Peer Revenue An exchange of ideas

Papers

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

Computer Science

cs Watch Computer Science

Monday 28 September

Robotics

GuardPIBT: Counterfactually Gated Neural Guidance for Ultra-Large-Scale 3D Multi-Agent Path Finding

Yuan Zhou, Zhenyu Hou, Guangtong Xu et al. (+4 more)

Large-scale 3D multi-agent path finding becomes increasingly difficult under dense traffic. Priority Inheritance with Backtracking (PIBT) scales well, but its one-step goal-directed ordering may become insufficient under dense interactions and large-scale congestion. We present GuardPIBT, which augments rather than replaces the PIBT executor: neural predictions only propose residual reorderings of PIBT's native candidates, while final actions remain determined by PIBT. First, local graph attention models nearby interactions, while global source–goal transport features provide population-level coordination context for candidate reordering. Second, a counterfactual group gate filters reorderings whose closed-loop effects may degrade coordination. Third, for ultra-large populations, population-adaptive grouping preserves decision granularity, asynchronous cached inference amortizes neural computation, and selective repair resolves long-tail agents. PIBT retains validity checking, priority inheritance, and backtracking throughout. Experiments with up to 100,000 agents demonstrate reliable completion across 2D and 3D environments, including all three 100,000-agent warehouse runs with zero audited graph violations. The project website is available at {\color{magenta}https://guardpibt.github.io/GuardPIBT/}.
Read the full abstract

All authors Yuan Zhou, Zhenyu Hou, Guangtong Xu, Xiaoqiang Ji, Yuqing Tang, Jialiang Hou, Fei Gao

Cryptography and Security

Continuous Assurance of Agentic Security Auditors for Software Delivery Decision Gates

Guy Lupo, Nguyen Hung Nguyen, Viet Vo et al. (+4 more)

Large language model (LLM)-based repository auditors are increasingly deployed as security controls within continuous integration (CI) pipelines, where their findings admit, block, or delay software changes. As Agentic Software Development Life Cycle (SDLC) Security Controls, their non-deterministic behaviour changes the evidence, while organisational risk appetite and jurisdictional or data-sovereignty policy change its interpretation. Point-in-time audits therefore cannot maintain current assurance for merge decisions. We propose the Policy-Evidence-Execution Separation Pattern, implemented by the Trustworthy AI Posture (TAIP) Assurance Engine and operated as Continuous Control Posture Assurance (CCPA). By separating policy from stable execution and binding admitted evidence to a versioned Posture Tree, the same assurance logic operates across models, environments, and policy profiles. We evaluate the approach using unmodified RepoAudit on a fixed Python Null Pointer Dereference benchmark. The retained evidence repository contains 80 RepoAudit executions across two OpenAI model configurations, gpt-4o-mini and gpt-4.1. TAIP recomputes assurance posture after policy, evidence, and model-context changes and is evaluated across increasing numbers of independent Decision Gateway contexts. The maximum observed policy-to-posture latency was 1.1 ms across three policy-class cycles in one execution. At 1,000 independent assurance contexts, full policy-triggered recomputation with one worker recorded a maximum aggregate refresh of 1.62 s, below the predeclared 5 s Decision Gateway budget. These single-host measurements concern assurance over retained evidence and exclude RepoAudit execution and provider inference.
Read the full abstract

All authors Guy Lupo, Nguyen Hung Nguyen, Viet Vo, M.A.P. Chamikara, Guangdong Bai, Nazatul Haque Sultan, Alsharif Abuadbba

Robotics

Repair Before You Fuse: Frozen-Host Adaptation for Corrupted-but-Present Sensors

Gia-Huy Thai, Quang-Thinh Ly, Anh-Minh Phan et al. (+1 more)

Camera-LiDAR detectors can continue to consume unreliable features even when both sensors remain present, synchronized, and calibrated. We introduce Boundary Feature Repair (BFR), a frozen-host adaptation framework that learns task-supervised residual corrections at modality interfaces the detector already consumes. BFR-C repairs each camera feature level read by fusion, whereas BFR-L aligns host-conditioned LiDAR candidates to a selected boundary and routes site-wise innovations relative to the frozen anchor. Their jointly trained composition is BFR-CL. Zero-initialized per-channel scales make every variant an exact detector-level identity before optimization; only the repair modules train, while the encoders, fusion consumer, router, detection head, and host normalization statistics remain fixed. At inference, BFR requires neither clean references, corruption metadata, temporal history, nor online updates. Across the complete 20-corruption, five-severity KITTI-C grid, BFR-C reduces RCE from $14.07$ to $11.92$ on MVX-Net and from $14.29$ to $11.00$ on Focals Conv-F relative to their reproduced frozen baselines. On the latter host, BFR-L raises AP$_{\mathrm{cor}}$ from $73.65$ to $74.48$, while BFR-CL reaches $77.01$ AP$_{\mathrm{cor}}$ and $10.46$ RCE with $86.02$ clean AP. On nuScenes-R, BFR-CL raises the reproduced MoME baseline's mAP robustness ratio from $80.1$ to $81.4$. These results establish boundary repair as a targeted retrofit for corrupted-but-present sensing without retraining the deployed detector.
Read the full abstract

All authors Gia-Huy Thai, Quang-Thinh Ly, Anh-Minh Phan, Tuan Dang

Distributed Computing

WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse

Aaryam Sharma

Pipeline parallelism can improve prefill throughput by processing multiple request chunks concurrently across different stages of the model. However, keeping the pipeline fully utilized requires efficient scheduling and request preparation. In systems where stages retain and evict cache state independently, a local cache hit does not guarantee that the same prefix can be reused across the pipeline. Here, coordination overhead can impede request admission cadence and thus reduce overall throughput. In this paper, we present WavePP, a prefill runtime built on top of TensorRT-LLM that addresses these challenges by overlapping request admission with pipeline execution. WavePP asynchronously finds a prefix that can be reused across all stages, protects the cached state, and reserves space for the remaining input while earlier requests continue to execute. It subsequently plans the chunk sizes of each request dynamically to maximize pipeline fill. Each stage then completes the local preparation before executing the request. In the same system and pipeline topology, WavePP improves TensorRT-LLM's prefill throughput in 37 of 40 tested settings on GLM 5.2 and MiniMax M2.7. At concurrency 128 with high cache reuse, these changes increase throughput by factors of 2.91 and 2.02, respectively. Across 28 Kimi K3 settings, WavePP also has the highest measured throughput in all 18 settings at concurrency eight or higher, compared with tensor/expert-parallel and pipeline-parallel baselines from TRT-LLM, SGLang, and vLLM.
Read the full abstract

Computation and Language

Rubric-Aware On-Policy Self-Distillation for LLM Personalization

Yilun Qiu, Xiaoyan Zhao, Chengbing Wang et al. (+6 more)

LLM personalization aims to generate responses aligned with individual users' preferences and needs. User-specific rubrics make these expectations explicit, providing direct supervision on what a satisfactory answer should cover. Existing rubric-guided approaches, however, exploit such guidance only at a coarse granularity, either by using rubrics to supervise the prediction of relevant aspects for subsequent generation or by reducing aspect coverage to a single response-level reward for reinforcement learning. This leaves a gap between specifying what a personalized answer should contain and teaching the model how to generate it. To bridge this gap, we propose GRASP, a rubric-aware on-policy self-distillation framework for LLM personalization that turns user-specific rubric aspects into fine-grained, token-level supervision. Specifically, GRASP pairs a rubric-free student with a rubric-informed teacher that additionally receives the target user-specific rubrics. By aligning their next-token distributions along on-policy trajectories generated by the student, GRASP transfers the teacher's rubric-conditioned guidance into the student, translating user-specific semantic requirements into dense token-level supervision. Since rubric-informed teachers can still produce inadequate supervision, we further introduce Rubric-based Teacher Validation (RTV), which retains only instances where the teacher sufficiently covers the target aspects, improving both supervision quality and training efficiency. Experiments on the LaMP-QA benchmark for personalized question answering demonstrate that GRASP achieves state-of-the-art performance across multiple backbones, supporting the effectiveness of rubric-guided token-level supervision for personalization. To ensure reproducibility, our code is available at https://github.com/SnowCharmQ/GRASP.
Read the full abstract

All authors Yilun Qiu, Xiaoyan Zhao, Chengbing Wang, Cilin Yan, Rui Zu, Wanyang Zhang, Xiaolong Jiang, Jiayin Cai, Yang Zhang

Artificial Intelligence

Imprint Reader: From Weight-Update Readout to Behavioral Intervention

Guanxu Chen, Qihao Lin and Jing Shao

As language models take a growing role in AI development, a natural aspiration is for them to reflect on their own learning process, as humans do, and use that reflection to improve themselves. At the same time, these models have an advantage that human learners lack, since training leaves parameter-level traces that can, in principle, be inspected directly. However, current models cannot decode these traces into an explicit account of what they have learned. To this end, we introduce the Imprint Reader, a model trained with Semantic Mount-and-Read Tuning (SaRT) to describe frozen weight updates. SMaRT mounts each update onto the Reader and uses an anchor-free meta-query to elicit a natural-language description, while no-change and random-perturbation controls discourage unsupported claims. On held-out updates, the joint Reader reaches judge-based Pass@100 of $2\%$ for knowledge and $16\%$ for behavior. These results demonstrate the feasibility of natural-language readout while pointing to reliability across updates as the next step. Beyond free-form generation, the Reader provides a differentiable proxy for the gap between a specified target behavior and a candidate weight update. Its coordinate-aligned gradients support intervention through MetaEdit. At a $0.5\%$ pruning rate, Reader-guided selection raises measured harmful-prompt refusal from $57.9\%$ to $64.1\%$ under a safety-maintenance target. Using behavior descriptions without target-task training data, MetaEdit increases the frequency of backtracking and sub-goal expressions in mathematical reasoning traces and raises BFCL Overall from $41.69\%$ to $44.60\%$.
Read the full abstract

Machine Learning

Latency and accuracy tradeoffs in Spiking Neural Networks

Zhanglu Yan, Zixuan Zhu, Kaiwen Tang et al. (+3 more)

Spiking neural networks are attractive for low-power speech command recognition, yet their latency has received far less attention than their energy efficiency, and their multi-timestep execution is widely assumed to make them slower than quantized neural networks. This paper challenges the assumption that more local timesteps necessarily imply higher network latency. By overlapping computation across adjacent layers at the timestep level, SNNs may complete execution in less time than comparable bit-serial QNNs. However, this overlap relies on spikes firing on incomplete inputs, and a spike once generated cannot be withdrawn, so its error persists and reduces accuracy. Waiting for more input before firing would seem to improve accuracy at the cost of reduced overlap. Yet we find and prove that this intuition fails at some layers, where even a small increase in waiting can change spike timing and downstream computation, making the network both slower and less accurate. We therefore propose a Pipeline Delay Search method which selects each layer's delay by balancing task-level accuracy gains against added network latency. We then adapt the selected configurations through spike-based quantization-aware training and bounded tuning of firing thresholds and initial membrane potentials. Together, these steps form Falcon, a framework for Fine-grained Analysis of Latency and Controlled firing which systematically analyzes and optimizes SNN latency under a spatial analog compute-in-memory mapping with shared digital engines. We evaluate Falcon on GSCV2 and SSC, achieving competitive accuracies of 96.31 and 83.02 at modeled network-core latencies of 119.64 and 124.00us, respectively. Together, our analysis and results show that SNNs can compute more yet finish faster, and wait longer yet predict worse, highlighting why Falcon matters for both latency and accuracy.
Read the full abstract

All authors Zhanglu Yan, Zixuan Zhu, Kaiwen Tang, Yuyang Cai, Qianhui Liu, Weng-Fai Wong

Machine Learning

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Julianna Piskorz, Antonin Berthon and Mihaela van der Schaar

On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve generalisation. However, existing comparisons between supervised fine-tuning and reinforcement learning vary many factors simultaneously, making the contribution of rollout policy difficult to isolate. We study the effect of rollout policy in a controlled strong-to-weak distillation setting, by independently varying rollout policy, token-level KL direction, and learning rate across the Llama3 and Qwen2.5 model families and reasoning tasks spanning scientific, medical, and arithmetic domains. Our analysis reveals a nuanced picture of distillation dynamics in which rollout policy does not necessarily play a central role. Instead, token-level KL direction more clearly shapes task performance and output coverage, while learning rate governs forgetting and update sparsity. Analysis of KL gradients and experiments along a continuous student-teacher rollout-policy spectrum explain this pattern: forward KL is remarkably robust to rollout policy, with its performance stable and strong despite changes to the rollout policy, whereas reverse KL is substantially more sensitive and favours student-generated rollouts. On-policy data nevertheless improves generalisation to harder variants of the Countdown arithmetic task under both KL directions, although this advantage does not reliably persist after subsequent RLVR. Our broader conclusions remain robust to removing gradient clipping, using sampled KL estimators, and training on tasks requiring longer reasoning chains. Overall, our results challenge the view that on-policy rollouts are inherently preferable and show that their value depends critically on the objective, evaluation setting, and optimisation hyperparameters.
Read the full abstract

Machine Learning

AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning

Yue Xie, Zhi Zheng, Yunpeng Ba et al. (+5 more)

Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbed parameters, without backpropagation or activation storage. However, in billion-parameter LLMs, isotropic perturbations often waste many forward evaluations on weakly informative directions. To make these evaluations more informative, existing ZO methods restrict perturbations to low-dimensional subspaces. Yet the quality of these subspaces is critical: overly compressed or poorly maintained spaces can miss useful update directions. To obtain a high-quality subspace for ZO updates, this paper proposes AIM-ZO, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance. AIM-ZO uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training. To access broader gradient-relevant structure while keeping individual perturbations low-dimensional, AIM-ZO activates only a smaller set of shared and sampled directions, decoupling the maintained width from the active width. We evaluate AIM-ZO across 5 LLMs and 11 downstream tasks under matched forward-evaluation budgets; its six-task average exceeds the strongest fully evaluated ZO baseline by 1.26 percentage points on OPT-2.7B and MeZO by 2.85 percentage points on OPT-30B. Our code is available at https://github.com/EkkoXy/AIM-ZO
Read the full abstract

All authors Yue Xie, Zhi Zheng, Yunpeng Ba, Xuyang Wu, Xialiang Tong, Zhichao Lu, Tao Zhong, Zhenkun Wang

Cryptography and Security

Implementing Data Diodes Using Commodity Hardware and Open Source Software

Peter Story and Gert-Jan den Besten

One-way network devices, known as data diodes, are used to defend against sophisticated cyberattacks. Partly due to their high cost, data diodes are mostly deployed in nuclear power plants and within the government for handling classified information. Although commercially available data diodes are expensive, a data diode's hardware can assembled from commodity fiber-optic network equipment. However, specialized software is needed to send data through a data diode reliably: the receiving program cannot request retransmission of dropped packets, so packet loss must be minimized and mitigated. First, we developed a minimal program to measure packet loss. We found that most packet loss was caused by the receiving program processing incoming packets too slowly, and that packet loss often occurs in clusters. Also, we discovered ways to minimize packet loss on Linux and macOS without using superuser privileges. Next, we tested three existing open source programs for one-way data transfers: netcat, UDPcast, and lidi. Although these programs were unreliable in their default configurations, we identified reliable configurations for UDPcast and lidi. Finally, we incorporated our findings into pydiode, our cross-platform program for reliable one-way data transfers.
Read the full abstract

Artificial Intelligence

Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses

Huachi Zhou, Yujing Zhang, Jiahe Du et al. (+7 more)

Large language model agents are increasingly deployed for data-intensive work, yet reliable data analysis requires more than general-purpose reasoning and ad hoc tool augmentation. Data Agents, equipped with workflow harnesses, offer a promising paradigm for automating the end-to-end data science lifecycle. This paper examines Data Agents from a harness-centric perspective. First, we introduce a taxonomy of Data Agents and associated data environments, organizing the literature around five functional stages: perception, planning, execution, verification, and repair. Second, we analyze the key technical routes within each stage, identifying 15 distinct approaches ranging from data structure probing to data state reconstruction. Third, we identify four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository. These problems explain why silent failures can persist even when individual components function correctly, highlighting the need for rigorous workflow harnesses and shared reliability resources. Finally, we summarize the horizontal task families of Data Agents, examine their vertical application settings, and benchmarks for evaluation, while maintaining a companion repository at https://github.com/DEEP-PolyU/Awesome-Data-Agents.
Read the full abstract

All authors Huachi Zhou, Yujing Zhang, Jiahe Du, Jiacheng Cai, Zijin Hong, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Qing Li, Xiao Huang

Hardware Architecture

MEGATRON: a 28nm Analog PCM CiM/Digital System-on-Chip for Edge GenAI at 57.5 TOPS/W and 1.52 Mparam/mm${}^2$

Alessandro Nadalini, Angelo Garofalo, Lorenzo Greco et al. (+12 more)

We present MEGATRON, a heterogeneous Edge GenAI System-on-Chip in 28nm FD-SOI CMOS technology combining a non-volatile analog in-memory-computing engine based on a 4Mi-cell phase-change memory (PCM) array with a digital RISC-V-based flexible neural processing unit. MEGATRON demonstrates up to 3.5 TOPS/W using the RISC-V processors and 57.5 TOPS/W with PCiM, at a storage density of 1.52 Mparam/mm${}^2$ with 4-bit effective weight precision.
Read the full abstract

All authors Alessandro Nadalini, Angelo Garofalo, Lorenzo Greco, Andrea Belano, Alessio Antolini, Francesco Zavalloni, Andrea Lico, Riccardo Zurla, Emanuela Calvetti, Luigi Croce, Marco Pasotti, Alessandro Cabrini, Eleonora Franchi Scarselli, Davide Rossi, Francesco Conti

Computation and Language

SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys

Yuanzi Li, Lingjie Wang, Zihang Tian et al. (+2 more)

Large Language Models (LLMs) offer a scalable way to simulate survey respondents using demographic profiles and observed reference responses. However, the conventional approach of predicting one question per prompt repeatedly encodes the same context, limits each target to a narrow set of reference responses, and prevents later predictions from using information in earlier answers. Predicting multiple questions in one prompt can reduce these costs, share a broader pool of references, and let later predictions build on earlier ones. This requires forming coherent batches, selecting shared references, and ordering questions and references effectively. We propose Semantically Coherent Batching and Ordering (SCBO), a training-free framework that addresses these challenges. SCBO first uses an LLM to extract compact semantic representations from survey items and filter out template noise. It then groups related questions into batches and builds a shared reference bank using target-specific retrieval and centroid-based completion. Finally, it orders target questions from easy to hard and arranges references according to their semantic alignment with those questions. Experiments on four large-scale survey datasets and four LLMs show that SCBO substantially reduces token consumption and inference time while generally improving prediction accuracy over a non-batched baseline. Code is available at https://anonymous.4open.science/r/SCBO-41D8.
Read the full abstract

All authors Yuanzi Li, Lingjie Wang, Zihang Tian, Lei Wang, Xu Chen

Robotics

Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies

Dingsheng Liu, Yangzheng Wu, Mahboubeh Asadi et al. (+5 more)

Pretrained robot manipulation policies such as vision-language-action models (VLAs) or world-action models (WAMs) leave interaction-relevant metric geometry implicit. Recent breakthroughs in spatial reconstruction can supply the necessary geometry reliably, but their features describe local shape without stating where it lies with respect to the robot. How best to deliver these features to a pretrained policy remains unresolved. We propose Spatial Grafting, a versatile, lightweight spatial module that binds frozen reconstruction features to metric, robot-relative geometry. Spatial Grafting constructs metric-grounded spatial tokens and injects them into the flow-matching action expert through cross-attention, without modifying the host's perceptual pathway, so the host retains the full benefit of its pretraining. We evaluate it more broadly than any geometry-aware policy we compare against: one graft architecture, with no per-host redesign, on two VLAs and two WAMs, across four simulation benchmarks that span short-horizon manipulation, visual robustness, clutter and long-horizon mobile manipulation, and on three real-robot platforms with single- and dual-arm configurations. On RoboTwin 2.0, a dual-arm manipulation benchmark, the graft improves every host across VLAs and WAMs. Grafted $\pi_{0.5}$ gains 11.3% and 15.6% on clean and randomized scenes, reaching 94.0% and 92.4%, above the strongest published 3D-conditioned policy, WAM4D (93.8% and 89.9%). The margin widens as the horizon lengthens: on tasks from BEHAVIOR-1K, a dual-arm mobile manipulation challenge scored by average task progress, it surpasses the 2025 challenge winner on five of six tasks,by up to 0.47 Q-score, and exceeds a map-conditioned spatial policy on average across the three tasks both report.
Read the full abstract

All authors Dingsheng Liu, Yangzheng Wu, Mahboubeh Asadi, Zhiyuan Li, Jinbang Huang, Yixin Xiao, Tongtong Cao, Yingxue Zhang

Computer Vision

AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors

Mohamed Eltahir, Fardows Adam, Duaa M. Tahir et al. (+6 more)

When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, which originate too early to reflect the final output and require white-box access to the model. We introduce AnswerMap, a training-free, task-agnostic, black-box visual rationale constructed from the output head. The image is cut into K row and K column bands, each shown alone to the frozen model along with the query in the format of a yes/no relevance question. The outer product of the row and column “yes” posteriors gives the query-conditioned spatial map. Crucially, by defining a fixed read-out R (e.g., expectation, maximum) on top of AnswerMap, we can derive continuous outputs like location natively. This bypasses the reliance on discrete text tokens for continuous-output tasks and guarantees an image-dependent answer by construction. However, a rationale can be confabulated, so we validate AnswerMap across four models and three query distributions with two tests: (a) agreement with the model's own generated point and (b) deletion of the map's region. The map lands where the model points (AUC 0.85 against 0.38 for attention), and deleting its region flips 53% of correct answers (against 19% for attention's). Beyond establishing faithfulness, we demonstrate the map's task-agnostic utility through three distinct read-outs: its maximum flags hallucinated objects without generation, its expectation localizes correctly when the model's own pointing fails, and its top-mass region, fed back as a crop, fixes half of the model's wrong answers. AnswerMap thus offers a new lens on VLM interpretability and, through its read-outs, a new output interface for visual tasks beyond text tokens.
Read the full abstract

All authors Mohamed Eltahir, Fardows Adam, Duaa M. Tahir, Lama Alamoudi, Sana Ammar, Atheer A. Alboloshi, Jory Albluey, Tanveer Hussain, Naeemullah Khan

Systems and Control

Hard-Constrained Probabilistic Factor Graph Neural Network for Distribution System State Estimation under Non-Gaussian Uncertainty

M. Furqan Azam, Marta Vanin, Chris Hermans et al. (+1 more)

Robust and accurate state estimation is fundamental for the reliable operation and monitoring of active distribution networks. Conventional numerical estimators, such as weighted least squares, are computationally slower and often suffer from convergence issues in the presence of sparse measurements affected by non-Gaussian noise. Physics-informed neural networks have recently emerged as a promising alternative by incorporating physical principles through residual-based penalty terms in the objective, which can improve robustness to noise and computational efficiency. However, such penalty-based approaches do not guarantee strict enforcement of physical constraints during inference and provide limited support for principled uncertainty modeling. To address these limitations, we propose a novel Hard-Constrained, Physics-Informed Factor Graph Neural Network (HCP-PINN) that formulates distribution system state estimation as a probabilistic constrained estimation problem on a factor graph. The proposed approach explicitly models non-Gaussian (pseudo-)measurement uncertainty through flexible, closed-form likelihood-based loss functions. It further incorporates a differentiable optimization-based estimation layer that strictly enforces nonlinear equality constraints and measurement consistency, producing physically feasible state estimates during both training and inference. To the best of our knowledge, this is the first PINN-based DSSE framework to combine hard physical constraints with non-Gaussian uncertainty modeling for unbalanced three-phase networks. Numerical experiments demonstrate that the proposed method delivers more accurate and physically consistent state estimates than deep learning benchmarks and numerical estimators, while exhibiting greater robustness to network model errors and improved computational efficiency under realistic measurement scenarios.
Read the full abstract

All authors M. Furqan Azam, Marta Vanin, Chris Hermans, Geert Deconinck

Computer Vision

DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model

Shurui Liu, Weide Chen, Changwang Yi et al. (+1 more)

Scalable Vector Graphics (SVG) are essential for modern industrial Computer-Aided Design (CAD). However, existing autoregressive SVG generation models are predominantly tailored for artistic creation and struggle to maintain the rigorous geometric fidelity and cross-view spatial alignment required for engineering drawings. To bridge this gap, we introduce DrawingsDreamer, a unified Large Language Model (LLM)-driven framework for multi-view vector-based engineering drawings generation. By formulating the generation of multi-view engineering drawings purely as a sequence modeling task, we eliminate the need of raster image encoders. We propose a Streamlined Representation utilizing hierarchical postfix tokenization, which guides the model to establish local geometric coordinates before assigning semantic boundaries. Optimized via a progressive task-aware curriculum schedule, DrawingsDreamer effectively transitions from localized structural repair to macroscopic generation in a unified model. Extensive experiments demonstrate that our unified model achieves strong performance in both geometric fidelity and syntactic accuracy across diverse conditional and unconditional generation tasks.
Read the full abstract

All authors Shurui Liu, Weide Chen, Changwang Yi, Ancong Wu

Machine Learning

Disentangling Lung-Cancer CT/LDCT AI: A Systematic Evidence Map of Clinical Tasks, Evidence Chains, and Translational Gaps

Surajit Das

Artificial-intelligence studies using computed tomography (CT) for lung cancer are often broadly labelled "prediction" despite addressing clinically distinct tasks. We systematically mapped CT/low-dose CT (LDCT)-centered lung-cancer AI using five-database retrieval, full-text eligibility assessment, role-aware modality/omics extraction, clinical-task classification, and a Multi-Tier Evidence Graph (MTEG). The final corpus comprised 293 studies (2016-2026): 230 Detection, 8 future Risk-prediction, and 55 Other studies. Clinical variables (96.2%), 3D CT/LDCT (73.0%), and radiomics (63.5%) predominated, whereas external validation (29.0%), calibration (20.5%), decision-curve analysis (13.0%), longitudinal CT (17.7%), and saliency/attribution XAI (21.5%) were less frequent. The MTEG comprised 377 nodes and 3,444 edges; only 31 studies (10.6%) completed the six-tier substantive evidence chain, with greatest attrition at reasoning/explanation. Overall, the literature is detection-dominated, genuine future risk prediction remains uncommon, and complete translational evidence chains are rare.
Read the full abstract

Computational Complexity · Cross-listed from quant-ph

Computational Complexity of Clifford Template Compilation: Are Quantum Computers Useful for Compiling Quantum Circuits?

Keisuke Fujii

A Clifford template is a finite ordered family of repeatable Clifford operations, and an instantiation specifies how many times each operation is applied. The Clifford template compilation problem asks how to choose these repetition numbers so that the template realizes a target transformation of Pauli operators. This problem arises, for example, when searching for logical operations in quantum error correction using only Clifford operations permitted by physical or fault-tolerance constraints. Although forward Clifford dynamics is efficiently classically simulable, this inverse problem has sharp complexity transitions. For commuting templates with unrestricted integer exponents, feasibility lies in $\mathrm{NP}\cap\mathrm{BQP}$ and a constructive quantum algorithm returns a particular solution together with the full exponent-relation lattice; already at $k=1$, recovering the repetition number contains finite-field discrete logarithm over $\mathbb{F}_{2^r}^{\times}$. In general, restricting every exponent to $\{0,1\}$ removes the Abelian-group closure and makes feasibility NP-complete for variable $k$, even for exactly commuting CNOT-only operations and X-type Paulis. For commuting self-inverse Clifford actions, both binary feasibility and recovery of one solution are classically polynomial-time solvable, but imposing a bound on the total repetition count is NP-complete, even for CNOT-only operations. These results reveal a rich complexity landscape within Clifford template compilation, spanning classically tractable cases, problems admitting quantum polynomial-time algorithms, and NP-complete variants.
Read the full abstract

Machine Learning

Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation

Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu et al. (+5 more)

Long-horizon agents improve solutions through sustained interaction, execution, and task feedback. Scaling studies relate performance to resources and capabilities, yet how existing capabilities shape returns to extended interaction remains less understood. To address this gap, we analyze AutoLab and EdgeBench, two long-horizon benchmarks. We find that starting performance and subsequent growth are associated with different capabilities: within a task category, similar early scores can precede different later gains. To formalize this finding, we model capability-time scaling with category-specific logistic power laws shared across models. Fitted to early trajectories, these curves extrapolate the observed models' category-average scores to later computation. However, rising average scores mask narrowing improvement opportunities: later gains concentrate among fewer improving models. High final scores and continued improvement also have distinct capability profiles. Predicted mean gains estimate each model's fraction of improving tasks; averaging these estimates forecasts the average share of improving models. These uneven returns motivate deciding whether a specific run should continue. We therefore derive a continuation policy to save time and compute with limited score loss. The policy conditions growth predictions on the run's observed progress and weighs immediate and delayed gains against computation costs. In replay with training and price calibration based on other models' histories, the policy saves roughly one-third of full-run time, with relative score losses of 2.4% on AutoLab individual runs and 3.3% on EdgeBench published mean curves. Our repository is available at https://github.com/Chihaya-Anon-chan/long-horizon-scaling.
Read the full abstract

All authors Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu, Ruishan Fang, Teng Xiao, Yiwei Li, Jingang Wang, Wenqiao Zhang

Data Structures and Algorithms

A $5/2$-Approximation for Weighted Ultrametric Embedding with Outliers

Chenglin Fan

Weighted ultrametric embedding with outliers asks for a minimum weight set of points whose deletion makes the remaining metric an ultrametric, equivalently, leaves no triple with a unique largest distance. We give a deterministic $5/2$-approximation using $O(n^5)$ arithmetic and comparison operations, improving the previous factor $3$ for arbitrary nonnegative vertex weights. Approximating the problem within any factor strictly below $2$ is UGC-hard.
Read the full abstract

Cryptography and Security

Poster: Towards ProofWeave: A Privacy-Minimised, Integrity-Anchored Evidence Plane for Continuous Agentic Assurance

Guy Lupo, Nguyen Hung Nguyen, Viet Vo et al. (+2 more)

Agentic AI systems increasingly act via tools, memory, delegation, and external services. Existing observability and provenance mechanisms can reconstruct events post hoc, but they rarely show, at the time of the record, whether each policy-relevant action was checked by the intended control before execution. This leaves a trust-observability gap for continuous monitoring, detection, and response: later assurance may rest on evidence that is incomplete, privacy-leaking, mutable, or detached from the policy context that governed the event. What's missing in the literature is contemporaneous, policy-bound evidence that the intended control was evaluated under the policy in force at the time. We introduce ProofWeave, a record-time chain-of-evidence concept for agentic AI assurance. At each policy-relevant action boundary, ProofWeave generates a privacy-minimised and integrity-anchored evidence transaction that binds (i) agent intent or action, (ii) control response, and (iii) a policy-at-time snapshot. Each transaction is committed to an append-only ledger and materialised into a derived proof graph. A bounded Weaver Agent translates policy intent into proof obligations, while deterministic validators check evidence completeness, privacy minimisation, policy binding, and integrity. In the minimal scenario, an agent attempts to transmit a secret to an unapproved external sink. The audit compares a logs-only correlation baseline with ProofWeave across verdict latency, join ambiguity, privacy exposure, tamper detection, and resistance to graph-only proof injection. ProofWeave reduces candidate bindings per verdict from up to `10,201` to one, validation operations from up to `10,201` to approximately `26`, and assurance evidence storage from `0.79`M̃iB to `0.15`M̃iB per project.
Read the full abstract

All authors Guy Lupo, Nguyen Hung Nguyen, Viet Vo, Chamikara M.A.P., Guangdong Bai

Artificial Intelligence

EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents

Fengzhou Sun, Yuan Zhang, Xintong Yu et al. (+1 more)

Large language model (LLM) agents face critical privacy risks when acting as delegates in human-agent-human communication. To prevent such breaches, agents must understand users' social relationships and adhere to context-dependent social information disclosure boundaries. Current studies on agent memory privacy focus on instantaneous interactions, leaving the long-term relational disclosure problem unexplored. In this paper, we propose EP-Mem, an Elastic Privacy Memory architecture that reframes privacy as user-owned boundary control across social roles. EP-Mem introduces (1) token-level memory driven by user-configurable a privacy policy that stratifies persons and events, combining domain-level default circulation rules with fact-level whitelist/blacklist exceptions; and (2) a pluggable sidecar with a privacy engine that aligns disclosure controls with memory across summary, detail, and boundary granularities, enforced throughout generation, storage, and retrieval. We construct EP-Bench, to our knowledge the first long-term multi-party benchmark with cross-session correlated events for policy-conditioned relational disclosure. Experiments show that EP-Mem achieves 94.0% privacy classification accuracy, improves disclosure-permission judgment from 22% to 68%, and reduces privacy leakage by 75.6%, while maintaining retrieval performance and cross-benchmark generalization.
Read the full abstract

All authors Fengzhou Sun, Yuan Zhang, Xintong Yu, Jinyao Yan

Computer Vision

Beyond Selection: Token Parameterization for Extreme Visual Token Compression

Rui Zhong, Yu Li, Zheyu Yan et al. (+1 more)

Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pruning can break visual grounding while learned resamplers increase parameter count, attention cost, and training complexity. We revisit compression through a token parameterization lens, separating (i) basis transformation and structured truncation (retained subspace/compressibility) from (ii) coordinate organization (optimization and cross-modal alignment). This view yields two coupled objectives, compressibility and learnability, which we formalize as unified functionals. Guided by these objectives, we design Braco, a lightweight four-step coder that combines transform-basis truncation, input-independent basis-coordinate embeddings, budget-dependent orthogonal re-parameterization, and learned spatial residual tokens from lightweight pooling. Experiments show that Braco forms the favorable empirical accuracy-efficiency frontier under $23\times$–$64\times$ compression and remains competitive at $144\times$, reaching 95.2% accuracy while reducing prefill FLOPs by 84.2%–86.7% relative to the uncompressed upper bound. Against prior methods, Braco matches or improves accuracy while achieving up to approximately 36% end-to-end speedup and using $16.6\times$/$78.8\times$ lower compressor latency/FLOPs.
Read the full abstract

All authors Rui Zhong, Yu Li, Zheyu Yan, Cheng Zhuo

Robotics

Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies

Weihang Guo and Lydia E. Kavraki

We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching, including diffusion policies and vision-language-action models. Our work injects gradients from a signed distance field, a function returning each point's distance to the nearest obstacle, into the policy at inference time to steer it away from obstacles. It supports any common action parameterization, from absolute or relative joint poses to end-effector poses, through a differentiable joint-trajectory decoder. Experiments show that NUDGE preserves the policy's task distribution and runs reactively in real time.
Read the full abstract

Computer Vision

Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning

Hao-Xuan Ma, Yihao Liu, Yutao Sun et al. (+8 more)

Latent test-time scaling improves reasoning by refining hidden states during inference, but existing methods typically apply a single scalar reward to all editable latent tokens. For multimodal large language models, this global update ignores that generated tokens play different roles: some are sensitive to visual evidence, while others correspond to uncertain reasoning decisions. We present Token-Disentangled Latent Test-Time Scaling, an inference-time framework that makes latent refinement token-role-aware. Starting from an initial generated trajectory, we optimize a short hidden-state prefix while routing perception-side visual feedback to image-sensitive tokens and reasoning feedback to high-entropy tokens. Tokens selected by neither route are constrained by an anchor regularizer. Across both perception and reasoning benchmarks on Qwen2.5-VL-7B and InternVL3.5-8B, our method lifts macro accuracy over CoT by +2.57 and +1.51 respectively, and outperforms strong output-space test-time scaling baselines under matched decoded-candidate budgets. Code is available at https://github.com/Qwen-Applications/TD-LTTS.
Read the full abstract

All authors Hao-Xuan Ma, Yihao Liu, Yutao Sun, Yanting Miao, Mengyu Zhou, YiCheng Xiao, Long Chen, Zhenguo Li, Han-Jia Ye, Xiaoxi Jiang, Guanjun Jiang

Computer Vision

Generative AI-Based Data Augmentation for Oral Lesion Classification: The PhotoMOCI Dataset and Benchmark

Marco Parola, Mario G.C.A. Cimino and Sabrina Senatore

Early detection of oral cancer via photographic imaging presents a promising avenue for large-scale oral cavity screening. However, the development of robust deep learning models is frequently hampered by the scarcity of high-quality, annotated datasets. To address this limitation, a novel and well-curated resource, the Photographic Multi-purpose Oral Cancer Imaging (PhotoMOCI) dataset, is introduced for developing models across multiple diagnostic tasks in oral oncology. Then, a comprehensive benchmark study was conducted to investigate how various data augmentation strategies influence the performance of image classifiers. Our analysis spans different generative AI frameworks, evaluating the efficacy of traditional methods against advanced generative approaches, including Generative Adversarial Networks (GANs) and Diffusion Models (DMs). Additionally, we propose the Synthetic Image Filter (SIF), a mechanism to select specific samples based on two auxiliary models: Synthetic Proxy Classifier to ensure samples are representative of the target class and Synthetic Image Detector to verify they appear realistic, thereby selecting only the high-utility images that contribute to improving downstream performance. Across the evaluated datasets and classifiers, the best SIF-filtered setup improves accuracy over traditional augmentation in all cases, with gains of +1.73% and +2.35% on PhotoMOCI and +2.38% and +2.08% on KOCD for ResNet50 and ViT, respectively. Our findings reveal that while the direct application of generative data augmentation may yield performance drops, the integration of SIF, considering (i) how synthetic data looks real and (ii) how it reflects the discriminative features of the belonging class, provides a simple yet effective mechanism to filter out synthetic samples that confuse the classifier during training.
Read the full abstract

Computation and Language

SignFLIP: A Unified Model for Sign Language Translation and Generation via Stage-wise Alignment at Scale

Zhaoyi An, Sihan Tan, Youngbae Hwang et al. (+2 more)

Sign language translation and generation share the goal of bidirectional alignment between text and sign representations. However, existing approaches either treat them as isolated tasks or are only verified on limited datasets, limiting effective modeling between modalities. In this paper, we propose SignFLIP, a unified LLM-centered framework for translation and generation. To enable bidirectional mapping between text and sign, SignFLIP adopts a symmetric architecture together with a stage-wise training strategy built on large-scale data. The shared sign–text representation is progressively refined: pre-alignment facilitates subsequent SLT, while the SLT-adapted representation further benefits SLG. Extensive experiments on multiple benchmarks show that SignFLIP shows competitive performance compared with task-specific models on both translation and generation tasks, as well as strong transferability to sign language recognition.
Read the full abstract

All authors Zhaoyi An, Sihan Tan, Youngbae Hwang, Kazuhiro Nakadai, Rei Kawakami

Machine Learning

TANGO: Watermarking Masked Diffusion Language Models in Token Pairs

Kasra Arabi, Nir Weinberger, Micah Goldblum et al. (+1 more)

Masked-diffusion language models fill in masked positions in parallel and in no fixed order. Most practical text watermarks assume left-to-right generation. They key each token to the tokens before it, and in a diffusion model those tokens may still be masked. A fixed green list needs no such context, but it favors the same tokens at every position, so these tokens appear more often in watermarked text. An attacker who compares token frequencies in watermarked and unwatermarked text can recover the list and forge text that the provider's own detector accepts. We present TANGO, a watermark for masked-diffusion language models that keys each new token to a nearby token that is already unmasked. A secret key splits the vocabulary into color classes, and TANGO biases the new token toward a color determined by the key and the nearby token's color. The watermark is therefore embedded in pairs of tokens. Because the favored color changes from position to position, token frequencies stay much closer to those of unwatermarked text than under a fixed green list. Detection needs only the text and the key, and it does not assume any unmasking order. On two masked-diffusion models, TANGO detects nearly all unedited watermarked texts and most edited ones, and frequency attacks that forge the fixed green list fail against it.
Read the full abstract

All authors Kasra Arabi, Nir Weinberger, Micah Goldblum, Niv Cohen

Machine Learning

Temporal Heterogeneous Graph Pretraining for Relational Deep Learning

Yixin Peng, Er Jin, Diego Collarana et al. (+1 more)

Relational deep learning models database rows and foreign-key links as a heterogeneous graph for prediction from record attributes and relational context. These graphs contain two distinct temporal signals: record age changes with the prediction cutoff, while intervals between observed records remain fixed. Prior work often treats time as a single signal or studies temporal representation and pretraining separately. We investigate how explicitly encoding both signals affects temporal pretraining for downstream tasks. Our framework combines Multi-scale Time Encoding, which captures record age using learnable time scales and type-specific projections, with Rotary Time Encoding, which represents signed inter-record intervals through rotary transformations during graph propagation. We pair these encodings with three self-supervised objectives: historical relation recovery, horizon-aware future relation activity prediction, and temporal subgraph contrast. All inputs respect their observation cutoffs. Pretraining proceeds in two stages: subgraph contrast first learns neighborhood representations, followed by refinement through either relation recovery or future activity prediction. We evaluate on five RelBench datasets across 11 classification and regression tasks using heterogeneous GNN and graph Transformer backbones. With both encodings, the best evaluated staged schedules improve over supervised training with the same encodings by 3.02% and 1.06% on the two backbones, respectively, and over controls without pretraining or either encoding by 3.24% and 2.37%.
Read the full abstract

All authors Yixin Peng, Er Jin, Diego Collarana, Stefan Decker