depend only on the shape of the group delay curve, a monotonic delay separates the modes, whereas a symmetric delay leaves pairs of modes with identical intensity profiles and a persistent beat noise. Dispersion downconverts the beats of overlapping modes to baseband, where receivers cannot filter them. The detected power follows random phasor statistics, and Gaussian estimates of fade probability can be wrong by orders of magnitude. Mode partition noise grows with dispersion and dominates in band limited links.
Read the full abstract ▾
Artificial Intelligence
Kecheng Liang, Haoyang Liu, Zexin Chen et al. (+5 more)
A key challenge in physics diagram understanding is correctly associating visual information with the physical entities, relations, and conditions it describes. Even when a value, symbol, or other local element is accurately recognized, assigning it to the wrong entity or scope can distort the underlying physical premise and lead to incorrect
reasoning. To systematically study this challenge, we introduce PhysAlign, a
benchmark designed to assess whether
multimodal models correctly associate information recognized from physics diagrams with its intended physical role. By disentangling visual recognition from physical-role assignment through localized probes and controlled variants, PhysAlign isolates correspondence errors from recognition failures. It contains 3,341 human-validated probes spanning 986 physics problems, enabling systematic evaluation of visual recognition and physical-role correspondence at scale. We further introduce five complementary evaluation metrics, including CAcc, GAcc, and JAcc, which provide a comprehensive assessment of models' ability to recognize diagram content, establish correct physical correspondences, and solve the underlying physics problem. Across our evaluated
multimodal models, PhysAlign reveals a consistent gap between local visual recognition and physical-role grounding. Even when the queried content is correctly recognized, the conditional correspondence error rate remains 13.8% for GPT-6-Astra and rises to about 50.6% for InternVL3.5-8B. These findings indicate that strong perception alone does not ensure reliable physical interpretation, exposing a distinct grounding bottleneck that is largely hidden by answer-level accuracy and highlighting the need for future models to better align recognized visual evidence with its physical meaning.
Read the full abstract ▾
All authors Kecheng Liang, Haoyang Liu, Zexin Chen, Zirong Liu, Weixing Chen, Qiufeng Wang, Yang Liu, Liang Lin
Computer Vision
PIC-UIE: Predicting Image-Adaptive Corrections for Lightweight Underwater Image Enhancement
Cunhao Zhu, Dongliang Xu, Xiangtao Kong et al. (+3 more)
Underwater image enhancement (UIE) aims to restore visibility, color fidelity, and structural detail from images degraded by wavelength-dependent attenuation and backscatter. State-of-the-art UIE methods often rely on large backbones and dense image-to-image prediction, limiting their practicality for edge deployment. Moreover, operating entirely in a single color space couples degradation estimation with luminance and chroma correction. To address these challenges, we propose PIC-UIE, a lightweight predictor–executor framework that predicts image-adaptive corrections from a fixed $256\times256$ RGB thumbnail and applies them to the native-resolution input in the YCbCr color space. The predictor produces seven outputs, organized into spatial correction, nonlinear luminance and coupled chroma mapping, and image-level color calibration. A depth map regularizes the transmission proxy during training, whereas inference uses only the RGB input. With 9,486 parameters and 0.094 GFLOPs at $256\times256$, PIC-UIE achieves 24.137 dB PSNR and 0.9216 SSIM on UIEB-90 and 21.320 dB PSNR on zero-shot LSUI. It further processes native 4K images at 55.0 FPS under the comparison protocol. These results show that structured correction prediction provides an effective and practical alternative to dense RGB reconstruction for
underwater image enhancement.
Read the full abstract ▾
All authors Cunhao Zhu, Dongliang Xu, Xiangtao Kong, Xiaoyan Lu, Tianyu Wang, Yue Yao
Solar and Stellar Astrophysics
Modeling of the variability of D-region ionospheric electron density during solar cycle-24
Sayak Chakraborty, Sourav Palit, Semontee Deb et al. (+1 more)
Solar cycle variation of earth's atmosphere, particularly the ionosphere is of particular interest in the field of space science and space weather studies. In this article, we present the outcome of our detailed quantitative study on
solar cycle variation of lower ionospheric properties using numerical investigation. First, we seek to model and compare the collective D-region ionization rates (q's) due to the individual contributions from the ionizing sources, namely, (a)
solar extreme ultraviolet (EUV) radiation including the Lyman-alpha irradiation and (b)
solar X-ray irradiation throughout the 24th
solar cycle (C24). Then, we compute the electron density (Ne) profiles using the ionization rates. We report significant
solar cycle variation in ionization rate and electron density profiles for the entire span of C24. We use the sunspot number (SPN) profile to substantiate the finer details of Ne profile during C24. For the segments of the D-region above two different geographic coordinates, we report that Ne profiles show a consistent "dual peak" nature. It is very similar to the SPN profile during C24. As a next-order validation, we compare our modeled Ne profiles with their IRI-2020 counterpart (Ne,iris). Their overall trends are found to be in agreement. Finally, we discuss the response of the D-region in terms of Ne due to C24. The work lays the foundation for our upcoming studies on D-region response to
solar cycle variation with Very Low Frequency (VLF) observation.
Read the full abstract ▾
All authors Sayak Chakraborty, Sourav Palit, Semontee Deb, Tamal Basak
Analysis of PDEs
Forward self-similar solutions of the Navier-Stokes equations in R^n
Baishun Lai, Changxing Miao and Xiaoxin Zheng
We investigate forward self-similar solutions to the incompressible Navier–Stokes equations with homogeneous initial data $u_0(x)=\sigma(x/|x|)/|x|$, $x\in\mathbb R^n$, focusing on the critical four-dimensional case. For the existence theory in dimensions $3\leq n\leq5$, we develop a Galerkin scheme for the Leray profile problem, featuring a decomposition of the self-similar data and nonlocal heat kernel effects across spatial scales. Exploiting the structural properties of the data and the coercivity of the Leray operator, we derive uniform a priori estimates, pass to the limit, and obtain weak forward self-similar solutions. In the 4D case, we prove new Stokes-type estimates for the linear Leray system. The inverse Leray operator admits an integral representation as a singular integral operator; its $L^p$-boundedness follows from Calderón–Zygmund theory. Combined with a 4D compactness estimate for the convective term, this closes the regularity iteration. For spatial decay, we reformulate the problem in weighted spaces. The non-integrability of the low-frequency kernel causes a logarithmic loss under $\sigma\in W^{1,\infty}(\mathbb S^3)$. With $\sigma\in C^{1,\gamma}(\mathbb S^3)$, $0<\gamma<1$, frequency-localized estimates remove this loss and yield sharp decay.
Read the full abstract ▾
Distributed Computing
AgentLoop: Runtime Control of Slot-closed Execution Loops for Tool-augmented LLM Agents
Wanyi Zheng, Minxian Xu, Kan Hu et al. (+2 more)
Tool-augmented large
language model (LLM)
agents are becoming an important execution unit in service computing, but existing
agent loops still lack explicit runtime signals for assessing task completion. The challenge lies in the fact that an
agent may continue
reasoning or invoking services even after the runtime context has stopped changing, while evidence already collected remains unsynthesized into a complete answer, which leads to inefficiency in resource usage. To address these challenges, this paper presents AgentLoop, which provides runtime control of slot-closed execution loops for tool-augmented
agents. Slot closure means that the information slots required by a request have been covered by sufficient runtime evidence, and that unresolved slots are explicitly identified before the loop stops. AgentLoop converts open-ended
agent iteration into state-driven execution control: it maintains a compact runtime state, uses model-assisted structured verification to check answer completeness and missing evidence, and applies bounded stability and low-gain signals over neighboring LLM/tool rounds before selecting one of three actions: Continue Invocation, Answer Synthesis, or Terminate Iteration. Experiments show that AgentLoop reduces redundant execution and context growth, with total
token cost reduced by up to 88.44% and average service invocations reduced by up to 76.85% against baselines. The ablation study further shows that the slot-centered control path plays a central role, since disabling it increases execution depth and substantially reduces accuracy. Overall, the results suggest that efficient tool-augmented
agents can benefit from explicit runtime signals for deciding when further LLM/tool iterations no longer add useful context or supported evidence.
Read the full abstract ▾
All authors Wanyi Zheng, Minxian Xu, Kan Hu, Kejiang Ye, Chengzhong Xu
Machine Learning
ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models
Zhongjian Zhang, Xiao Wang, Busheng Zhang et al. (+5 more)
Zero-shot graph models (ZGMs), which learn transferable knowledge from source graphs and directly apply to unseen target graphs without any adaptation, have achieved promising performance and attracted considerable
attention. Despite their proliferation, existing ZGMs are predominantly evaluated on clean graphs, while existing graph robustness
benchmarks mainly focus on supervised settings, leaving a fundamental question largely unexplored: How robust are ZGMs when their unseen target graphs are exposed to
adversarial manipulation? In this paper, we answer this question by proposing ZeroGAR, the first systematic
benchmark for evaluating the
adversarial robustness of ZGMs. ZeroGAR evaluates 13 representative ZGMs from 3 different paradigms on 8 graph
datasets across 4 domains, covering both in-domain and cross-domain transfer under structural, textual, and node injection attacks with multiple perturbation budgets. It further investigates whether existing graph defenses remain effective in the zero-shot setting. Extensive experiments reveal that strong clean zero-shot performance does not guarantee
adversarial robustness, with three key findings: (1) Vulnerability patterns are related to model prediction mechanisms: GNN-based methods are particularly vulnerable to structural and node injection attacks, whereas LLM-based methods are more vulnerable to textual attacks; (2) Stronger LLM backbones introduce a structure-text robustness trade-off; (3) Existing graph defense methods do not consistently improve zero-shot robustness and may compromise clean performance. We hope that ZeroGAR will facilitate rapid, equitable evaluation and inspire further innovative research in ZGM security.
Read the full abstract ▾
All authors Zhongjian Zhang, Xiao Wang, Busheng Zhang, Bo Yan, Xingtong Yu, Yue Gao, Jia Li, Chuan Shi
Symbolic Computation
The Moment Method for Computing Real Points of Sparse Polynomial Systems
Tom Baumbach and Matías Bender
One of the most important problems in computational
algebra is the computation of real solutions of a
polynomial system. Lasserre, Laurent, and Rostalski introduced a numerical method to compute the real radical of an ideal defining a finite set of real points. Their method is based on moment
matrices and reduces the problem to solving a semidefinite program. In this work, we build on this method and on the work of Laurent and Mourrain to exploit the sparsity of the input
polynomials. For this purpose, we extend the theory of moment
matrices to the setting of affine toric varieties. We prove that, for sparse
polynomial systems, this approach allows us to recover real points on affine toric varieties. Moreover, we show that a projection of the spectrahedron associated with the semidefinite program is, in fact, a polytope, and we propose a variation of the method to compute only one real solution of the system.
Read the full abstract ▾
Game Theory
When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions
Dipankar Sarkar
Moving ML-mediated decision making onto
privacy-preserving clients decentralises the economic decision along with the inference. Shared budget constraints then depend on information that cannot be globally current, creating an information-structure failure that conventional pacing is not designed to solve. We study this information misalignment in an auction-logic-faithful on-device simulation with 36 campaigns and 50 devices. Accounting is in dimensionless integer score units; no currency semantics are claimed. Across 30 paired demand paths, proportional Even pacing overspends 17.77% after one tick of staleness and 1,669.31% after 50 ticks under the original 20-times budget pressure. The effect does not depend on that severe a budget: at two-times pressure, 50-tick overspend remains 106.95%. A visible-budget no-sale guard makes zero-lag compliance exact at this score-unit granularity, yet leaves 11.88% overspend at one tick because other devices' debits remain invisible. A declared bursty, heterogeneous-device sweep retains a strictly increasing mean lag curve. We derive a finite-window expected excess-debit bound under conditional charge caps and find positive paired slack in every bounded-value
cell. A second, incentive misalignment arises when the ML/pacing score transformation is allowed to change payment units: 98.23% of rival auctions at one tick admit a profitable deviation. An executable implementation-level counterexample isolates the runner-up's multiplier in the winner's price. Critical-base-bid payment is per-auction DSIC conditional on current multipliers, but does not establish dynamic truthfulness and does not repair base-value ranking disagreement.
Read the full abstract ▾
Robotics
SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation
Chengqun Yang, Tengjie Zhu, Liang Xu et al. (+10 more)
Humanoid robots are increasingly expected to serve as
embodied social
agents that communicate naturally with humans through face-to-face interaction. During such communication,
humanoid robots require body behaviors that are synchronized with
speech, affectively expressive, and suitable for real-time execution. However, existing co-
speech methods are primarily developed for digital humans and lack joint support for affective control and low-latency continuous generation on physical embodiments. To bridge this gap, we present SocialHumanoid, a system for expressive
humanoid behavior via one-step co-
speech motion generation. Given response
speech and a specified affective condition, SocialHumanoid generates each full-body motion window in a single forward pass and connects successive windows through motion-history conditioning. The generated human motion is further converted online into embodiment-compatible
robot references and tracked by a whole-body controller for physical execution. To provide explicit supervision for affective body expression, we further introduce AffectMoCap, a 4-hour
dataset captured from two professional actors, containing synchronized
speech, body motion, fine-grained hand motion, and
emotion annotations. On BEAT2, SocialHumanoid achieves the best FGD among the compared generation methods, competitive
speech-motion synchrony, and approximately $6\times$ faster inference than GestureLSM under the same protocol. Perceptual evaluations further show that training with AffectMoCap improves affect recognition from generated body motion, while real-
robot experiments demonstrate continuous affect-conditioned behavior and stable long-horizon execution. Our project page is https://rex0191.github.io/SocialHumanoid/.
Read the full abstract ▾
All authors Chengqun Yang, Tengjie Zhu, Liang Xu, Fulong Liu, Guanzhu Ren, Yitong Xing, Xuefeng Lu, Fei Shi, Siyuan Fan, Weijie Dong, Yao Mu, Xiaokang Yang, Yichao Yan
Robotics
CompliantWBC: Whole-Body Compliance for Heavy Humanoids via Force Latent Estimation and Residual Impedance Targets
Tan-Dzung Do, Cuc T.Trinh, Tuan Dat Phuong et al. (+4 more)
Whole-body compliant control is essential for deploying heavy
humanoids under high payload in human-centric environments. Most prior force-aware learning-based pipelines focus on end-effector resistance, per-link upper-body springs, or end-effector stiffness modulation, leaving arbitrary-site perturbations on heavy platforms with lower-body engagement largely unaddressed. We close this gap with CompliantWBC comprising: (1) A base policy trained with RL to maximize compliance-fidelity reward, guided by a multi-site whole-body impedance reference controller, extending classical Cartesian impedance to any controlled link; (2) A bounded residual policy that edits the per-link impedance
equilibrium over a frozen base, correcting the coarse but structured wrench estimate supplied by a force encoder co-trained behind a gradient barrier; (3) A Phong-weighted force-origin sampler with an axis-decoupled pelvis anchor induces lower-body-inclusive compliance curriculum training via two interpretable parameters. We evaluate CompliantWBC in simulation against both compliant and stiff baselines, achieving best compliant fidelity of 2.58cm deviation from analytical solutions, and demonstrate it on a real heavy
humanoid across static/dynamic force reaction, board wiping, squat under payload, and cooperative payload transport. Project website: https://dotandung.github.io/compliantwbc/
Read the full abstract ▾
All authors Tan-Dzung Do, Cuc T.Trinh, Tuan Dat Phuong, Chien Le, Thanh Ly, Vien Anh Ngo, An Thai Le
Geometric Topology
Satellites and invariants of links
Sergey A. Melikhov
An invariant $v$ of $m$-component links is called "cableable" if there exists a $k$ such that whenever a link $L'$ is obtained from a link $L=(K_1,\dots,K_m)$ by replacing each
knot $K_i$ with its $(p_i,q_i)$-cable for some $p_i$ and $q_i$, we have $v(L')=(p_1\cdots p_m)^kv(L)$. The following problem is implicit in a number of papers by P. M. Akhmetiev and originates from the Arnold-Moffatt program for finding topological lower bounds for the energy of a
magnetic field: Does there exist a cableable finite type invariant of links in $S^3$ which is not a function of the pairwise linking numbers? According to Akhmetiev, he solved this problem himself, with the desired invariant being defined for $3$-component links as an analytic expression involving a
magnetic field modeled on the given link. We offer a different solution, with the desired invariant for $m$-component links, $m\ge 3$, being a function of the coefficients of the Conway
polynomial of the link and its sublinks; the function is given explicitly when $m=3$. Moreover, we show that the cables can be replaced by arbitrary satellites. Much of the proof is a study of low degree coefficients of the Conway potential function $\Omega_L(x_1,\dots,x_n)$ expanded as a formal power series in Conway's variables $z_i=x_i-x_i^{-1}$. We also discuss type $n$ invariants which are "cableable up to an invariant of type $n-1$", some cableable invariants which are not of finite type (particularly a certain modification of Milnor's $\bar\mu$-invariants), and applications to links of solenoids.
Read the full abstract ▾
Cryptography and Security
SweepSketch: Detecting Carpet-Bombing Attacks Before They End
Yutong Yan, Sijia Du, Haowei Wang et al. (+1 more)
Carpet-bombing DDoS attacks spread traffic almost uniformly across a destination prefix, keeping each host below alarm thresholds while exhausting prefix-level resources; spoofed sources make source-side evidence unreliable. Existing detectors either decide on windows of seconds, alarming only at window boundaries, or depend on supervised training, so short attacks often end before the first alarm. We present SweepSketch, a destination-anchored, per-packet sketch detector that keeps no source-side state, needs no training, and alarms while the attack is still in progress. Its core is a tagged self-cleaning windowed HyperLogLog (T-HLL) that turns uniformity testing into one event per distinct destination per window; per-packet cumulative-sum (CUSUM) decisions and dual exponentially weighted moving average (EWMA) gates form the decision chain. The reference state occupies 512 KB, and a bit-exact C++ implementation reaches 13.2 Mpps per core. On attacks lasting only 0.5 s, it raises its first alarm before the attack ends in 95.6% of attacks; on real captures, 49.3% alarm within the first second; static and mixed-traffic F1 both reach 0.991. SweepSketch is deployed in two hardware forms: a Tofino2 program carries the complete per-packet state chain and places the final gates on the control plane, while a DPU micro-engine keeps the entire decision chain in the fast path.
Read the full abstract ▾
All authors Yutong Yan, Sijia Du, Haowei Wang, Bo Yang
Other Quantitative Biology
A mechanistic interpretation of mutation risk across biological scales
Satavisha De and B Vibishan
The allometry of cancer risk in mammals is scale-specific, as the inter-specific, intra-specific, and inter-organ patterns in cancer risk scaling are distinct from each other. While cancer risk barely changes with increasing body sizes across species, larger conspecifics are known to be at a higher risk of cancer. Cancer risk trends with age and lifespan have likewise been documented in humans and other species. Nevertheless, mammals broadly share developmental features, and the twin processes of
cell division and differentiation are central to developmental dynamics. In this study, we suppose that a better understanding of these processes across biological scales could lead to a clearer understanding of cancer risk allometries. We develop an
agent-based model in which a
cell compartment grows from one
cell to a target size. We assess how developmental dynamics scale with compartment size and influence mutation accumulation. Our data identify specific regions of the parameter space where the accumulation of neutral mutations increases with
cell number, while providing a mechanistic explanation for such behavior. The accumulation of non-neutral mutations reveals an interesting antagonism in
cell fitness between mutation and differentiation, which could change the viability of a given developmental strategy. Our model is able to produce a wide range of trends in cancer risk allometries in different parts of its parameter space, reflecting the observed heterogeneity across biological scales. Our results provide a theoretical framework that allows us to elucidate the conditions of mutation-differentiation balance under which having more
cells does lead to higher cancer risk, and importantly, the conditions under which it does not.
Read the full abstract ▾
Computer Vision
LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking
Liang Peng, Chenxiao Li, Libo Zhang et al. (+2 more)
Current
Transformer-based tracking methods typically stack multiple
Transformer blocks with separate parameters to model interactions between the target template and the search region for target localization. These trackers often incur substantial parameter overhead from stacked blocks, making their deployment on resource-limited devices difficult. To address this, we propose a parameter-efficient
Transformer tracking framework, dubbed LoopTrack, which repeatedly applies a set of
Transformer blocks with shared parameters to interact features in a looped architecture for tracking, significantly reducing the number of parameters. To further exploit target cues, we present two lightweight designs, including target-aware looping (TAL) and gated target
memory (GTM). The former applies intermediate target information generated by one loop to guide feature interaction in the subsequent loop, enabling progressive feature refinement, while the latter maintains a compact
memory across frames, which is incorporated into the loop process to provide long-term information to the tracker, mitigating temporal drift in tracking. Compared to existing
Transformer trackers, LoopTrack enables multiple rounds of feature interaction with fewer model parameters, making it resource-friendly for deployment. In extensive experiments on multiple
datasets, LoopTrack shows a favorable accuracy-parameter trade-off. In particular, our LoopTrack$_{\rm One}$, with a single shared
Transformer block, achieves 66.2% SUC score on LaSOT with only 3.4M parameters, while LoopTrack$_{\rm Three}$, using three shared blocks, achieves 69.3% SUC score with 6.4M parameters, surpassing existing parameter-efficient tracking methods with comparable or larger model size. With LoopTrack, we aim to establish a simple yet strong baseline for parameter-efficient
Transformer tracking. Our code and models will be released.
Read the full abstract ▾
All authors Liang Peng, Chenxiao Li, Libo Zhang, Xingping Dong, Heng Fan
Signal Processing
A Low-Dimensional Riemannian Alternating Optimization Algorithm for BD-RIS-Assisted Multiuser Beamforming
Weitao Xia, Zheyu Wu and Ya-Feng Liu
This paper investigates joint active and passive beamforming for a multiuser downlink system assisted by a fully-connected beyond-diagonal reconfigurable intelligent surface (BD-RIS). Since the number of tunable components grows quadratically with the number of RIS elements, directly optimizing the full scattering
matrix becomes increasingly computationally expensive. To address this challenge, we first derive an equivalent low-dimensional formulation that replaces the full scattering
matrix with a variable whose number of columns equals the number of users. We further establish a smooth
manifold structure on a dense subset of the equivalent feasible set, based on which we develop a low-dimensional Riemannian alternating optimization (LD-RAO)
algorithm, where the passive variable is updated using a single Riemannian gradient ascent step at each iteration. The convergence of LD-RAO is established under mild assumptions. Numerical results demonstrate that the proposed
algorithm achieves the same performance as the existing state-of-the-art (SOTA) full-dimensional methods with significantly less CPU time, particularly for large-scale BD-RIS.
Read the full abstract ▾
Computer Vision
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
Fuyao Zhang, Xuan Wang, Zherui Li et al. (+3 more)
Personal Graphical User Interface (GUI)
agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing approaches retrieve task-relevant history and append it to the policy's context, implicitly assuming that experience relevant to a task remains useful for each decision within it. We find that this help is largely spent at the first decision: retrieved history strongly improves the opening step of an episode, yet provides little sustained benefit over the remaining 90% of steps, and offers weak guidance on whether a proactive suggestion is warranted. A relevant record may tell the
agent where to begin, but not which past action applies to the current screen or whether a routine is due now. The underlying issue is that relevance does not imply applicability}: relevance is determined at the task level, whereas applicability depends on the situation at decision time. We therefore recast personalization as experience activation and introduce ExpActivator, a training-free framework that activates only the experience applicable to the current situation. During execution, ExpActivator matches each new screen to historical states in the frozen GUI backbone's latent space and supplies the corresponding action as a reference. Before execution, it activates a recurring intent only when the current time and scenario provide sufficient support, and otherwise abstains. Across four GUI backbones, ExpActivator improves within-trajectory step success by 28% on average, achieves the best personalized execution on every backbone while using about one-fifth as many history
tokens, and reaches approximately 2.3$\times$ the Matthews correlation coefficient of the strongest proactive baseline. Experience pays where it is activated, not where it is appended.
Read the full abstract ▾
All authors Fuyao Zhang, Xuan Wang, Zherui Li, Jiaming Zhang, Longtao Huang, Wei Yang Bryan Lim
Machine Learning
BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting
Kangjia Yan, Linfeng Wang, Tianen Shen et al. (+7 more)
Despite recent progress in irregular time series
forecasting, the field still lacks a unified
benchmark for fair and comprehensive evaluation. Existing evaluations are often conducted on a limited set of
datasets with inconsistent experimental protocols and predominantly error-based metrics, rendering it difficult to compare and assess methods fairly and comprehensively across diverse settings. To eliminate these limitations and accelerate progress, we propose BITS, a standardized, reproducible, and extensible
benchmark for advancing research on irregular time series
forecasting. BITS covers eleven
datasets from nine domains with diverse irregularity characteristics, and it characterizes the
datasets according to their missing rate, missing pattern complexity, sampling irregularity, and skewness. Further, it offers a unified pipeline for data preprocessing, model integration and evaluation, and reporting. It accommodates regular and irregular time series
forecasting methods, including time series foundation models, under consistent settings, incorporating both error-based and non-error-based evaluation metrics. Findings include that method performance varies substantially across irregularity characteristics, with no single modeling strategy consistently dominating. We also find that using error-based or non-error-based metrics can yield different model rankings, highlighting the need for multi-dimensional evaluation. The code can be found at https://anonymous.4open.science/r/BITS-8F2E/.
Read the full abstract ▾
All authors Kangjia Yan, Linfeng Wang, Tianen Shen, Xiangfei Qiu, Ruitong Zhang, Hao Miao, Jilin Hu, Chenjuan Guo, Bin Yang, Christian S. Jensen
Materials Science
Low-temperature thermal expansion of the $\alpha$ and $\omega$ phases of titanium
Norimasa Nishiyama, Atsushi Togo and Yoshitaka Matsushita
We investigated the low-temperature thermal expansion of the $\alpha$ phase and the $\omega$ phase, a high-pressure polymorph of titanium, by X-ray diffraction measurements from approximately 5 to 300 K, together with first-principles calculations. Single-phase bulk polycrystalline $\omega$-Ti was synthesized at 7.7 GPa and 500 $^\circ$C and recovered to ambient pressure. Although the two phases exhibit very similar volumetric thermal expansion, their axial responses are markedly different. In $\alpha$-Ti, the $c$-axis thermal expansion coefficient becomes negative below approximately 50 K and reaches a minimum of $-0.71 \times 10^{-6}$ K$^{-1}$ at 20 K. Both experiment and theory indicate substantially smaller $c$-axis negative thermal expansion than previously reported from single-
crystal length measurements. In contrast, $\omega$-Ti expands nearly isotropically along the $a$ and $c$ axes, and its $c/a$ ratio remains nearly temperature independent and close to the ideal bcc-derived value. The $c$/$a$ ratio of $\alpha$-Ti decreases with increasing temperature. Debye-Grüneisen analysis yielded Debye temperatures of $427 \pm 5$ K and $409 \pm 12$ K and effective Grüneisen parameters of $1.33 \pm 0.04$ and $1.23 \pm 0.04$ for $\alpha$-Ti and $\omega$-Ti, respectively. The first-principles calculations reproduce the volumetric thermal expansion of both phases and capture the overall trends of their axial responses.
Read the full abstract ▾
Computation and Language
Jianguo Huang, Lipeng Wan, Yanchen Deng et al. (+1 more)
Diffusion large
language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a
token at every masked position, but the decoder commits only a confident subset of these proposals. Trace-based on-policy
distillation (TOPD) builds on this process by matching the student to a stronger teacher, yet only at the committed positions. We argue that this discards much of the useful signal, which resides in the uncommitted proposals, where the student has made a prediction but is not yet confident enough to commit it. We call these proposals hesitations. In our pilot study on an SDAR-4B student, hesitations make up only 24% of supervisable state-position pairs but carry 66% of the teacher-student divergence. To exploit this signal, we propose Hesitation-Aware On-Policy
Distillation (HOPD), which extends teacher distribution matching to every masked position of each denoising step. Because hesitations are not equally informative, we further allocate supervision using hindsight from the completed trajectory, placing more weight on positions whose proposal was later disagreed with the final
token and on blocks where first-step proposals rarely survive. Since both models already produce distributions at all masked positions, HOPD requires no additional forward passes over TOPD. The only extra cost is evaluating the loss at more positions. With SDAR-1.7B and SDAR-4B students distilled from TraDo-8B-Instruct, HOPD achieves the best average score among the evaluated methods on five math and coding
benchmarks, under both static and dynamic decoding and at both scales. It also speeds up decoding. On SDAR-4B, the HOPD student hesitates less and commits 11% more
tokens per denoising step than TOPD, while reaching higher accuracy.
Read the full abstract ▾
All authors Jianguo Huang, Lipeng Wan, Yanchen Deng, Bo An
Complex Variables
A Converse to the Skoda $L^2$ division theorem II
Zhi Li, Xiankui Meng, Jiafu Ning et al. (+1 more)
We prove a converse to the original Skoda $L^2$ division
theorem, asserting that Skoda $L^2$ division estimates for a single nonzero holomorphic function force the weight to be plurisubharmonic. In addition, we establish corresponding results for higher-rank quotient bundles. Finally, we derive an optimal $L^2$ extension
theorem directly from the division estimates.
Read the full abstract ▾
All authors Zhi Li, Xiankui Meng, Jiafu Ning, Xiangyu Zhou
Robotics
AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents
Cunhao Zhu, Yifeng Wang, Dongliang Xu et al. (+3 more)
World Action Models (WAMs) are becoming increasingly important and useful for
embodied intelligence, as they enable
robots to anticipate the consequences of candidate actions before interacting with the physical environment. However,
underwater robots are usually subject to passive dynamics, such as inertia, buoyancy, hydrodynamic drag, and persistent drift, which can continue to affect the vehicle even after an action is completed. Existing WAMs, which primarily predict action-conditioned visual observations, are not explicitly designed to capture such passive motion dynamics. In this paper, we present AquaWAM, the first World Action Model designed for
underwater embodied agents. Instead of predicting future images, AquaWAM models both action-conditioned and passive physical dynamics, including the thruster dead band, the inertial glide that outlasts each command, and ambient currents. Specifically, it senses through the DVL, IMU, pressure sensor and joint encoders, while cameras supply only semantics for understanding goals and target pose. By modeling compact
navigation states rather than high-dimensional visual observations, AquaWAM substantially reduces the model size and computational cost compared with conventional WAMs. Experimentally, AquaWAM achieves a 72.6% task success rate across 20
underwater tasks on the USIM
benchmark, outperforming existing methods while making action decisions 2.7x faster than U0 on an NVIDIA Jetson AGX Orin. Our model also remains effective when some onboard sensor measurements are unavailable. For example, without DVL velocity measurements, our method still achieves a 61.6% success rate, compared with 39.4% for U0.
Read the full abstract ▾
All authors Cunhao Zhu, Yifeng Wang, Dongliang Xu, Yunzhong Hou, Yue Yao, Chi Harold Liu
Machine Learning
Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs
Fansheng Zhang, Shengran Guo, Zexiao Wang et al. (+3 more)
In many settings, post-training need not create the target behavior from scratch: the base model can already produce it, but not reliably. This shifts part of preference
alignment from capability acquisition to behavioral expression. We ask how a specified preference is represented in native model computation, what prevents target-supporting computation from reliably dominating generation, and whether this structure can directly guide control. We introduce Residual Competition Maps (RCMs), which map a behavioral preference onto signed causal effects of native residual computation. Across preference domains, RCMs reveal coexisting target-supporting and target-competing effects, input-dependent component roles, and cases where a single native-component intervention reverses the preference outcome. DPO substantially reorganizes these effects and can weaken opposition without guaranteeing its removal. We then propose Direct Hidden-State
Alignment (DHSA), which treats inference-time hidden states rather than base-model weights as the direct adaptation space. RCM-guided Causal Activation State Transition (CAST) implements DHSA through local state interventions at a small number of preference-relevant interfaces while freezing the base model. With only 256-16,384 controller parameters, CAST reaches DPO-competitive operating points across three preference domains, can complement DPO-trained models, and can be enabled or removed at inference time.
Read the full abstract ▾
All authors Fansheng Zhang, Shengran Guo, Zexiao Wang, Liang Yuan, Jiyuan Chen, Ruikun Luo
Artificial Intelligence
The Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization
Yiguo Wang, Ziyuan Yang, Yi Zou et al. (+3 more)
Verifying multi-step LLM
reasoning requires more than determining whether a trace is correct: a useful verifier should identify where the
reasoning first goes wrong. However, existing holistic methods provide little positional evidence, while forward sequential verification often treats the first rejected step as the error source. Under error propagation, this assumption can fail, since an earlier mistake may remain locally plausible and become observable only through its downstream consequences. We therefore rethink
reasoning verification as a progression-aware error-source localization problem: rather than asking only where a
reasoning trace first appears inconsistent, we ask which earlier step best explains how that inconsistency emerges along the trajectory. Based on this view, we propose Progression-aware
Reasoning Origin (PRO), a training-free framework for first-error localization. PRO jointly models incoming support from the preceding context and outgoing compatibility with subsequent
reasoning, selectively refines regions where these signals disagree, and finally performs detector-conditioned source attribution with intervention-based evidence to distinguish the true error origin from its propagated manifestations. We further formalize the gap between forward rejection and structural exposure, showing why incoming-side evidence alone is insufficient for reliable localization under error propagation. Experiments across open-form, medical, and structured
reasoning tasks demonstrate consistent improvements over strong verification baselines, supporting progression-aware source attribution as a more faithful formulation of
reasoning verification.
Read the full abstract ▾
All authors Yiguo Wang, Ziyuan Yang, Yi Zou, Dan Lin, Rongsheng Li, Yi Zhang