Cryptography and Security
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Sunday 16 August
Entropy-based Distributed Denial of Service (DDoS) detection in Software-Defined Networking (SDN) commonly relies on spatial traffic distributions and static or loosely adaptive thresholds, making it vulnerable to legitimate traffic fluctuations in Internet of Things (IoT) environments. This paper proposes a lightweight spatiotemporal entropy-based detector for DDoS attacks. Spatial entropy is computed from dynamically selected traffic attribute pairs, while temporal entropy captures the randomness of packet inter-arrival times. The two normalized entropy measures are fused into a unified indicator and evaluated using a constrained second-order Exponentially Weighted Moving Average threshold that jointly tracks entropy trend and volatility. To prevent attack-contaminated observations from biasing threshold adaptation, threshold updates are performed only for windows classified as normal. Testbed results show 99.26% recall, a 0.9737 F1-score, and a 3.2% false positive rate (41.74% below that of spatial entropy alone). On CICDDoS2019, the method achieves an FPR of 0 and remains competitive with machine-learning-based methods. It requires 3.95 ms of core processing per window and 11.65% system-wide CPU utilization, supporting resource-constrained edge and IoT deployment.
Computation and Language
Wiktionary as a Crowdsourced Lexicon for English Dialects
This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descriptive analysis of the crowdsourced lexicon for 12 national varieties of English before applying the lexicon to geo-referenced, country-level social media language data to examine the real-world performance of this crowdsourced dialect lexicon. We demonstrate that Wiktionary matches or exceeds the coverage of traditional dictionaries, such as the Oxford English Dictionary (OED), for regional and Outer-Circle varieties. Our dialect-specific case study on New Zealand English found high alignment between Wiktionary and the OED based on word-formation patterns (R = 0.883). Similarly, we observed high alignment between the dialect lexicon and geo-referenced social media language. While this paper found that Wiktionary has broad coverage of lexical properties, it also highlighted some of the macro-challenges involved in evaluating dialect-responsive language resources and tools, such as the role of language contact in dialects and register effects in web-based corpora.
Read the full abstract
Cryptography and Security
A contribution to the critique of blockchain censorship
We study the blockchain censorship attack introduced in [21], which shows that joining the attack is a dominant strategy. We show that, by introducing certain detectability threshold, joining the attack can lead to strictly less reward for whales, which are defined to be a small number of validators that hold significantly more voting power than the rest (henceforth known as minnows). This leads to a change of the equilibrium: With whales unwilling to participate in the attack, it is difficult for minnows alone to launch the attack. We also perform Monte Carlo simulation to show the existence of reduction for whales' reward in Ethereum and Solana.
Read the full abstract
Distributed Computing
When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
Split Federated Learning (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split strategy may be suboptimal because clients can differ in data distributions, adaptation dynamics, and representation learning progress, making a single split point insufficient to accommodate client-specific training states. In this paper, we propose FedSGA, a Sufficiency-Guided Adaptive split Federated learning framework that addresses this question through client-specific shallow sufficiency estimation. First, we introduce a client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active. To further avoid repeated online probing over multiple candidate depths, we design a shallow sufficiency estimator that combines cross-client semantic alignment, temporal interface stability, and prompt-state variation to estimate whether the shallowest split is already sufficient. Finally, we introduce a split-compatible interface harmonization module that projects activations from different split depths into a shared semantic space, improving the comparability of heterogeneous client interfaces before server-side prediction. Extensive experiments on multiple heterogeneous benchmarks demonstrate the effectiveness of FedSGA in improving model performance compared with state-of-the-art methods while reducing unnecessary client-side computation.
Read the full abstract
Robotics
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment. Although Dadu-Corki, a dedicated accelerator for efficient embodied AI, has been introduced, it does not exploit the inherent interaction patterns between the robot and its environment, which results in a relatively short predicted action length. We observe that robotic environments naturally alternate between active states-where precise actions are crucial-and inactive states-where actions have limited impact on task success. This insight enables a new scheduling opportunity: long-action-length speculative prediction in inactive states, paired with selective verification in active states. We propose SpecVLA, an algorithm-system co-design framework that adaptively balances action length, inference latency, and task reliability. On the algorithm side, SpecVLA introduces a state-aware VLA inference execution paradigm and a hardware-friendly construction of a smaller verification model (sVLA) using differential residuals and block-wise mixed-precision quantization. On the system side, we develop a heterogeneous architecture consisting of a GPU and a robotic-specific hardware module, along with a speculative dataflow that decouples VLA and sVLA through parallel execution. Comprehensive evaluations on OpenVLA and RDT across LIBERO and ManiSkill benchmarks show that SpecVLA reduces end-to-end latency significantly while preserving task success rate. By enabling long-action-length speculative prediction with timely verification, SpecVLA achieves real-time robotic manipulation with both high efficiency and reliability.
Read the full abstract
Artificial Intelligence
Argumentation for Common Ground: Finding Zones of Possible Agreement between Individuals in Conflict
How can common ground between societies in conflict be identified when citizens' acceptability of peace agreements is shaped by contested narratives? Such acceptability is mediated not only by the clauses that agreements include or exclude, but crucially by citizens' subjective reasoning concerning agreements' clauses. In this paper, we leverage computational argumentation to introduce a novel approach to identifying mutually acceptable agreements among individuals in conflict, i.e. a Zone of Possible Agreement (ZOPA). First, we introduce a quantitative bipolar argumentation framework tailored to represent each side's reasoning about peace agreements. We then show how merging these frameworks can enable negotiators to identify peace agreements that are mutually acceptable. To evaluate our approach under conditions of real-world relevance, we focus on the Palestinian-Israeli conflict, where long-standing policy, practitioner and public interest underscores the demand for methods capable of analysing polarised public reasoning. We show how our framework identifies a ZOPA through theoretical analysis and preliminary experiments using survey data from both existing work and retrieved by a large language model. The results illustrate how argumentation can empower negotiators and conflict-resolution teams in mapping feasible ZOPAs grounded in citizens' reasoning.
Read the full abstract
Machine Learning
Sparse Prototype Code Underlies Classification and Prediction Across Modalities
Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structure makes them difficult to interpret. We show that classification tasks give rise to a universal representational geometry, shared across state-of-the-art models in vision, audio, and language processing. The key structure is that within-class variability is not random in representation space. Instead, its classifier-relevant component has strong and structured correlations with the class's own centroid and with the centroids of its competing classes. Building on this observation, we derive an analytical mean-field theory governed mainly by the variability along true-class and rival-class centroid coordinates, together with a global renormalization of the class radius that compensates for the non-Gaussian statistics of real representations. The theory accurately predicts classification accuracy across architectures and modalities. The relevant geometric quantities improve systematically with model scale, mirroring the observed gains in accuracy. A striking feature of the theory is its sparsity: accurate prediction requires only a small set of centroid coordinates associated with the true class and its strongest rivals - connecting our framework to sparse-feature extraction approaches such as sparse autoencoders. Together, these results provide a parsimonious predictive theory of neural representations and suggest that classification in deep networks is governed by a sparse, centroid-aligned structure embedded within the full high-dimensional representation space.
Read the full abstract
Game Theory
Non-obvious Manipulability with Groups in Shapley-Scarf Housing Markets
In Shapley-Scarf housing markets, Ma (1994) shows that top trading cycles (TTC) is the unique mechanism satisfying individual rationality (IR), Pareto efficiency (PE), and strategy-proofness. We ask what other mechanisms become possible when strategy-proofness is replaced by a weaker condition called non-obvious manipulability (NOM), introduced by Troyan and Morrill (2020). We first show that this weaker condition does not help on its own: every IR and PE mechanism is already NOM. We therefore introduce a new condition: NOM with groups, under which each agent knows the preferences of the other members of her group, but not those of agents outside the group. This condition reduces to strategy-proofness when all agents belong to one group, and to standard NOM when every group is a singleton. Also, we introduce a participation condition called group rationality (GR), which requires that no group do worse than it would by trading only among its own members. We then define a class of mechanisms called TTC with super-groups, whose members satisfy GR, PE, and NOM with groups. The class includes mechanisms that differ from standard TTC, including mechanisms that are not strategy-proof. Furthermore, we show that every mechanism that satisfies GR, PE, and NOM with groups has the same best- and worst-case outcomes as every TTC with super-groups mechanism.
Read the full abstract
Human-Computer Interaction
Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis
The rapid development and growing deployment of large language models (LLMs) have made it increasingly important to understand their capabilities. A common approach is to evaluate LLMs using assessment instruments originally designed to measure skills and competencies in humans, such as standardized exams, and to use performance on these instruments as evidence for generalizable claims about LLMs' underlying abilities on the same skills the assessments are intended to measure in humans. However, from a validity perspective, such inferences require that the relationship between observed performance and underlying constructs established for humans also holds for LLMs. In particular, a necessary condition for transferring score interpretations is similarity in the latent structure of responses to the assessment. In this study, we examine whether this condition holds in two educational contexts: high-school chemistry and a quantitative reasoning section of a university entrance exam. Using a case study design, we compare human response data with responses generated by six multimodal LLMs. Our analytical approach combines exploratory factor analysis, factor congruence, and resampling to assess latent structure similarity across human learners and LLMs. Across both instruments, we find systematic differences between human and LLM factor structures, showing evidence that the analyzed assessments may not measure the same constructs for humans and LLMs. These findings call into question the validity of evaluation practices that use educational assessments to make claims about AI capabilities.
Read the full abstract
Machine Learning
In Defense of OCTA: The Reconstruction-Utility Gap in OCT-to-OCTA Synthesis
Optical coherence tomography angiography (OCTA) images retinal blood flow, giving capillary-perfusion and foveal-avascular-zone biomarkers that grade diabetic-retinopathy ischemia. Because OCTA hardware is less common than structural OCT, recent work synthesizes it from OCT, reporting strong reconstruction (3D PSNR > 31 dB, SSIM > 0.9). We ask not whether the synthetic image looks similar, but whether it supports the measurements OCTA is acquired for. A frozen real-OCTA segmenter, applied as a probe to two synthesizers (XOCT, TransPro), shows downstream Dice falling with structural fineness: large vessels survive (0.862 -> 0.831) while the fine capillary network collapses (0.798 -> 0.635, five times the large-vessel loss; paired Wilcoxon p < 1e-3), TransPro worse throughout. A matched-blur control shows this detail is fabricated, not blurred. Retrained on a private Spectralis dataset, neither synthesizer reproduces the neovascular lesion (qualitative, n=3). Reconstruction fidelity is not clinical utility; we establish downstream-task fidelity as the evaluation OCT-to-OCTA synthesis needs.
Read the full abstract
Numerical Analysis
Uniform-in-time strong convergence rates of fully discrete approximations for stochastic Cahn–Hilliard equations with multiplicative noise
This paper investigates the uniform-in-time strong convergence rates of a fully discrete approximation for the stochastic Cahn–Hilliard equation driven by multiplicative noise in spatial dimensions $d\in\{1,2,3\}$. The proposed scheme combines a spectral Galerkin method in space with a backward Euler scheme in time. The main analytical difficulties arise from the state-dependent stochastic perturbation, the absence of a global monotonicity structure for the nonlinear term, and the fourth-order nature of the Cahn–Hilliard operator. In particular, these features make the derivation of uniform $L^{\infty}$-moment estimates highly nontrivial in three dimensions. For the continuous equation, by utilizing the Itô formula to $\|u\|^p$ and introducing the energy functional $\mathcal{E}(u(t))$, we derive the uniform moment boundedness of the solution. At the fully discrete level, we develop discrete energy estimates and close the required high-order moment bounds through an induction argument. Based on these regularity estimates, we deduce uniform-in-time strong convergence rates for the fully discrete scheme. Moreover, we prove the existence and uniqueness of invariant measures for both the exact dynamics and the fully discrete numerical dynamics. Numerical experiments are provided to confirm the theoretical findings.
Read the full abstract
Information Retrieval
Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark
Scientific papers contain multiple searchable facets such as background, methods. However, many paper retrieval benchmarks merely evaluate individual query-paper relevance, while overlooking other facets of the same paper. To bridge this gap, we introduce MAPLE, an expert-validated benchmark for multi-aspect, full-paper retrieval that evaluates whether retrievers can consistently recover the same paper from queries targeting its motivation, method, and experimental findings. MAPLE contains 2,095 queries about recent ML and NLP papers, grounded in both textual and multimodal content. We further propose MAPLE-Synth, a retrieval-based in-context learning pipeline that leverages OpenReview discussions and human-written query exemplars to generate realistic queries reflecting researchers' interests in different aspects of a paper. Our expert validation shows that these queries are comparable in realism to human-written queries and highly relevant to the target papers. Experiments across lexical, scientific-domain, general-purpose text, and multimodal retrievers reveal a substantial gap between retrieving a paper from any one aspect and retrieving it from all aspects: the strongest model achieves 98.1% AnyAspect@20 but only 15.7% AllAspect@20. Experiment/result queries and table-referenced queries are particularly difficult across retrievers. Although multi-chunk aggregation improves multi-aspect paper retrieval, considerable failures persist. MAPLE provides a testbed for evaluating and developing retrievers that represent scientific papers more comprehensively.
Read the full abstract
Artificial Intelligence
Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts
Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial measurement units (IMUs) across sessions. In multi-IMU settings, this can induce independent orientation offsets across body locations, a deployment shift that conventional scalar HAR models do not structurally handle. Existing remedies rely on rotation augmentation, whose robustness depends on sampled transformations, or calibration and orientationnormalization pipelines requiring additional reference-frame assumptions or explicit procedures. We present Truly Rotation-Invariant HAR (TRI-HAR), a rotation-invariant framework that makes robustness to independent per-location IMU orientation offsets a structural model property. TRI-HAR reshapes accelerometer and gyroscope streams into triaxial vectors, applies a shared SO(3)-equivariant backbone and invariant projection to each IMU location, and fuses the resulting invariant features for activity classification. Across four multi-IMU benchmarks, TRI-HAR preserves macro-F1 under fixed independent per-location SO(3) rotations and outperforms rotation-augmented baselines under this target shift without requiring rotational augmentation.
Read the full abstract
Artificial Intelligence
Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds
Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been reached is seldom asked with discipline. Our aim is not to pin this ceiling to a single number, but to quantify how far it depends on finite annotation, estimator choice, annotation noise, and the evaluation protocol, and thereby to discipline how confidently saturation can be claimed. We propose Bias-corrected Affective Ceiling Estimation (BACE), an analysis framework that estimates a bias-corrected ceiling, separates irreducible from reducible error, and disciplines the resulting claims. An anchored Dirichlet-mixture empirical Bayes estimator, bracketed between plug-in and NSB, recovers the human-consensus distribution; an annotator split, a noise deconvolution, and a fixed claim gate then attribute error without circularity. Methodologically, unconstrained point estimates place reachability anywhere from 0.38 to 1.03, so saturation cannot be decided by any single estimator. Substantively, the only assertion passing the claim gate is that at least about 33% of a representative classifier's error on GoEmotions is irreducible, with the same pattern recurring on offensiveness and irony.
Read the full abstract
Machine Learning
Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do
Machine-learning detectors for power-system cyberattacks are themselves attack surfaces, and quantum machine learning has been proposed for them. We benchmark fidelity-kernel SVMs and variational classifiers against six tuned classical models on public power-system attack data (Mississippi State/ORNL), across white-box, transfer, decision-based black-box, and poisoning attacks. Our headline finding is methodological: the benchmark's answers are set by the evaluator's choices before the models. Eight choices – six in the evaluation protocol, two in the tuning the benchmark itself runs – each reversed or moved a conclusion at fixed models. The largest is the split: the row-level protocol scores 0.905 macro-F1 where holding whole source files out leaves 0.594, and in the capped matched-dimensionality regime the quantum arm sits within noise of chance with the classical arm 0.024 above it. A fidelity kernel looks most robust until attacked directly (retention 0.886 to 0.064); a mis-fitted surrogate manufactures a 10x asymmetry; an unseeded black-box attack moves 75% between restarts. A positive control explains the accuracy null: the labels, not the pipeline. We give the control that catches each choice and release the seeded benchmark.
Read the full abstract
Computer Vision
EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input
The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget. Memory and compute cost scale with the number of visual tokens, and high-resolution video quickly becomes expensive to transmit and process at scale. Prior work (GazeLLM) addresses this by cropping the video around the camera wearer's gaze. This reduces the number of visual tokens by about tenfold while maintaining or improving the quality of full-resolution descriptions. However, this compression strategy depends on dedicated eye-tracking hardware, which is unavailable on consumer smart glasses. Building a software-only substitute poses a joint constraint: the predictor must be accurate enough to preserve downstream description quality, yet light enough to run on-device, within the power and compute budget of a smartphone. We address this with EgoGazeLite, a lightweight dual-process gaze predictor for egocentric video. Across two MLLMs, three automated metrics, and two LLM judges, predicted-gaze crops show no significant difference from ground-truth-gaze crops. Equivalence is confirmed in all ten cases. EgoGazeLite achieves this at 15.7M parameters, 6.71 GFLOPs, and runs the full gaze-and-crop pipeline end-to-end in real time (21.6 ms/frame) on consumer accelerator hardware. Together, these results remove the need for eye-tracking hardware for token-efficient, gaze-conditioned egocentric video understanding with MLLMs.
Read the full abstract
Computer Vision
AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models
This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics. Spatial cognition, shaped by cognitive psychology, spatial science, and cultural context, often assigns directionality to objects. However, natural language descriptions of spatial relations frequently omit explicit reference frames, leading to semantic ambiguity and potentially serious errors for embodied AI robots. Existing VLMs, due to insufficient training on reference frames and object orientations, often produce inconsistent responses. To address this issue, we construct a new dataset, AlloEgo-View, comprising (image, query, view-specific answer) triplets that capture key object relations from both allocentric and egocentric perspectives. The view-specific descriptions follow a structured spatial representation that annotate detailed scene descriptions, reference and target objects, their orientations, reference frames, and view types. Building on AlloEgo-View, we develop AlloEgo-VLM, a framework to disambiguate allocentric and egocentric reference frames, even under ambiguous queries, and to be easily integrated into existing VLMs via supervised fine-tuning. Furthermore, we deploy our framework onto an embodied robotic platform within NVIDIA Isaac Sim to validate its real-world feasibility in open-ended object searching tasks. Experiments highlight the limitations of current VLMs in handling view-specific queries and demonstrate the strong disambiguation ability of AlloEgo-VLM.
Read the full abstract
Information Theory
Off-Grid Position Optimization under Mutual Coupling in Fluid Antenna Arrays
Fluid antenna arrays exploit continuous antenna repositioning within a finite aperture to provide geometry diversity beyond grid-constrained port selection. Every displacement, however, changes both the radiation response and the multiport mutual-impedance network, coupling geometry optimization with the source-voltage constraint. This paper develops an electromagnetic-aware (EM-aware) beamforming framework for planar fluid antenna arrays. Phase retrieval converts an amplitude-only shaped-beam specification into an aperture-compatible complex target, and an EM-aware orthogonal matching pursuit (OMP) method selects grid-constrained initial antenna positions. Continuous refinement then alternates exact voltage-constrained current optimization with movement-constrained projected adaptive moment estimation (Adam) updates of all physical antenna positions. Across independently perturbed symmetric dual-beam targets, the proposed method consistently improves the average mainlobe signal-to-noise ratio (SNR) and reduces the peak sidelobe level (PSLL) over a uniform array and discrete port selection.
Read the full abstract
Machine Learning
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads. To bridge this gap, we propose FluxBin (Flexible LUT-based Ultra-low-bit eXecution with Binary bases), an algorithm-kernel co-design that synergizes post-training quantization with a highly optimized CUDA kernel. Algorithmically, we introduce Decoupled Row-Column Binary Decomposition to enhance representational capacity while maintaining hardware efficiency, complemented by a Hessian-guided saliency-aware hybrid bases that preserve critical information. At the kernel level, we implement a Lookup Table Building Approach with Scale Fusion to reduce floating-point arithmetic, featuring a Virtual Columnar Mapping that transforms irregular, sparse, and salient matrices into dense execution. Extensive evaluations demonstrate FluxBin achieves up to $5.92\times$ speedup and $10.19\times$ energy savings across diverse model architectures, delivering comparable accuracy to heavily fine-tuned methods. This effectively enables the deployment of 70B-scale models on one single A100 GPU with a $4\times$ memory reduction. Code is available at https://github.com/nicyyyy/FluxBin.
Read the full abstract
Machine Learning
Quantum Models with Multi-Stage Training for Compositional Concept Generalization
Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for multimodal learning. In this work, we provide a solution using a compositional model of meaning that separates nouns from relations and uses tensors and variational quantum circuits to train them on data. This model enables us to employ a multi stage training paradigm, one that first learns object representations from single-object image-caption pairs, then subsequently transfers these to the relational stage where object parameters are frozen and optimisation is only applied to relational components. This design explicitly enforces compositional factorisation at the circuit, ensuring that relations are learned as transformations over stable primitives. The training paradigm is tested on the CLEVR dataset developed specificially for CoCoGen. For text, we work with vector representations of nouns and higher order tensor representations of relations using a set of different ansatz. For images, we work with quantum encodings of image embeddings dervied from Open AI's Vision Language tool CLIP and contrast amplitude encoding, which preserves the original embedding geometry, with angle encoding, which introduces nonlinear feature transformations. Our results show that multi-staged training combined with structured encodings significantly improves out of distribution relational generalisation, while using orders of magnitude fewer trainable parameters than classical baselines. We find that performance gains arise from the interaction between representation and encoding, with nonlinear quantum encodings enhancing the separability of compositional structure. These findings demonstrate that structured quantum representations and staged learning provide an effective framework for compositional generalisation in multimodal quantum machine learning.
Read the full abstract
Artificial Intelligence
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
The widespread circulation of abusive online content has increased the need for reliable moderation of Chinese social-media text. Existing Chinese benchmarks support label classification, fine-grained toxicity categorization, and target-aware extraction, but do not provide a unified representation for deterministically verifying the stated basis of a moderation decision. We introduce VARM-Bench, a benchmark for field-anchored chain-of-thought rationales in Chinese abusive-speech moderation. Each instance contains a concise natural-language rationale with explicit anchors for six decisions: target, target type, target explicitness, author stance, harmfulness label, and fine-grained category. Our deterministic protocol evaluates field correctness, target alignment, output validity, complete-record agreement, and hidden record errors conditioned on correct final decisions, without relying on an LLM judge. Under a common structured-output protocol, we evaluate language models across multiple model families using zero-shot prompting, taxonomy guidance, and structured CoT supervision, and analyze lexical-cue sensitivity and field-level errors. Results show that strong label-level performance can conceal substantial errors in complete moderation records. VARM-Bench provides an auditable and reproducible benchmark for evaluating verifiable moderation rationales in Chinese abusive-speech moderation.
Read the full abstract
Information Theory
Sparse Port Selection under Mutual Coupling in Fluid Antenna Arrays
Fluid antenna systems obtain spatial degrees of freedom by reconfiguring antenna positions within a confined region, a principle that extends to beamforming: shaped beams can be synthesized using far fewer radio-frequency feeds than candidate antenna positions. When the candidates are densely arranged, however, electromagnetic mutual coupling changes the relationship among terminal voltages, induced currents, and radiated fields, so an uncoupled model no longer describes the hardware and may activate an unsuitable set of ports, distorting the synthesized pattern. This paper develops a mutual-coupling-aware framework that converts the desired beam amplitude into a finite-aperture-compatible complex target and models the complete antenna lattice as a coupled multiport network, selecting the active ports and their source voltages through the coupled voltage-to-field response. Inactive candidate ports remain part of the network and carry induced currents, and every compared design is evaluated through the same electromagnetic model under the same source-voltage budget. Numerical results show that the mutual-coupling-aware design improves both the average mainlobe signal-to-noise ratio (SNR) and the peak sidelobe level (PSLL) over coupling-unaware selection and a fixed array, demonstrating that mutual coupling should be exploited in the design itself rather than compensated only in the final evaluation.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
Underwater Color Restoration with Vanishing Uncertainty
Underwater color restoration promises to unlock color as a reliable signal for aquatic sciences, but achieving this with scientific confidence remains out of reach. Current methods are validated almost exclusively on an empirical basis, which provides confidence only to the extent that the vast diversity of possible visibility conditions is covered with end-to-end testing using a known ground truth. This is exacerbated by color restoration being a fatally ill-posed problem when considered in full mathematical generality, requiring additional constraints to narrow the solution to a finite uncertainty interval. The gap between which constraints suffice in theory and which constraints are satisfied by real-world data is poorly understood, making it unclear whether existing methods are solving a problem that is actually solvable. In this article, we investigate the theoretical side of this gap, identifying idealized conditions which guarantee bounded uncertainty that converges to zero as the spatial resolution of the camera increases.
Read the full abstract
Computational Engineering
Toward Decentralized Carbon Trading in Indonesia: A Public-Blockchain Architecture for Tokenized Real-World Assets
Indonesia has established a regulated carbon market supported by national registry infrastructure and the IDXCarbon exchange. Carbon units can be issued, recorded, traded, and retired within this framework. IDXCarbon currently uses a private blockchain for its trading infrastructure. This creates an opportunity to examine how Indonesian carbon credits could also be represented and traded through public blockchain infrastructure. This study proposes an architecture for tokenizing Indonesian carbon credits as real-world assets (RWAs), with particular focus on Sertifikat Pengurangan Emisi Gas Rumah Kaca (SPE-GRK). The proposed architecture retains the Sistem Registri Unit Karbon (SRUK) as the authoritative source of carbon-unit status. It introduces a public-blockchain layer for token representation and programmable transactions. The architecture is designed to support lifecycle management, token-based asset representation, public observability of token activity, interoperability, wallet-based transactions, and programmable settlement. The architecture consists of four layers: the authoritative carbon layer, the registry interoperability and tokenization layer, the public-blockchain RWA layer, and the market and application layer. Access to the tokenized carbon assets remains regulated. Token issuance and transfers are linked to participant eligibility and registry status. Retirement also remains dependent on the authoritative carbon registry. The proposed architecture provides a framework for introducing public-blockchain RWA infrastructure into Indonesia's existing carbon market while maintaining SRUK authority and existing market-integrity controls.
Read the full abstract
Software Engineering
AutoSQL: Extracting SQL Templates from Imperative ORM Code in Large-Scale Repositories
Suboptimal SQL queries can significantly degrade the performance of cloud systems, motivating the extraction and auditing of SQL statements before deployment. However, Go ORM frameworks construct SQL imperatively through scattered method-call sequences, making it difficult to statically recover the resulting SQL templates. We present AutoSQL, a system that reconstructs SQL templates from Go ORM code. AutoSQL constructs a Code Index, a directed graph that captures structural dependencies between functions, types, and global variables as navigable edges. It then traces upstream call chains from ORM invocation sites to identify database-interacting functions as entry points. For each entry point, an LLM agent traverses the Code Index to collect code slices that influence SQL generation, switching to pattern-based search when the graph cannot resolve a retrieval goal. We call this strategy Hybrid Context Retrieval. Once sufficient context is collected, the agent synthesizes SQL templates. Evaluation on a benchmark of 579 test-covered entry points and 1,186 runtime-traced SQL statements from five large-scale Go repositories shows that AutoSQL achieves 68.04% to 72.18% recall, exceeding the static reachability baseline by 11.80% to 15.94% and outperforming existing methods by 8.52% to 21.50%.
Read the full abstract
Artificial Intelligence
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails. Existing defenses lack the reasoning capacity to identify evolving manipulation patterns, often trading helpfulness for safety by over-refusing benign requests related to sensitive topics. We introduce Trace, a multi-turn defense with trajectory-aware structured reasoning. Before generating each response, the model identifies manipulation cues from the trajectory, evaluates both the benign and adversarial interpretations of user intent, assigns a jailbreak score, and commits to an action: Allow, Caution, or Decline. We curate 4k multi-turn adversarial conversations from five attack frameworks, pair them with 2.4k benign dialogs, and 600 sensitive-but-benign conversations. We train Llama-3.1-8B-Instruct with SFT and GRPO under a multi-component reward that jointly optimizes helpfulness on benign prompts and robustness against jailbreak attempts. Across seven multi-turn attack benchmarks, Trace attains an average attack success rate (ASR) of 14.5% against 31.4% for the strongest baseline and 74.9% for the undefended target, while significantly raising the attacker effort required per successful jailbreak. Trace also balances usability and safety, achieving a 93.3% average compliance on over-refusal benchmarks.
Read the full abstract
Artificial Intelligence
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Output length prediction enables length-aware scheduling and reduces overhead. Existing methods, including entropy-guided token pooling, rely on token-level entropy but overlook semantic differences between tokens, causing them to underweight important tokens and overemphasize less informative tokens. We introduce ESTP(Entropy-and-Semantic Token Pooling), a lightweight framework that combines entropy representations with attention-based semantic representations. By deriving both representations directly during prefill, ESTP captures uncertainty and semantic importance while incurring negligible additional inference latency and memory overhead compared with methods using external auxiliary models. On the ForeLen benchmark, ESTP outperforms baseline methods, achieves better prediction accuracy and lower prediction errors across most scenarios. When integrated with a length-aware scheduler in end-to-end system tests, it further improves overall throughput and reduces the padding ratio.
Read the full abstract
Artificial Intelligence
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve. Existing approaches address agent construction and one-time evaluation but provide no structured mechanism for continuous post-deployment behavioral correction without modifying the agent's source code. Most of the approaches offered in the market, require intense collection of logs and traces, and re-examining the agent design by the engineering team, a process which is heavy, long and negates the economical value of agentic transformation. We introduce Agent Gym, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop. The framework provides six composable capabilities — Act, Evaluate, Investigate, Correct, Learn, and Observe — organized across three architectural zones: a constitution layer that codifies domain knowledge in configuration artifacts, a runtime inference pipeline that chains acting, investigation, and adaptive correction, and a learning loop that enables subject matter experts to discover and validate new correction rules through natural language interaction. The key technical contributions include a hybrid deterministic-LLM correction engine with 21 condition operators and three-tier actions, a three-layer investigation architecture for ground-truth-free compliance validation, and a programmatic safety loop that guarantees rule correctness before human approval. We further introduce the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency. An open-source reference implementation for invoice processing demonstrates that the framework is fully operational and ready for adoption.
Read the full abstract
Machine Learning
GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix
Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage requirements: a long shared prefix demands contiguity, while the per-request suffix demands fine-grained allocation. We present GraniKV, a KV-cache layer that allocates the shared prefix in a contiguous HOT pool and the suffix in a token-level COLD pool, combined with a per-step dispatcher which selects the appropriate backend among dual backends for each regime (compute-, memory-, or communication-bound). To the best of our knowledge, GraniKV is the first system to apply asymmetric paging granularity to the KV cache of a production paged-serving engine. At $L_p{=}16$\,K shared tokens GraniKV reaches $\mathbf{2.16\times}$, $\mathbf{1.98\times}$, and $\mathbf{1.57\times}$ output-token throughput over the production baseline on Llama-3.1-8B/TP=1, Qwen-2.5-14B/TP=2, and Qwen-2.5-32B/TP=4. The gain decomposes: cascade attention integration contributes the majority at saturation; the asymmetric storage layer adds $1.05$–$1.15\times$ end-to-end while being what makes the batched-GEMM prefix backend possible at all. Under heterogeneous multi-agent serving with distinct prompts of different lengths, the attribution inverts: GraniKV sustains $\mathbf{1.95\times}$ while batch-global cascade collapses to parity — the storage layer alone carries the win in the regime that motivates the paper.
Read the full abstract
Computer Vision
PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes
While Text-to-Image (T2I) diffusion models have achieved remarkable success, precise spatial and orientational control in multi-object scenes remains a persistent challenge. Existing methods either rely on computationally expensive dense 3D maps or suffer from severe attribute leakage and "cut-and-paste" artifacts. To address these limitations, we propose PoseAdapter, a lightweight framework for high-fidelity 2.5D controllable image generation. Instead of dense spatial maps, it establishes precise spatial-angular anchors using an efficient condition layout: individual object captions, 2D bounding boxes, and 3D angles. To resolve the generative trade-off between strict instance isolation and global coherence, we introduce a Context-Aware Dual-Stream Representation. By injecting local object tokens and relation-enriched scene tokens into the visual stream of modern MM-DiT architectures via parallel masked and unmasked pathways, PoseAdapter eliminates attribute leakage while preserving natural inter-object relationships and scene-level coherence. To support this paradigm, we construct OrientLayout, a high-quality dataset featuring standardized 2.5D annotations and instance-level decoupled semantics. Extensive experiments demonstrate that PoseAdapter outperforms state-of-the-art baselines in spatial accuracy, orientational precision, and multi-object visual fidelity. Code and dataset will be available at https://github.com/cyf23/PoseAdapter.