Computer Vision
Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems
Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory et al. (+2 more)
Preprocessing-based defenses are the standard first-line response to
adversarial attacks on edge
vision systems, requiring no retraining, no architectural changes, and widely recommended as model-agnostic mitigations. Yet the foundational evaluations of these defenses were conducted on residual or Inception-class architectures, not on the depthwise-separable CNNs that dominate edge deployments. This untested assumption leaves a gap in the security evaluation literature. This paper closes that gap by evaluating six preprocessing defenses against
adversarial perturbations across both architecture families. Across all perturbation levels and defenses tested, the two depthwise-separable architectures show consistently poor recovery while the residual architecture shows partial recovery; ablation results are consistent with an architectural rather than parametric explanation, though only three architectures and one attack family are evaluated. Crucially, this failure is not merely a negative result. The same output divergence that disqualifies preprocessing as a recovery mechanism reveals a detection opportunity: preprocessing consistently disrupts clean predictions while leaving
adversarial predictions largely unchanged, an asymmetry that is directly measurable without retraining or architectural modification. We further show that standard image quality metrics are unreliable proxies for defense effectiveness, a methodological gap in current evaluation practice. A practitioner decision framework is provided for adversarially resilient edge
vision deployment.
Read the full abstract ▾
All authors Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory, Md. Saifur Rahman, Khondokar Fida Hasan
Information Retrieval
Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory
Kazuki Nakayashiki
A model that inherits one-line
memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or both. Across sixteen registered studies (179,352 attempts) we measured where the request goes under each form; every result is descriptive, with registered intervals, no mechanism claim. A length-matched criterion exceeded a bare id on six direct-provider models (D) and failed its registered superiority rule on a nine-model OpenRouter panel (E). On generated worlds (K2-K5): the two registered signatures held on Opus 5 and Fable 5.1, Fable 5 followed the same sign, Haiku 4.5 reversed, and Sonnet 5, the GPT-5.6 endpoints and GPT-6 Astra lay near zero (K2). With a defensive adapter at five gains, the 70B rule for a gain-dependent change of the composite - criterion contrast was not met (K3 and K4); under the 8B attenuation rule (0.95 intervals: slope below zero; change beyond the margin), the 8B change of -17.5 [-26.7, -8.1] did not meet it on 36 families (K4) and at registered power on 337 families -16.6 [-19.4, -13.8] did (realised one-sided error at the margin 1.8 to 3.2% per corner of a finite grid, nominal 2.5%, not a uniform-error guarantee; K4's status stands; K5, first ladder), while a second SecAlign++ adapter under the imposed Meta-SecAlign template did not (-11.8 [-14.3, -9.3]; K5, second ladder); no NOT-MET is a statement that the contrast was unchanged; their difference (+4.7 [+2.3, +7.2]) describes two fixed execution paths, licenses no superiority, equivalence or 'significant difference' claim; nothing follows from the statuses differing (K5). Intervals describe family-reweighting stability conditional on the execution, not reproducibility across engine executions; audit replays were neither substituted for nor averaged into outcomes; no missingness gate fired and directional completions changed no status.
Read the full abstract ▾
Computer Vision
STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface Reconstruction
Bocheng Li, Wenjuan Zhang, Jie Pan.Dongxu Han et al. (+3 more)
Large-scale 3D surface reconstruction from aerial imagery is fundamental to geospatial mapping and urban modeling. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated considerable potential for this task. However, existing methods still face three major challenges in large and complex scenes: scene partitioning may split continuous scene elements across independently optimized sub-regions;
geometric constraints mainly focus on the attributes of individual Gaussians while overlooking their local organization; and uniform regularization struggles to accommodate heterogeneous
geometric structures. To address these issues, we propose
STARS-GS, a structure-aware 3DGS framework for large-scale surface reconstruction. First, we introduce a structure-aware scene partitioning strategy that better preserves continuous scene structures during partitioning and reduces cross-region
geometric inconsistencies and stitching artifacts through boundary refinement. Second, we develop neighborhood-aware Gaussian organization that extends
geometric constraints from individual primitives to their neighborhood organization, encouraging Gaussians to better conform to local surface geometry. Third, we introduce adaptive surface regularization that adjusts the regularization strength according to local
geometric characteristics, promoting
geometric consistency in structured regions while preserving plausible variations in unstructured regions. Extensive experiments on large-scale aerial photogrammetry
benchmarks demonstrate that
STARS-GS consistently outperforms the evaluated Gaussian-based methods in surface reconstruction. It increases the average F1-score from 0.640 for the second-best method to 0.698, corresponding to a relative improvement of approximately 9.1%, demonstrating effective improvements in
geometric accuracy and surface completeness.
Read the full abstract ▾
All authors Bocheng Li, Wenjuan Zhang, Jie Pan.Dongxu Han, Xuesong Ma, Yiling Yao, Yaning Wang
Computer Vision
Preserving Knowledge across Space and Time for Continual Video Deepfake Detection
Taehoon Kim, Jongwook Choi, Heejae Jo et al. (+2 more)
The continuous emergence of high-quality
video deepfakes requires detectors that continually adapt to new forgery patterns, yet existing approaches, which are designed for deepfake images, fail to capture
video-specific cues. Unlike deepfake images that contain only spatial artifacts, deepfake
videos leave distinct evidence along both spatial and temporal axes, necessitating the separate preservation of each modality during sequential model updates. To overcome this limitation, we introduce a continual deepfake
video detection framework, Modality-Specific Frequency
Distillation (MSFD), that explicitly decomposes
video features into spatial, temporal, and spatiotemporal modalities in the frequency domain. This decomposition enables independent preservation of each modality, as different deepfake
video types exhibit varying reliance on spatial and temporal cues across tasks. Furthermore, MSFD adopts a cross-modality decorrelation loss that encourages spatiotemporal representations to remain orthogonal to single-modality cues. Extensive experiments show that our framework achieves stronger adaptation and preserves performance more effectively than state-of-the-art methods across diverse continual deepfake
video scenarios.
Read the full abstract ▾
All authors Taehoon Kim, Jongwook Choi, Heejae Jo, Byungmin Park, Jongwon Choi
Computer Vision
OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement
Linnan Zhao, Kang Liu, Hao Yu et al. (+3 more)
Although document OCR systems perform increasingly well on routine documents, complex formulas, structured text, and long-tail formats remain error-prone. OCR predictions may omit fine-grained content or hallucinate unsupported outputs, while equivalent encodings of the same visible content must be accommodated. Existing OCR evaluation methods mostly report aggregate metrics, offering limited support for analyzing case-level errors and improving OCR performance. We propose OCR-EDR (OCR Error Diagnosis and Repair), a rendering-aware framework that advances from fine-grained diagnosis to iterative repair. Given a source image, an editable OCR prediction, and its rendered image, OCR-EDR first jointly assesses whether the prediction and its rendering are consistent with the source, preserving valid predictions, including rendering-equivalent ones, while diagnosing and localizing genuine errors. It then applies executable edits and may request an updated rendering for iterative reassessment. We construct OCRErrBench from diverse real OCR predictions, covering text and formulas, exact and rendering-equivalent positives, and genuine errors, and develop the DocEDR model to execute the diagnosis–repair loop. On OCRErrBench, DocEDR achieves 94.78% diagnostic accuracy. It repairs 86.23% of erroneous inputs to visual consistency, raises formula Case-F1 by 30.99 percentage points over DOCR-Inspector-7B on DOCRcaseBench, and improves formula CDM by up to 4.62 percentage points on the identified Bad subsets of four OCR systems on UniMER-Test. These results show that OCR-EDR turns fine-grained OCR analysis into verified corrections and performance gains.
Read the full abstract ▾
All authors Linnan Zhao, Kang Liu, Hao Yu, Jiabo Zhan, Chong Sun, Chen Li
Machine Learning
Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling
Junyi Lin, Mengyu Li, Jingxuan Hu et al. (+2 more)
The performance of Flow Matching largely depends on the quality of the coupling between the source and target distributions. However, independent coupling often leads to path crossings and local velocity ambiguity, while OT-based couplings typically incur high construction costs. To address this challenge, we propose
Quantile AlignTree Flow Matching (QAT-FM), an efficient structured coupling strategy that constructs a hierarchical coupling between a Gaussian prior and the target data distribution via a
quantile-aligned tree structure. QAT-FM constructs the coupling in $\mathcal{O}(Nd\log N)$ time and supports per-pair source sampling with $\mathcal{O}(d)$ complexity, enabling scalable training for large-scale high-dimensional generative tasks. Theoretically, we prove that the QAT coupling satisfies marginal consistency, induces non-crossing linear interpolation paths, and consistently improves path separation at intermediate times compared with independent coupling, thereby alleviating local velocity ambiguity. QAT-FM further extends naturally to conditional generation, enabling structured conditional coupling while preserving global Gaussian
alignment. Experiments across diverse
benchmark datasets demonstrate that QAT-FM achieves competitive generative performance while substantially reducing coupling construction cost.
Read the full abstract ▾
All authors Junyi Lin, Mengyu Li, Jingxuan Hu, Kejun He, Cheng Meng
Machine Learning
Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery
Sairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy et al. (+2 more)
Differentiable causal discovery methods increasingly encode expert priors as forbidden-edge constraints enforced by an Augmented Lagrangian (ALM) penalty, on the assumption that a data-adaptive relaxation mechanism will discount and eventually override a rule the data consistently contradicts. We show this design, which we call guide, not bind, fails for two independent, precisely characterized reasons, and that directly repairing both restores it only partially. First, sequential penalty-ramping ALM suppresses a wrongly-forbidden true edge before any counterfactual check can detect it: we give three necessary conditions any adaptive relaxation must satisfy to avoid this (Proposition~\ref{prop:conditions}), prove that DADU—the natural relaxation rule this paper introduces as the object of study—violates all three (Corollary~\ref{cor:dadu_failure}), and confirm the failure across 3{,}072 training runs spanning graphs from 4 to 32 nodes, where a single wrong prior suppresses a true edge in 87–97% of trials under DADU. Second, and independent of any fix to the mechanism, we prove in closed form that the standard correlation-matching objective ties a true edge and its reverse to an identical cost of exactly $2r^2$ (Lemma~\ref{lem:tie}), not because the underlying equal-variance model is unidentifiable, but because normalizing to correlation discards exactly the variance information that would make it identifiable; covariance matching instead separates the two directions by a provable margin of at least $w_0^4$ (Lemma~\ref{lem:separation}).
Read the full abstract ▾
All authors Sairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy, Samrudh N, Bhaskarjyoti Das
Databases
Does SRL Pave the Road to Explainable Reasoning? Lessons Learned from an Implementer's Perspective
Lander Maes, Bryan-Elliott Tam, Jitse De Smet et al. (+3 more)
The Shape Rules
Language (SRL) Working Draft defines how to derive new RDF triples from an RDF graph using inference rules. Each rule matches graph patterns and instantiates triple templates whose output feeds into validation pipelines, SPARQL queries, or further inference. RDF
reasoning has traditionally relied on fixed entailment regimes (RDFS, OWL), rule-based ad-hoc
languages such as N3, or other implementation-specific solutions without a shared standard. SRL introduces user-defined production rules with a defined grammar, dependency analysis, execution ordering, and termination guarantees. However, no authoritative implementation exists, leaving practitioners with little guidance on how to build a conformant engine or on what problems the
language can solve. We implemented two SRL engines and evaluated both on classical RDF
reasoning tasks for soundness, completeness, and speed. The first reuses an existing SPARQL query engine and its query parser; the second is a dedicated engine. The SPARQL-based engine reused an existing modular parser for query construction and SPARQL CONSTRUCT for triple production, reducing engine-specific work. The dedicated engine was two to six times faster, the gap widening as rule sets grow. Both engines were validated against the SRL conformance test suite, supplemented by additional use-case-driven tests. A usable SRL engine can be built inexpensively on top of a SPARQL engine, with a moderate speed trade-off that a dedicated implementation recovers. Despite the specification's immaturity, the
language already supports practically useful
reasoning tasks.
Read the full abstract ▾
All authors Lander Maes, Bryan-Elliott Tam, Jitse De Smet, Jos De Roo, Pieter Colpaert, Ruben Taelman
Artificial Intelligence
Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents
Zhaoyuan Huang, Tianjie Ju, Pengzhou Cheng et al. (+7 more)
Graphical user interface (GUI)
agents are increasingly used to execute natural-
language instructions on user interfaces, yet real users may issue infeasible instructions due to benign mistakes. A reliable
agent should not only know how to act, but also when not to act. In this work, we introduce CONFLICTGUI, a
benchmark covering instruction-internal conflicts and instruction-GUI context conflicts to study conflict-aware termination. Our evaluation reveals severe execution-biased overcompliance:
agents that perform well on feasible tasks often continue to execute blindly under conflicting instructions. To mitigate this behavior, we propose CONFLICTGUARD, an inference-time framework that aligns an
agent's feasibility awareness with its action generation. CONFLICTGUARD contains two coupled components: a feasibility verification protocol that guides the
agent to assess instruction logic and GUI-side evidence before acting, and a conditional action modulation mechanism that steers
agents from over-compliant execution into termination-oriented behavior. Experiments across five widely-used
agents demonstrate that CONFLICTGUARD improves average conflict task success rate significantly, while preserving normal GUI-task performance. These results validate that a lightweight inference-time intervention can substantially boost GUI
Agent's competence to identify inappropriate execution scenarios and refrain from unnecessary actions.
Read the full abstract ▾
All authors Zhaoyuan Huang, Tianjie Ju, Pengzhou Cheng, Zheng Wu, Yansi Li, Chuanbiao Song, Jun Lan, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang
Computational Engineering
Markovian Shock-Source Tracing and Multidimensional Asset Roles in Exchange Rates, Gold Futures, and Bitcoin
Seung Ho Choi, Seoin Jang, Hyunwoo Lee et al. (+1 more)
This study examines cross-asset connectedness in an international financial network of major exchange rates, gold futures, and Bitcoin. Moving beyond the conventional net transmitter–receiver classification, we characterize asset roles through three complementary dimensions: direct spillover transmission, stationary source-tracing dynamics, and multistep upstream connectivity. Return spillovers are estimated using VAR generalized forecast-error variance decomposition (VAR-GFEVD). The positive pairwise net-spillover structure is then mapped into a row-
stochastic Markov kernel whose transitions trace dominant net-spillover sources in the reverse direction of the original transmission edges. A stationary departure flux describes long-run movement in this source-tracing chain, while Viral Centrality is evaluated by the deterministic probability-propagation
algorithm of Fink et al. to approximate multistep upstream reach. Empirically, gold futures emerge as the dominant direct net transmitter and the leading stationary source-tracing node, but do not have the largest Viral Centrality. Several exchange-rate nodes classified as direct net receivers have relatively high Viral Centrality, indicating broad conditional access to upstream source nodes. Bitcoin occupies an intermediate role. An auxiliary specification including the U.S. Dollar Index yields qualitatively similar role differentiation. The results show that direct connectedness, stationary source tracing, and approximate multistep upstream reach cannot be inferred from NET spillovers alone. All
diffusion interpretations are descriptive and conditional on the estimated network, row normalization, and restart closure.
Read the full abstract ▾
All authors Seung Ho Choi, Seoin Jang, Hyunwoo Lee, Hayoung Choi
Machine Learning
It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories
Yigit Utku Bulut
Reasoning traces of large
language models are widely read as containing "breakthrough" moments and early-legible fates. Both readings rest on measurements missing a counterfactual control at the level of the claim; we supply both controls. First, a restart-controlled truncation probe separates when a solution fits the continuation budget from when a prefix carries value that fresh computation cannot buy, comparing per-anchor continuation solve rates against from-scratch restart curves at matched total generated-
token budget. Applied to 178 problem-model
cells (89 MATH problems x two small open models, an outcome-blind but difficulty-targeted cohort), exactly 1 of 178
cells survives as prefix-limited; restart dose-response separates a compute-starved model from a capability-limited one; and wherever the matched budget lies inside the restart grid, continuing the model's own prefix beats restarting (9 of 9) – predominantly compute compression rather than expanded reachability. Second, a pre-registered, difficulty-controlled test finds no detectable outcome information in early-window internal signals beyond a problem-difficulty baseline, and two generation-free analyses of public corpora show why this control is needed: a trace-blind difficulty proxy reaches AUROC 0.873 on 192K DeepSeek-R1 generations – inside the published probe range – and a closely matched reconstruction of the closest published early-window positive recovers a comparable pooled result (0.849) while within problem it is statistically indistinguishable from chance at all ten anchors (0.496 at t=4); a post-hoc within-targeted probe finds only a small average residual, concentrated in three low-failure problems. High pooled probe AUROCs cannot by themselves establish within-attempt information; a question-only baseline or within-problem evaluation is required.
Read the full abstract ▾
Computation and Language
Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks
Xiangyu Wang, Jin Wu, Xiaoyu Li et al. (+2 more)
Automated evaluation of creativity tasks remains challenging for LLM-as-a-Judge, as LLM is susceptible to biases such as verbosity bias and leniency bias. Such limitations are particularly evident in Contextually-Grounded and Procedurally-Structured Tasks (CGPST), a complex multi-step creativity task where inter-step dependencies, highly subjectivity, and wide scoring ranges lead to more unstable and biased judgments. Existing approaches either rely on task-specific training or directly apply LLM-as-a-Judge, both of which struggle to ensure reliable evaluation under such complexity. To bridge these gaps, we propose CreaEval, an automated creativity evaluator for CGPST that decouples typical LLM-as-a-Judge into analysis and judging. Correspondingly, CreaEval involves two critical phases:
Memory-augmented Analysis, a SoT-LLM converts multi-step responses into structured evaluation evidence, incorporating cross-step
memory; and Evidence-based Judging, a Judge-LLM uses the extracted evidence for judging without accessing raw responses. Comprehensive experiments show that CreaEval achieves an average performance improvement of 22.74% over the second-best baselines across CGPST and two classic simple creativity tasks, demonstrating its generalizability. The code is available at https://github.com/Jaong/CreaEval.
Read the full abstract ▾
All authors Xiangyu Wang, Jin Wu, Xiaoyu Li, Chanjin Zheng, Yifeng Zhou
Computation and Language
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Heng Wang, Jielin Qiu, Wenting Zhao et al. (+8 more)
Large
language models achieve superior performance on tasks that require extended
reasoning, but long chains of thought make the KV cache a severe
memory bottleneck. Existing KV cache compression methods share one paradigm: score each cached
token by some estimate of how much it will matter later, and keep the top-scoring ones. We show that the selection signal contributes almost nothing. Random
Attention keeps the
prompt and evicts uniformly at random within each
attention head, computing no score at all; across four models and six
reasoning tasks, it matches the strongest baseline in task performance while delivering 32-43% higher throughput than that method when deployed with vLLM. Controlled experiments explain this by showing that 1) the
prompt is the fragile part of the cache, and most of the gap between selectors is just whether their selection signal happened to keep it; 2) the
reasoning trace protects itself against eviction with redundancy at two levels, in the text (the model restates what it still needs as it works) and across
attention heads (each keeps its own copy of the trace), so once the
prompt is safe, a random draw retains enough copies of what the model still needs, and no score is required to pick them. Our code is publicly available at https://github.com/SalesforceAIResearch/Random-
Attention.
Read the full abstract ▾
All authors Heng Wang, Jielin Qiu, Wenting Zhao, Cheng Qian, Liangwei Yang, Weizhi Zhang, Jiawei Han, Heng Ji, Silvio Savarese, Shelby Heinecke, Huan Wang
Computer Vision
When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals
Wonbin Son, Gyumun Choi, Junil Seo et al. (+3 more)
Answering what-if queries about a scene with a VLM usually means injecting the assumption as text or repainting the scene with a generative model. We instead move the edit to the representation level, before the model input. The image is abstracted into a set of object-level
tokens, and the original image never enters the VLM. This design rests on an open question: when do frozen VLMs actually respond to such
token edits? We introduce an answer-key-free protocol: no post-edit answer is annotated. It scores edits whose answers are logically determined, and audits itself by reversing each scoreable choice. The protocol reveals three structures. The response is not free: explicit edit teaching, not ordinary VQA training, produces it in dense scenes and multiplies it in sparse ones, on all three operations. Once on, it is governed by
token cleanliness and density, with deployable detector+segmenter
tokens competitive with the oracle and outperforming it on VRSBench. And reading is a separable axis: the image-free
token route preserves 92-96% of a matched patch-
token baseline's free-text VQA, and the answers measurably depend on the
tokens. The response, cleanliness, and reading structures are sign-preserved across two remote-sensing
datasets (iSAID, VRSBench) and three frozen LM backbones. We release the probe generator, records, judge logs, and code.
Read the full abstract ▾
All authors Wonbin Son, Gyumun Choi, Junil Seo, Seungmin Rho, Mi Young Lee, Hyungjoon Kim
Machine Learning
TraveL: Transformer-based Multi-view Path Distributional Representation Learning
Fang He, Tao-yang Fu and Wang-chien Lee
Path representation learning (PRL) for road networks has received increasing research
attention, due to various path-related applications. Existing works on PRL typically exploit the co-occurrence relationship among road segments and paths to learn a vector as the path representation, without exploring the varied traveler behaviors and the regional correlation on the path. In this work, we propose to learn distributional representations, which provide valuable information for use in path-related applications, by capturing the varied traveler behaviors as well as the various dependencies within regions of road segments. We propose a novel
Transformer-based Multi-view Distributional Representation Learning (TraveL) framework to encode a path along with a travel starting time to a distributional representation, which can be used to decode possible samples of on-path traveler behavior. Moreover, by analyzing the regional correlation which reveals various road segment relationships, we propose a regional
attention to encode these correlations in a path. Also, we explore the idea of Kolmogorov-Smirnov (K-S) test to compare the sampled traveler behavior against the collected ground truth to facilitate training. Experimental results show that the proposed TraveL model outperforms the state-of-the-art methods on both synthetic and real-world
datasets, by 14.7% in Mean K-S distance for travel time distribution estimation, 16.7% in Mean Absolute Error (MAE) for path similarity prediction, and 3.97% in MAE for destination prediction.
Read the full abstract ▾
Computation and Language
Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations
Yunao Zheng, Bin Wen, Xiaojie Wang et al. (+12 more)
Transformers lack a native lookup mechanism, requiring repeated dense computation to recognize and reuse local static patterns. Lngram v1 introduces tokenizer-independent conditional
memory through discrete latent n-gram addressing, but its
memory capacity is coupled with the backbone width, limiting scalability due to high parameter and activation costs. We propose Lngram v2, which decouples the number of routes,
memory dimension, and backbone width, and introduces a context-aware grouped-query
attention readout to scale
memory capacity independently. A zero-value Sink and counterfactual surrogate gradients further improve readout selectivity and routing trainability while preserving hard discrete addressing. Experiments across
vision–
language models (VLMs) of different scales show consistent improvements, including successful scaling to a 30B-parameter model. Compared with Lngram v1, Lngram v2 substantially reduces both total and activated
memory parameters while maintaining or improving
language modeling performance. Further analysis shows that its discrete IDs preserve substantial semantic structure of continuous hidden states, enabling semantic recovery from IDs alone and stable ID–semantic associations across
datasets. These results establish Lngram v2 as an efficient and scalable latent conditional
memory mechanism whose discrete addresses also provide a structured interface for analyzing internal model representations.
Read the full abstract ▾
All authors Yunao Zheng, Bin Wen, Xiaojie Wang, Kaiyu Jiang, Xuanyu Zheng, Changyi Liu, Hongyi Fu, Jianxiong Wang, Tianke Zhang, Haonan Fan, Yingxin Li, Jiankang Chen, Xu Wang, Tingting Gao, Han Li
Multiagent Systems
The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems
Guangjun Liu
Humans are the transport layer between AI systems, losing context at every hop. We present the Civilization Framework, whose addressable party is the civilization, not the
agent (one human sovereign, a persistent ledger, and interchangeable
agents), and the Embassy Protocol, a carrier-agnostic overlay: messages arrive asynchronously at a resident ledger endpoint, any online
agent of the receiver handles them, and commitment state on both ledgers, not delivery, is ground truth. Authority derives from
memory: an
agent's power to act for its civilization is capped by the
memory it can access and externalized through signed credentials, separate from civilization-level reputation. We identify the temporal-weight effect, a hazard in AI-to-AI communication where what arrives first acquires unearned authority, and test it in one frontier model in a preregistered 1,908-trial experiment. With verification removed, an incorrect upstream claim arriving first captures 54.2% of answers (4.2% under full verification), while the same claim arriving after the receiver has sealed its own answer captures 31.6% (the two
prompt shells are not length-matched, so part of that gap may reflect shell form; see Section 7), and both registered question-set specifications agree on these two verdicts (the exclusion specification is preregistered as under-powered). Two secondary results, the mitigation from instruction-level provenance labeling and sealed-answer accuracy equivalence, are specification-dependent, holding only under the all-questions specification. Because a registered check of tool use failed its call-budget condition, the registration classifies the round as inconclusive and every result above, primary and secondary, is reported as exploratory; a replication with harness-enforced budgets is planned. The framework's intra-civilization layer has a working implementation.
Read the full abstract ▾
Artificial Intelligence
DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
Puneet Mathur and Dinesh Manocha
Full-duplex voice
agents must continuously decide when to speak, listen, backchannel, interrupt, overlap, and yield the conversational floor. Existing
benchmarks evaluate these behaviors through explicit turn-management instructions, whereas voice
agents are often configured through roles or personas from which appropriate conversational behavior must be inferred. We introduce DuplexSpeechBench-IFEval (DSB-IFEval), a
benchmark for evaluating implicit instruction following in real-time spoken interaction. DSB-IFEval comprises 1,038 test cases derived from 240 controlled conversations spanning eight behaviorally contrastive assistant roles and five conditioning protocols: default behavior, explicit behavioral instructions, persona-implied behavior, combined persona-rule conditioning, and instruction conflict. We measure real-time floor management using the deterministic Instruction Adherence Score (IAS) and persona-consistent response content using the LLM-judged Persona Adherence Score (PAS). Across eleven real-time
speech models, we find that executing an explicit floor-management policy does not reliably imply the ability to infer the same policy from a persona. Moreover, even frontier models such as GPT-Live-1 and Gemini-3.8-Live adapt their dialogue
language to the assigned persona without consistently translating that persona into the appropriate full-duplex floor-management behavior. Finally, models that successfully resolve benign instruction conflicts often fail when safety-relevant role behavior should override an explicit directive. These results show that inferring role-implied behavior, executing it in real time, and resolving instruction conflicts remain distinct challenges for full-duplex voice
agents.
Read the full abstract ▾
Machine Learning
Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models
Ross Tieman and Evan Markou
Diversity is a widely observed factor in the resilient function of collective systems, yet the type of diversity that matters depends on the properties and failure modes of the system. This distinction is important for systems composed of multiple
language models. Different models may be treated as independent components even when their behaviour and failures remain strongly correlated. Assessments of
language-model populations using semantic similarity demonstrate limited semantic diversity, but this captures only differences in the meaning of observed outputs. We argue that a more fundamental notion of model diversity is generative-process diversity, the differences between processes capable of generating the observed outputs. Drawing from Algorithmic Information Theory, we use Normalised Compression Distance between raw model outputs, residualised against a permutation control, as a measure of inferred generative-process diversity. Across 38
language models, this measure identifies population structure missed by semantic similarity and predicts cross-task variation in chance-corrected correlated failure among model pairs across ten disjoint
benchmark families, beyond semantic similarity and model-pair capability. The cross-
benchmark partial rank association is $-0.216$ with a 95% interval of $[-0.309,-0.122]$, and the estimate is negative on all ten
benchmarks. These results indicate that increased generative-process diversity is associated with reduced correlated failure in model pairs that is not attributable to semantic similarity or capability. Inferred generative-process diversity offers a novel and practical approach for investigating diversity of multi-model systems in safety-relevant contexts.
Read the full abstract ▾
Cryptography and Security
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek et al. (+1 more)
Federated learning enables
privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal differential
privacy guaranties, tolerance to Byzantine-
adversarial participants, and reliable detection coverage across severely imbalanced attack categories. Existing literature treats these properties as independently composable, an assumption that this paper challenges both theoretically and empirically. In this paper, we study how these requirements interact in class-imbalanced
federated NIDS and introduce
geometric indistinguishability as a conceptual lens for a regime in which
privacy-induced dispersion in client updates can make minority-class signals harder for robust aggregation to preserve. Using UNSW-NB15 as a case study, we evaluate DP-SGD combined with coordinate-wise median under label-flip and model-poisoning attacks, with threat coverage assessed across attack categories. Our results provide initial evidence that the joint use of
privacy noise and robust aggregation can disproportionately degrade detection of rare attacks relative to majority classes. We also show that part of the observed collapse under strong
privacy can arise from training miscalibration, while a residual performance floor may remain for ultra-rare categories even after epsilon-dependent tuning. These findings motivate studying
privacy, robustness, and rare-attack coverage jointly rather than as independently composable properties, and suggest that aggregation-aware modeling and sample-aware evaluation are promising directions for trustworthy
federated NIDS.
Read the full abstract ▾
All authors Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek, Khondokar Fida Hasan
Artificial Intelligence
Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection
Weijie Liu, Running Zhao, Wenhao Yuan et al. (+4 more)
LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-
agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-
Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-
language and code-
language introduces over-interpretation and over-reporting challenges in a multi-
agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents
agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy
datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.
Read the full abstract ▾
All authors Weijie Liu, Running Zhao, Wenhao Yuan, Jinfeng Xu, Zhanfeng Xu, Xiaoxi Zhang, Edith Cheuk-Han Ngai
Computer Vision
Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage
Jagadish Kashinath Kamble, Jayanta Mukhopadhyay, Debaditya Roy et al. (+1 more)
Automatic generation of hand gestures is essential for the transmission of Indian classical dance and critical for its preservation. Indian classical dance gesture
datasets are inherently low-resource, and the canonical Sanskrit definitions of many mudras lack precise textual descriptions, limiting the effectiveness of conventional text-conditioned image generation models. We present MudraGen, a conditional
diffusion framework that synthesizes realistic RGB images of Samyukta Hasta Mudras – interactive two-hand gestures from Bharatanatyam (an Indian classical dance form). Unlike prior work on simple hand signs or single-hand gestures, MudraGen introduces geometry-aware supervision to capture the precise coordination, anatomical validity, and cultural nuance of interacting hands. We formulate three geometry-aware objectives: Keypoint Loss for 3D joint
alignment, Joint Offset Loss for inter-hand spatial coherence, and Shape Consistency, which serves as an anatomical regularizer by encouraging consistent hand morphology while allowing independent hand poses. Together, these objectives guide the
diffusion model toward anatomically plausible and well-coordinated hand configurations, enabling the synthesis of photorealistic and pose-accurate gesture images. Experimental results show that MudraGen surpasses existing state-of-the-art generative approaches in visual realism, anatomical correctness, and preservation of fine hand-pose structure, enabling faithful reproduction of complex Samyukta Hasta mudras. Beyond quantitative gains, its ability to generate culturally grounded and structurally consistent gestures highlights practical applications in cultural preservation and dance education.
Read the full abstract ▾
All authors Jagadish Kashinath Kamble, Jayanta Mukhopadhyay, Debaditya Roy, Partha Pratim Das
Sound
StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios
Chenglin Wu, Junjie Wu, Jinhang Chen et al. (+5 more)
Audio enhancement in real-world scenarios involves complex distortion couplings and requires personalized enhancement. Existing solutions struggle to address both simultaneously. To improve robustness and enable autonomous operation in such scenarios, we propose StrixAE, an
agent based on a
multimodal large
language model (MLLM). StrixAE leverages the MLLM as a controller to coordinate multiple audio enhancement and personalization models. To further enhance system robustness, reduce artifacts, and improve generalization across diverse real-world scenarios, StrixAE is trained through a two-stage process: first, CoT supervised fine-tuning on AcoustBench to ground basic
reasoning and tool invocation; second, Audio Perception Reinforcement Learning (APRL), a reward design specifically tailored for audio restoration pipelines that jointly optimizes format validity, structural coherence, and perceptual quality. Unlike generic RL fine-tuning, APRL introduces structured rewards that enforce executable pipelines and logical section ordering, enabling the
agent to produce reliable, interpretable enhancement plans without hallucinated tools. Based on real-world test
datasets, our proposed method outperforms most existing open-source and proprietary solutions, achieving state-of-the-art performance across multiple perceptual metrics and demonstrating strong generalization robustness.
Read the full abstract ▾
All authors Chenglin Wu, Junjie Wu, Jinhang Chen, Mingyang Chen, Zixu Lin, Jiabian Chen, Xinghao Ding, Xiaotong Tu
Computers and Society
The 5P Reflection Model for Education in the Generative Artificial Intelligence (GenAI) Era
Rajan Kadel, Samar Shailendra, Islam Mohammad Tahidul et al. (+3 more)
Contributions: A reflection model suitable for the era of Generative Artificial Intelligence (GenAI) is introduced. The proposed model is an integrated model that extracts features from various existing models and also incorporates technological aspects of GenAI. Background: Universities worldwide are facing challenges in adopting GenAI into their curricula, as it has impacted academic integrity and the scholarship of teaching and research. Traditional reflection models are struggling to authenticate student reflection as GenAI is incorporated in education. This requires a GenAI-aware model to enable the opportunities that address the associated challenges with GenAI. Research Questions: Does the academic ecosystem require a GenAI-aware reflection model to adopt GenAI into education? How to make a reflection model structured to ensure student authenticity and cognitive engagement within a GenAI-aware learning environment? Methodology: This study employs a design-based research methodology, assisted by a critical inquiry approach, to analyse existing reflection models in the era of GenAI and examine the technological aspects of GenAI. Additionally, it identifies a gap and the absence of a comprehensive reflection model that enhances reflection in the era of GenAI and supports the effective integration of GenAI in education. Findings: The literature survey indicates there is a greater need for reflection in the era of GenAI to ensure learning, but the existing reflection models lack proper strategies to manage the problem introduced by GenAI. A standard GenAI-aware reflection model, called 5P (Purpose, Process, Product, Pitfalls and Plan), is proposed i) to manage greater demand for reflection, ii) to address the limitations of the existing reflection models, iii) to consider technological aspects of GenAI.
Read the full abstract ▾
All authors Rajan Kadel, Samar Shailendra, Islam Mohammad Tahidul, Urvashi Rahul Saxena, Aakanksha Sharma, Sabitra Kaphle
Computation and Language
To What Extent Do Large Language Models Understand Bangla Idioms?
Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi et al. (+1 more)
Idiomatic expressions are an integral part of natural
language, reflecting cultural nuances and posing unique challenges for computational models, particularly in low-resource
languages. In this paper, we present the first large-scale
benchmark dataset of Bangla idioms, complemented by a synthetic multiple-choice question (MCQ)
dataset for idiom meaning identification. We conduct a comprehensive evaluation of recent large
language models (LLMs) across three idiom-related tasks: paraphrasing, idiom span detection, and meaning identification, leveraging zero-shot and few-shot prompting strategies. Our results reveal substantial variability in model performance, with no single LLM consistently outperforming others across all tasks. Notably, Phi-4-mini-instruct excels in paraphrasing, Kimi-K2-32b-instruct in span detection, and Gemini-2.5-flash in meaning identification. We believe that our
datasets and analyses will provide valuable resources to guide future research in improving LLM comprehension of idiomatic expressions, particularly in Bangla and other low-resource
languages.
Read the full abstract ▾
All authors Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi, Swakkhar Shatabda
Artificial Intelligence
Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation
Yuhe Wu, Guangyu Wang, Yujie Chen et al. (+7 more)
People increasingly turn to large
language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory context. Most prior work has studied this context through single-turn judgments or pressure-laden rebuttals, assumptions that poorly match how guidance is sought in real-world contexts. These assumptions leave unclear whether narration alone, without an explicit opposing position, can shift model judgments during multi-turn moral consultation. Yet real-world moral-conflict conversation often elicits one party's self-justifying account, which can unfold over multiple turns and create information asymmetry. We introduce narrative captivity, a failure mode in which a model treats an unopposed one-sided account as complete and aligns with the narrator's interpretation without seeking missing perspectives. To measure this phenomenon, we build a
benchmark of $5{,}078$ interpersonal-conflict scenarios spanning six moral dimensions. Across 17 LLMs, narrative captivity is widespread: end-state judgments under multi-turn narration shift by 25 percentage points on average beyond the matched single-turn baseline. Stage-level analysis identifies preference optimization as a major contributor, while four inference-time strategies provide only partial mitigation. We hope our project fosters LLM advisors that preserve independent judgment in real-world consultation.
Read the full abstract ▾
All authors Yuhe Wu, Guangyu Wang, Yujie Chen, Jiatong Zhang, Yuran Chen, Yutong Zhang, Xiyin Cheng, Wenpeng Cao, Zhuang Liu, Guang Zhang
Computer Vision
Neural-Collapse-guided Task-Free Continual Anomaly Detection
Xiaotong Kong, Chaoyang Song, Ziai Zhou et al. (+3 more)
Recent years have witnessed growing interest in continual anomaly detection for industrial visual inspection. However, real-world manufacturing environments exhibit unpredictable shifts in data distributions, rendering task-dependent continual learning assumptions impractical. To address this limitation, we formulate industrial anomaly detection as a task-free continual learning problem and propose NC-TFAD, a neural-collapse-inspired, geometry-driven framework for learning from non-stationary data streams without task boundaries. NC-TFAD freezes a pretrained backbone and aligns streaming features to a simplex Equiangular Tight Frame (ETF) prototype space to stabilize representation geometry under non-stationary streams. To satisfy the NC-inspired
geometric construction in the absence of real anomalies, we generate synthetic anomaly samples as auxiliary anchors during training. Building on this geometry, we further introduce inter- and intra-class regularization together with a Focal Neural Collapse Contrastive (FNCC) loss to suppress representation drift and improve normal-anomaly separability. Finally, a normal-patch-prototype-guided localization branch constructs calibrated patch-wise deviation maps from normal training samples and fuses them with a weak self-
attention prior, producing anomaly heatmaps without pixel-level annotations. Extensive experiments on MVTec AD and VisA show that NC-TFAD consistently outperforms representative task-free continual learning methods adapted from general
vision, as well as unified anomaly detection baselines, in both image-level detection and pixel-level localization under the task-free continual learning protocol. These results highlight that geometry-driven modeling offers an effective and robust solution for task-free continual anomaly detection in real-world industrial applications.
Read the full abstract ▾
All authors Xiaotong Kong, Chaoyang Song, Ziai Zhou, Jinxia Zhang, Kanjian Zhang, Haikun Wei
Numerical Analysis
Semi-discrete quadratic Wasserstein energy and state-dependent Langevin exploration
Ran Gu, Gaoyue Guo and Kelvin Shuangjian Zhang
We study the semi-discrete quadratic Wasserstein energy. The energy is nonsmooth at collisions of sites. We prove local Lipschitz continuity on the full configuration space, together with global semiconcavity, coercivity, and dissipativity; show that every global minimizer is interior and collision free; and establish $C^2$ regularity on the collision-free configuration space. The gradient is expressed through the barycenters of the balanced Laguerre
cells, while the Hessian is given by an explicit facet formula and satisfies a global one-sided bound. We also solve the one-dimensional problem explicitly in each ordering chamber and give a two-site example on the unit square with non-minimizing Lloyd fixed points. For $d\ge 2$, we then formulate an
entropy-regularized relaxed control of the Langevin temperature. The controlled dynamics is strongly well posed, nonexplosive, and collision free. Its value function is a classical interior solution of the exploratory Hamilton-Jacobi-Bellman equation; the
Laplacian of the value function is locally $C^1$, which yields a locally Lipschitz optimal temperature feedback. Independently of this optimal-control result, for every fixed Borel temperature rule bounded away from zero, and every sufficiently small step size, the associated Gaussian Euler chain is geometrically ergodic with a full-support invariant law. The raw iterates do not converge, whereas the best-so-far energy converges almost surely to the global minimum and the running record approaches the set of global minimizers.
Read the full abstract ▾
Artificial Intelligence
A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant
Saptarshi Basu, Sandeep Kakar and Ashok Goel
Artificial intelligence (AI) teaching assistants powered by large
language models (LLMs) offer scalable educational support but often provide limited personalization. This study presents a
prompt-engineering-based framework for personalizing general-purpose LLM/RAG-based AI teaching assistants such as Jill Watson across academic disciplines and courses. The framework adapts responses using six learner-specific dimensions: self-assessment, abstraction preference, verbosity preference, perceptual orientation, information processing style, and level of understanding, yielding 96 distinct learner profiles. Student queries are additionally analyzed using Bloom's Taxonomy to estimate cognitive complexity at the interaction level. Learner attributes and cognitive assessments are encoded in structured
prompts that condition the LLM without requiring model retraining. The framework is evaluated through experiments using NLP metrics and a human study with five participants. Results show perceived differences in response style and structure across personalization conditions, with statistical analyses identifying learner attributes associated with measurable response changes. These findings provide preliminary evidence that
prompt-based personalization can support adaptive behavior in LLM-powered educational
agents.
Read the full abstract ▾
Numerical Analysis
Spectral Convergence of Random Feature Method in Multiple Dimensions
Pingbing Ming and Hao Yu
We first prove spectral convergence of the random feature method (RFM) for multidimensional targets in Sobolev, Gevrey, ultra-analytic, and bandlimited classes. The analysis establishes general high-probability approximation estimates in the interpolation scale generated by a kernel integral operator. On a single event determined only by the sampled features, one random space approximates every target in a prescribed source ball; moreover, for each target, a single coefficient vector defines an approximant that attains spectral accuracy simultaneously in all admissible error norms. For both regularity-adapted frequency distributions and uniform distributions on growing frequency windows, the resulting rates range from super-exponential to algebraic, depending on the regularity of the target. Second, we establish abstract error estimates for strong- and weak-form RFM discretizations, thereby converting the preceding approximation bounds into convergence estimates for multidimensional second-order
elliptic boundary value and
eigenvalue problems. Finally, for random feature
matrices (RFMtxs), we prove super-exponential singular-value decay with
Fourier features and exponential decay with $\tanh$ features, together with corresponding condition-number lower bounds. The analysis identifies a common mechanism: the same spectral approximation that yields high accuracy also drives severe ill-conditioning.
Read the full abstract ▾