跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 03:48 — 2026-11-22 03:48(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2611.18527

WaferTetris: Efficient Freeform Mapping on Wafer-Scale Accelerators

Dayou Du, Congjie He, Andrew Boutros, Luo Mai, Vaughn Betz, Jianyi Cheng

原文摘要

Wafer-scale accelerators offer massive compute capacity through hundreds of thousands of processing elements (PEs) interconnected across a single wafer, but realizing this potential requires efficient application mapping. Their scale makes programming these systems and mapping applications onto them challenging. Existing approaches rely on template-based mappings to maintain productivity, but these templates restrict the mapping design space. In particular, they impose fixed geometric layouts over the PE grid, often leaving compute and memory resources underutilized. In this work, we present WaferTetris, a system that removes these geometric restrictions through freeform mapping. Its Tetris-like strategy flexibly packs computation across the wafer, improving PE utilization and usable memory capacity while preserving PE-task code. We develop a recurrence-based throughput model that captures branch-and-join dependencies to guide spatial parallelism, and an architecture model with per-color gates that enable existing FPGA place-and-route algorithms to enforce WSE routing constraints. We evaluate WaferTetris on Cerebras WSE-3 using LLM decoding and scientific stencil benchmarks. For LLM decoding, it achieves up to $4.42\times$ the system throughput of a template-based automatic mapping baseline on the same fabric size. Compared with the manually optimized WaferLLM, WaferTetris supports $1.8\times$ the context length for LLaMA3.1-8B (80k versus 44k), while delivering equal or higher per-user throughput at matched context lengths, up to $1.10\times$.

cs.AR · cs.CL

新论文 · v1arXiv:2611.21959

OCCAM: Improved Single-Cell Representation Learning and Perturbation Effect Prediction

Ihab Bendidi, Kian Kenyon-Dean, Alisandra K. Denton, Auguste Genovesio, Emmanuel Noutahi

原文摘要

Predicting the effects of genetic perturbations requires models that generalize beyond observed cell contexts and gene combinations. We introduce Occam, a multilayer perceptron (MLP) framework for representation learning and perturbation-effect prediction. Occam combines cell representations learned through denoising with gene interaction, text, and protein-sequence features. It achieves the highest aggregate representation scores for perturbation information and cell-type preservation with batch integration. In cross-context few-shot prediction, a perturbation and a cell context are each observed during training, but never together. Occam better captures the measured response patterns for these unobserved combinations than four retrained competitors or direct transfer of the same perturbation's measured effects from other training cell lines. Without fine-tuning, Occam best distinguishes perturbations among the evaluated models and simple baselines in cell lines held out from predictor training, across seen and unseen assays. Predicting expression levels accurately in these settings remains challenging. For double perturbations, which target two genes simultaneously, Occam composes learned single-gene responses to better capture the combined response and reduce expression error compared with competing models and summed single-gene effects. These gains extend to both strongly additive and weakly additive responses. Together, these results support simple MLPs for cell representation learning and perturbation-effect prediction across contexts and gene combinations.

q-bio.QM · cs.AI · cs.LG

新论文 · v1arXiv:2611.21958

Weight-space programming for tractor guidance controller: large language models natively write neural network weights that steer a real tractor

Timo Oksanen

原文摘要

Weight-space programming is a process where a large language model reads and writes the weights of a neural network directly, guided by a natural language specification, without an optimiser or gradient descent. This study applies it to automatic tractor guidance, where a 253-parameter neural network steers along paths of lines and arcs and must be adapted when the machine changes, such as a slower steering actuator. GPT-6 Astra and Claude Fable 5.1 (also 5.2) edited the network for our research tractor using a small budget of simulated evaluations to repair a network trained for another tractor and write a controller into a network with zero weights. We compared them with an evolution strategy, gradient descent and pure pursuit in simulation and on the real tractor. Both models read the network and analysed the closed loop with control theory correctly, and Fable's repair without simulation succeeded only occasionally. With simulated feedback, both models repaired the trained network in single sessions and wrote a working controller from zero weights, whereas from zero the evolution strategy found none. The controllers written from zero were sparse and in a classical cascaded structure; one model edited the trained network while the other replaced it. Gradient descent reached higher accuracy with far more simulation, and all language model controllers steered the real tractor without intervention, with errors of the same order as pure pursuit. Language models can program the weights of a neural controller directly, much as control engineers design one. We call this Weight-Space Engineering.

cs.LG · cs.AI · cs.RO · eess.SY

新论文 · v1arXiv:2611.21957

Operating an Agent-Driven Dataset Factory: Discovery, Construction, and Public Release

Eduardo Ariño de la Rubia, Szilard Pafka

原文摘要

Turning public data into prediction datasets requires connecting source discovery, task definition, construction, and distribution. We deployed Dataset Factory to perform these steps continuously under a standing release policy. Bounded language-model tasks interpret sources, write construction code, and review task meaning; deterministic software manages state, workers, retries, and publication. Over 81.53 hours, the factory published 14 datasets at an estimated recurring operating expenditure of about \$2.74 per publication. The accounting includes failed attempts, inference, workers, and hosting. Separate agents completed prediction experiments on all twelve evaluated releases. Source review nevertheless identified a task whose construction filters contradicted its population declaration. The original reviewer accepted later-record exclusions without reconciling them with the published selection rule. This experience documents an operating source-to-release workflow and shows why successful execution and consumer use need separate checks of task meaning.

cs.SE · cs.MA

新论文 · v1arXiv:2611.23333

Classification of Forbidden 0-1 Patterns by Their Extremal Function

Jesse Geneson, Seth Pettie

原文摘要

This paper concerns the maximum weight of $n\times n$ 0-1 matrices that avoid some pattern $P$, denoted $\operatorname{ex}(n,P)$. Furedi and Hajnal initiated a research program of classifying all patterns according to their extremal function, but to date, only the weight-4 patterns are completely understood. In this paper we make progress on several fronts of the classification problem. A pattern is light if its columns have weight 1 and linear if $\operatorname{ex}(n,P)=O(n)$. We characterize the set of weight-5 linear light patterns, and the set of weight-5 linear patterns more generally. Along the way we identify several new infinite classes of linear patterns, which support the Pettie-Tardos conjecture on characterizing all linear light patterns. It was known that there exist infinitely many minimally nonlinear patterns. We identify a specific infinite set of minimally nonlinear patterns. We also prove that there are $2^{Ω(r)}$ weight-$r$ minimally nonlinear patterns, and that every minimally nonlinear pattern has extremal function $O(n\log n)$, with the exception of the 4-cycle. We classify many of the outstanding weight-5 patterns according to their extremal function, leaving only a small set remaining. The newly classified weight-5 patterns have extremal function $Θ(n)$ or $Θ(nα(n))$. We also exhibit a large number of weight-6 patterns with extremal function $Θ(n\log n/\log\log n)$, which is notable in that this function had not been encountered before for any single pattern $P$, though it was known to be the correct extremal function for a pair of forbidden patterns.

math.CO · cs.DM

版本更新 · v2arXiv:2604.01830

Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids

Pantelis Dogoulis, Maxime Cordy

原文摘要

Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system's physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post action overload risk of feasible topology actions. These predictions are used to construct a physics-informed Gibbs prior that both selects a small state-dependent candidate set and reweights policy logits before action selection. In this way, our method reduces exploration difficulty and online simulation cost while preserving the flexibility of a learned policy. We evaluate the approach in three realistic benchmark environments of increasing difficulty. Across all settings, the proposed method achieves a strong balance between control quality and computational efficiency: it matches oracle-level performance while being approximately $6\times$ faster on the first benchmark, reaches $94.6\%$ of oracle reward with roughly $200\times$ lower decision time on the second one, and on the most challenging benchmark improves over a PPO baseline by up to $255\%$ in reward and $284\%$ in survived steps while remaining about $2.5\times$ faster than a strong specialized engineering baseline. These results show that our method provides an effective mechanism for topology control in power grids.

cs.LG · eess.SY

新论文 · v1arXiv:2611.21952

A Log-Timescale Perturbation Bound for Selective State Space Models at Every Sequence Length

Jack Humphries, Daniel Midgley

原文摘要

Mamba models deployed on streaming data, such as limit order book updates, run far past the sequence lengths they were trained on. A guarantee on how much a small change of input can move the hidden state therefore has to hold at every length. The closest existing bound we know of measures the change of the timescale additively, and it grows linearly with the sequence length unless the timescale is bounded away from zero. In this paper, we measure the change on a log scale instead. The key observation is that the decay factor of each step then moves by at most a fixed fraction of that step's input weight, so the per-step errors cannot pile up. Using this, we prove that two runs of a selective-scan cell from a common start stay within a bound that holds at every length, shrinks to zero with the size of the change and needs no lower bound on the timescale. We give a construction showing that, for small changes, this bound is within a factor of about 2 of the best possible, and we extend it to the update used in Mamba's released code when the timescale is bounded above. We then evaluate block-level bounds built from the theorem on two small models trained on one day of order book data. With a bounded timescale, a bound built on the existing analysis is tighter than ours for at most the first 8 steps. With Mamba's softplus timescale, whose certified lower bound is as small as $10^{-21}$, it is looser at every length. Our bounds hold for every input to a block, but they remain more than five orders of magnitude above the changes that gradient attacks find.

cs.LG

新论文 · v1arXiv:2611.21951

PersonaHate: A Scalable Persona-Based Data Synthesis Pipeline for Hate Speech Analysis

Xinyu Zhang, Ziqing Yang, Michael Backes, Yang Zhang

原文摘要

Hate speech remains a persistent and evolving threat on online platforms. The widespread use of large language models (LLMs) further intensifies this problem by making hateful content easier and cheaper to generate at scale. Although stronger hate speech detectors continue to be proposed, their performance remains uneven across target identity groups and different forms of hateful expression, partly because existing training data provides only limited coverage of these cases. Thus, we introduce PersonaHate, a scalable persona-driven data synthesis pipeline for constructing diverse hate speech datasets. PersonaHate begins with a large persona pool of 457K personas drawn from two real-world sources. Conditioned on selected personas from this pool, it prompts eight LLMs to generate hate speech across 34 identity groups and performs multi-judge annotation to obtain reliable labels. The resulting corpus contains 791K samples, from which we curate a 67K group-balanced training set. Our modular design also supports extension to new identity groups, generators, and emerging hate targets. Built upon this dataset, we evaluate two detector training strategies: training from scratch and further fine-tuning. Results show that all trained models achieve competitive performance across four widely used external benchmarks. Notably, a 184M-parameter DeBERTa-v3 model trained on PersonaHate reaches 77.5% average F1 and 79.4% average accuracy, outperforming OpenAI's Moderation API on HateBenchSet and MHS. Furthermore, fine-tuning Llama-3.1-8B raises its average F1 from 70.7% to 78.4%, a gain of 7.7 percentage points, surpassing LlamaGuard-3, Meta's official safety model based on the same Llama-3.1-8B architecture, on three of four benchmarks. These results show that PersonaHate can substantially improve the robustness and cross-dataset generalization of hate speech detectors.

cs.CR

新论文 · v1arXiv:2611.21950

DiscoveryAgent: A Framework for Scientist-centric Agentic AI

Owen Queen, Ioana Ciuca, Emma Dann, Jean Somalwar, Carine You, Steven Dillmann, Viraj Manwadkar, Evan Gorrell 等 12 位作者

原文摘要

AI agents can assist scientific research, but balancing autonomous investigation with scientists' ability to inspect and redirect ongoing work remains a central design challenge. We present DiscoveryAgent, a domain-agnostic, scientist-centric system that combines autonomous investigation with scientist-directed hypothesis steering. Scientists select, refine, or replace hypotheses between research rounds, while audit agents interrogate checkpointed records to trace claims, reproduce analyses, and inform subsequent decisions. Across two predictive modeling tasks, DiscoveryAgent produced the best variable-star classifier among evaluated baselines and, with scientist steering, a protein variant-effect predictor surpassed by only one of 106 ProteinGym baselines. We develop a rigorous checkpointing system that enables highly capable audit agents, a scalable form of oversight for agentic research. Audit agents autonomously identify errors at higher rates than previous AI scientist agents, and scientists collaborating with audit agents identify 14x more valid errors versus scientists performing manual review. In three case studies led by domain experts across physical science, social science, and life science, we developed a multimodal photometric-redshift estimator that resolves complementary failures of images and photometry, achieving 0.971 AUROC for low-redshift classification; documented an 83% rise in Florida homeowners-insurance premiums from 2013 to 2023, with a growing, regressive burden; and identified CD4+ T-cell relay genes, which both receive and exert broad transcriptional regulation, enriched for autoimmune disease associations. Together, these results show how autonomous research can expand scientists' empirical reach while centering their authority over research direction and their ability to understand and challenge the evidence.

cs.AI

版本更新 · v2arXiv:2608.11475

Probing and steering biology across Boltz-1s trunk-diffusion boundary

Piotr Jedryszek, Tongmeng Xie, Adam Winnifrith, Alexander Hasson, Weronika Ślesak, George Wicks, Toby Winnifrith, Oliver M. Crook

原文摘要

AlphaFold3-class structure predictors pair a representational trunk, which processes sequence and context, with a diffusion module, which generates atomic coordinates. How biological information changes as it crosses this architectural boundary remains poorly understood. We analyze per-residue activations from the Pairformer trunk and diffusion module of Boltz-1 using linear probes, sparse autoencoders (SAEs), and causal interventions. From the trunk, both geometry (secondary structure, disorder) and sequence chemistry (amino-acid identity, signal peptides, disulfide-bond annotations) are linearly decodable. In the diffusion module, the two diverge. Secondary structure remains equally decodable, whereas sequence chemistry becomes much less linearly accessible. We then test whether decodable directions can steer the model by editing the trunk's single representation. Helix and coil directions change predicted structure dose-dependently, but a beta-strand direction that is highly predictive on the same proteins (held-out F1 =0.78) produces no measurable increase in strand content at any of the steered layers. Removing helix or coil directions does not remove that structure. Linear decodability therefore did not imply causal influence at the sites we tested. The same probes also score markedly lower against SwissProt annotations than against DSSP labels, because unannotated residues that the model gets right are charged as false positives; such scores are therefore lower bounds. Finally, supervised probes outscore single SAE features wherever a label already exists.

q-bio.QM · cs.LG

版本更新 · v2arXiv:2610.34156

ASR-Protected Fusion and Reference-Anchored Policy Optimization for Joint ASR and Word-Level Speech Anti-Spoofing

Xueping Zhang, Xiaoxiao Miao, Tiantian Feng, Ming Li

原文摘要

Existing anti-spoofing systems report either an utterance-level score or a time-based spoof interval: the former cannot show which words are spoofed, while the latter does not directly match the transcript and must be post-aligned with words, so alignment errors can lead to wrong word-level labels. Standard ASR model outputs only text; spoof information in the audio is lost after recognition and is not passed with the transcript. Yet changing only a few words can change the meaning of a sentence, leaving downstream systems to use incorrect text without knowing which words are spoofed. We therefore treat partial anti-spoofing as tagged ASR: the model transcribes speech and marks spoofed words at the same time, directly linking spoof labels to output words. We adopt the audio LLM and use ASR-Protected Subspace Gated Fusion (APSGF) to fuse spoof cues with ASR features. Spoof cues are added only outside an ASR-protected subspace, so they do not disturb recognition features. After cross-entropy training, we fine-tune the model with Reference-Anchored Policy Optimization (RAPO). Since the SFT policy is already concentrated, multiple samples from the same input tend to receive similar rewards, resulting in weak group-wise advantages. RAPO instead generates a single sample with low sampling randomness and anchors its advantage to the reward of a reference model. This allows the model to reinforce responses that outperform the reference while suppressing those that underperform it. Experiments on five datasets demonstrate the effectiveness of our approach in jointly detecting spoofed words and preserving ASR accuracy. The code is publicly available.

cs.SD

新论文 · v1arXiv:2611.21946

Conserved Verdicts, Drifting Commitments: Identifying Harmful Overthinking

Jianghong Zhou, Hao Rong, Chen Lin

原文摘要

A reasoning model that has reached a correct answer can lose it by continuing to think. Deciding whether to stop means comparing two probabilities at the same point of a chain: that the answer the model would give if stopped now is correct (its commitment), and that the answer it will finish with is correct (its verdict). We show that the verdict alone, which is what final-correctness probes estimate, cannot make this comparison. As a forecast of a fixed outcome it has no predictable drift, whether continuing helps or hurts. The commitment-verdict gap equals the expected remaining change in answer quality and the accuracy gained by stopping. A second identity splits any accuracy-versus-budget curve into answer change within chains and change in which chains are still running. We measure both on MATH-500. At all 379 points where DeepSeek-R1-Distill-Qwen-1.5B holds a correct answer, selected without regard to how its chain ends, continuing loses 3.6 points on average (95% CI [2.2, 5.2]), and the loss concentrates in a few problems. In six reasoning models from three families, on MATH-500 and OlympiadBench and with budgets up to 16,384 tokens, declining accuracy curves come from which chains remain, while the chains still reasoning keep or improve their answers. An oracle stopping rule gains at most +1.8 and +2.5 points at 1.5B and 7B. The framework says what to measure before building a stopping rule.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.21943

Beyond 4: Improved Competitive Traveling Repairperson

Bibek Maharjan, Gokarna Sharma

原文摘要

With $k\geq 1$ repairpersons starting initially from a depot, we present a 3.877-competitive deterministic algorithm for the fundamental online traveling repairperson problem on an arbitrary metric. For the special class of zero-residual instances, we improve the ratio to $3+ε$ for every $ε>0$. We also extend these results to some variants of the related so-called online dial-a-ride problem. The state-of-the-art is the 4-competitive deterministic algorithm for both problems.

cs.DS · cs.DM · cs.MA

版本更新 · v4arXiv:2602.16736

The Compute ICE-AGE: OPAL ONE, Continuity That Persists While Reasoning Is Idle

R. Jay Martin

原文摘要

The Compute ICE-AGE separates persistent application memory from probabilistic reasoning. We present OPAL, a CPU-resident C++17 graph engine that preserves record identities, relationships, and accepted numerical state between reasoning sessions. Applications evolve that state through defined updates, save canonical checkpoints, and recover continuity after restart. Bounded Local Generator Classes (BLGC) provide the mathematical foundation for this bounded local evolution. On Apple Silicon M2 Pro hardware, the current-engine resident-update P50 measured 0.083 microseconds at 100,000, 1,000,000, and 5,000,000 retained Atomic Memory Vertices (AMVs). A same-session 1M-5M-1M sequence reproduced that median using one frozen binary and 1,024 prepared targets, with every process passing its correctness checks. These measurements cover complete resident-update calls, including validation, indexed lookup, and numerical state mutation. Initialization and storage-growth costs are reported separately. Reliability tests verified event replay, conflict rejection, concurrent calls, allocation-failure handling, and fresh-process recovery with continued operation. Engine-version comparisons produced byte-identical checkpoints and continuation files. The installed PYAMV Python package passed 17 SDK contract checks and 20 workload checks. KINDRED's Model Context Protocol interface passed 22 distinct focused checks covering memory operations, authorization, and transport. Together, these results demonstrate persistent continuity with low recurring local-update costs through five million retained AMVs, providing working interfaces for applications and developers. The architecture keeps accepted memory available while reasoning is idle, allowing applications to invoke models only when tasks require interpretation, planning, or generation.

cs.OS · cs.AI

新论文 · v1arXiv:2611.21941

Complexity and precision in quantum associative retrieval

Carlo A. Trugenberger

原文摘要

We show that efficient and high-precision quantum associative retrieval is possible with an exponential complexity advantage with respect to the classical brute force approach and with a polynomial capacity advantage with respect to classical neural network implementations for any number of patterns scaling polynomially in the number of qubits. Both classical neural and quantum associative memories store the patterns in a Hamiltonian; in the classical case the dynamics is irreversible relaxation toward attractors, in the quantum case it is unitary transformations generating an effective thermal distribution, followed by a measurement.

quant-ph · cs.CC · cs.IR · cs.NE

版本更新 · v2arXiv:2605.25267

Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning

Minjae Kwon, Amir Moeini, Shangtong Zhang, Lu Feng

原文摘要

Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level check against predicted future cost. We propose a latent Q-Barrier shield that learns a context representation, latent dynamics, and an ensemble cost critic before deployment. Without parameter updates, the shield infers context from history and filters or softly reweights candidate actions using the remaining budget and predicted future cost. We prove a conditional one-step barrier-margin bound over realized candidate sets, with explicit Bellman and latent-prediction error terms. Across five safe ICRL benchmarks, the shield improves deployment-time reward-safety tradeoffs over a strong safe-ICRL baseline: after a short context window, it achieves higher return in four of five benchmarks while matching or lowering average episode cost in all five. Code is available at https://github.com/kmj1122/q-barrier.

cs.LG · cs.AI

新论文 · v1arXiv:2611.21938

HubEgo-100K: In-the-Wild Egocentric Video of Skilled Work for Robot Learning

Javad Amirian, Armin Kiani, Loïc Schaeffer, Tim Sprecher, Mohamed Taha, Karthik Yadati

原文摘要

Robot policies trained by imitation generalize poorly outside the environments and objects seen in training. Published data-scaling studies find that generalization grows with the diversity of training environments and objects rather than with more demonstrations per environment. Robot data is costly to collect across many environments, whereas egocentric human video can be recorded in the wild at scale; existing egocentric video, however, mostly shows daily-life activity and contains little skilled work in real workplaces. We present HubEgo-100K, a dataset built for diversity. This version of the paper covers the first release, v1.0: 10,124 hours of 1080p egocentric video with synchronized 100 Hz inertial (IMU) data from one head-mounted phone camera. In v1.0, 12,227 contributors record their own unscripted work in 15,548 environments (each one contributor's own setting of one type, such as their kitchen or workshop) across 11 setting types, 30 work categories, 56 task types and 35 action families, with 83% of hours in workplace settings. The release comprises 72,754 episodes with machine-generated action and language annotations, in LeRobot and MCAP formats under CC BY 4.0. We measure diversity along each axis, show that inside v1.0, with episodes in random order, new contributors and words keep appearing, and relate the measurements to published evidence on six data properties tied to policy performance, including hand visibility and inertial sensing. We also document collection, curation, privacy measures and data format, and provide a datasheet. Later versions of this paper will add benchmarks and cover further releases toward 100,000 hours.

cs.RO · cs.CV · cs.LG

版本更新 · v2arXiv:2611.16066

Optimal Additive Integer Masks for One-Guess Vulnerability under an Absolute-Moment Budget

Joonas Pääkkönen

原文摘要

We study the average one-guess success probability of an adversary who observes the ordinary integer sum of a finite-support secret and an independent integer-valued mask, subject to an absolute-moment budget on the mask. For a uniform secret on an interval the exact optimum and an explicit optimiser are obtained. For a biased bit the masks that achieve no increase over the prior baseline are characterised, and the entire cost--vulnerability frontier is determined. It is the piecewise-linear interpolation of an explicit sequence of points generated by cost-optimally shifted truncated geometric masks. It has infinitely many affine pieces, which accumulate at the critical cost, where the frontier meets the prior baseline with zero slope. The proof rests on a layer-cake decomposition of an arbitrary mask into truncated geometrics, along which both the vulnerability and the cost are exactly additive. The results give exact design guidance for additive integer noise under the average one-guess metric.

cs.IT · cs.CR

版本更新 · v4arXiv:2610.37690

Cassette-Editor: Shared Timeline Semantics for Human and Agent Editing

Zhixin Zeng, Jiahao Zhong

原文摘要

Video editing involves tedious manual manipulation across interconnected timeline tracks, motivating automated agents that offload routine work while keeping the project directly revisable by humans. Fixed operation catalogs limit expressiveness, while even a basic trim requires coordinated updates across later clips, attached titles, and transitions. We present Cassette-Editor, an agent harness that unifies manual user gestures and automated agent patches within a shared editing environment. The shared action language expresses the editor's manual content changes, and a common history records committed edits for undo and manual refinement. When the model selects an edit, a state executor automatically derives its downstream consequences, such as shifting later clips and attached titles after a trim, while a validation rulebook enforces structural invariants and returns localized diagnostics for automated repair. To keep the agent grounded as the project evolves, dynamic read operations map transcripts and shot descriptions onto the current timeline. Evaluated with GPT-6 Luna, the full harness passed the scored request checks in 92/93 trials across 31 authored requests on two interview documentaries, compared with 48/93 for an internal basic-tools baseline. In ablations, disabling the consequences derived by the executor reduced passed trials from 230/232 to 199/232 on edits with dependent timeline elements, while ablating rulebook validation and repair lowered passed trials from 46/48 to 10/48 on requests operating near structural validity boundaries. Evaluating the complete system on 50 TVSum videos further demonstrated greater agreement with human annotations than a general agent using the same model (F1 23.8 vs. 20.1).

cs.MM · cs.AI

新论文 · v1arXiv:2611.21937

SLED: Sensor SLicing from Edge to Datacenter

Alan Subedi, Avhishek Biswas, Apala Pramanik, Amlan Balabantaray, Mikhail Titov, Santosh Pitla, Ozgur Kilic, Mehmet C. Vuran

原文摘要

Modern sensing systems generate large volumes of heterogeneous data streams from multiple sensor modalities, increasing reliance on datacenters for computation, artificial intelligence/superintelligence (AI/SI) inference, and AI/SI training. Each sensor stream may have different network and compute requirements depending on its type and data volume. However, current wireless systems typically allocate resources at the device level, leading to contention among co-located sensor streams, where bulk data transfers may starve latency-critical telemetry. To this end, this paper introduces Sensor Slicing (SL). SL provides deterministic, medium access control (MAC)-level isolation for individual sensors within a single user equipment (UE) in open radio access networks (O-RAN). Using agentic coding techniques, SL is implemented in two O-RAN-compliant packages, reducing development time by 400 times (2 h 40 min [OCUDU] vs. 6.5 weeks [OAI]), 228-fold fewer human prompts (4 vs. 913), and less than half the tokens (0.64B vs. 1.43B). An associated end-to-end framework, SLED, is implemented to establish per-sensor radio and network isolation across edge, campus, and remote high-performance computing (HPC) tiers. Over-the-air wireless experiments demonstrate that while conventional network slicing causes critical delays to increase more than 2,300-fold under high traffic load, SLED maintains stable latency. Scaling evaluations on the two RAN stacks show that throughput remains within 0.9% and 1.4% of expected allocations even as the number of sensor slices increases. The results demonstrate that SLED preserves latency-critical telemetry while effectively utilizing resources across the sensor-to-HPC pipeline. The SLED software and evaluation datasets are publicly available at https://github.com/UNL-CPN-Lab/SLED-Sensor-SLicing-from-Edge-to-Datacenter.

cs.AI · cs.CE · cs.DC · cs.ET · cs.NI

新论文 · v1arXiv:2611.21936

CNN Architecture Comparison for Malware Classification with Limited Training Data

Noor Abo Hasan

原文摘要

Traditional malware classification methods struggle to keep pace with rapidly evolving threats. Image-based malware classification offers a promising alternative by converting malware binaries into grayscale images for analysis with deep learning. While effective, organizations often face practical constraints in acquiring sufficient training data, especially for newer threats. This thesis investigates dual-path CNN architectures with intermediate feature fusion as a potential enhancement for malware classification, with particular focus on how varying training data size affects their comparative performance against traditional single-path approaches. This research implements and compares two models: a baseline single-path using the pre-trained VGG16 architecture and a dual-path model that combines VGG16 with a custom CNN through intermediate feature fusion. Both architectures are evaluated on a binary classification task distinguishing between two malware families (C2Lop.P trojan and Dialplatform.B worm) from the Malimg dataset. Each model is trained across four different training data proportions (20%, 40%, 60%, and 80%), with three training runs per size to ensure statistical robustness, while being evaluated on complementary test sets of varying sizes. Though both architectures achieved perfect classification performance across all training percentages, the study revealed significant differences in secondary metrics including training efficiency, robustness to noise perturbation, and architectural complexity. The findings challenge common assumptions about complex architectures, demonstrating that simpler models can offer superior efficiency and robustness without sacrificing classification performance in image-based malware analysis.

cs.CR

新论文 · v1arXiv:2611.21935

Higher-Order Interaction Reconstruction via Integral Physics-Informed Neural Networks

Xin Mao, Zhen Xu, Shiyi Yang, Sukwon Yun, Yunmei Liu, Ren Wang, Tianlong Chen, Can Chen

原文摘要

Reconstructing higher-order interactions is a fundamental challenge in complex networked systems, with applications in ecological, social, and biological networks. This inverse problem is inherently difficult due to the combinatorial complexity of higher-order structures, the strong nonlinearity of the underlying dynamics, and the prevalence of noisy and sparse observations. In this article, we propose a novel integral physics-informed neural network (IntegralPINN) framework for higher-order interaction reconstruction. Instead of { penalizing derivative-based physics residuals,} we adopt an integral formulation over temporal intervals, which naturally suppresses high-frequency noise and mitigates derivative-induced instability. We further introduce a continuous parameterization of interaction tensors, enabling tractable identification of higher-order structures via gradient-based optimization. We provide theoretical analysis establishing a noise-robust error bound that is independent of derivative amplification when the integration window satisfies an excitation condition. Extensive experiments on ecological dynamics, social contagion, and neuronal synchronization systems demonstrate that IntegralPINN achieves accurate and robust reconstruction under noisy and sparse observations, outperforming state-of-the-art approaches.

cs.LG · eess.SY

版本更新 · v3arXiv:2609.34183

CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation

Joshua Li, Yuri Boykov

原文摘要

Weakly Supervised Semantic Segmentation (WSSS) learns pixel-level predictions from image-level tags. Recent work focuses on improving coarse CAMs extracted from large vision-language models (commonly CLIP), but does little to improve their accuracy along segment boundaries. That job is instead delegated to a post-processing method like DenseCRF. However, because DenseCRF relies on low-level colour cues, it can flip correct labels to incorrect ones when neighbouring pixels share similar colours. SAM has recently been adopted as a natural alternative, yet it simply takes on DenseCRF's role as an intermediate "refinement" step that outputs one-hot pseudo-labels in prior work. By discarding the valuable uncertainty in CAMs, these one-hot pseudo-labels turn borderline errors into confidently wrong targets. Our key insight is that CAMs should supervise training alongside SAM boundaries, each through its own loss, rather than being fused together into a single hard target. Inspired by CRF potentials, we propose a framework that disentangles soft pseudo-labels as unary supervision and binary edge maps as pairwise supervision. We realize our framework in a single-stage model, DS-CRF, using CAMs from dino.txt and boundaries from SAM. DS-CRF sets a new state-of-the-art of 56.5% mIoU on MS COCO among single-stage methods.

cs.CV

新论文 · v1arXiv:2611.21933

Physics-informed neural networks for spacecraft trajectory optimization with exact boundary conditions

Samuel Schönherr, Günther Waxenegger-Wilfing, Sascha Ranftl

原文摘要

We use neural networks to optimize trajectories by modeling the position as a function of time and minimizing the thrust with respect to the network parameters. This corresponds to an unsupervised training procedure in which physical laws are incorporated directly into the optimization objective. In standard physics-informed neural networks, initial and terminal states are enforced through additional weighted loss terms, resulting in a multi-objective optimization problem that is highly sensitive to the choice of loss weights and can lead to poor convergence and reduced accuracy. To address this challenge, we construct a simple transformation, exploiting the mathematical structure of trajectory optimization problems, to enforce boundary conditions exactly a-priori. This transformation can be interpreted as a reparameterization of the solution space that embeds the boundary conditions directly into the function. This converts the original constrained optimization problem into an unconstrained one over admissible trajectories. I.e. the transformation eliminates the boundary condition penalty terms and reduces the problem to a single-objective optimization. Crucially, trajectory optimization comes with a low-dimensional boundary, which allows particularly simple and stable constructions of distance functions compared to general domains in partial differential equations. Numerical experiments demonstrate that the proposed approach meaningfully improves convergence behavior and solution accuracy.

cs.LG

新论文 · v1arXiv:2611.21927

Polylogarithmic Regret via Certainty Equivalence in Degenerate LQR

Luca Vignola, Melanie Zeilinger, Bruce D. Lee

原文摘要

Singular input penalties, as in minimum variance control, can reduce what must be identified to control an unknown linear system. In online linear quadratic control, certainty equivalence can achieve polylogarithmic regret when the optimal controller is identifiable from data collected under optimal feedback. With a positive definite input penalty, however, this condition is restrictive, since for an invertible state matrix it requires all unknown parameters to be identifiable under optimal feedback. We show that singular input penalties relax this requirement, expanding the class of problems in which certainty equivalence achieves polylogarithmic regret. Specifically, we prove that a certainty-equivalence algorithm with a short initial exploration phase achieves $O(\log^2 T)$ expected regret over $T$ interactions whenever controller identifiability holds. We complement this guarantee with an $Ω(\sqrt{T})$ minimax lower bound for a family containing a system where controller identifiability fails. For minimum variance control, knowing the range of the input matrix suffices for controller identifiability, a weaker requirement than knowing the full input matrix, as assumed in prior work with positive definite input penalties. This condition also covers underactuated systems, as we illustrate with a cart-pole example.

math.OC · cs.LG · eess.SY

版本更新 · v2arXiv:2611.02380

Malware Clustering in the Wild: Taxonomy, Challenges, and Evaluation Metrics

Raguvir S, Bojing Li, Prajna Bhandary, Charles Nicholas

原文摘要

As malware continues to grow in volume, diversity, and sophistication, clustering has emerged as a critical technique for analyzing large malware corpora. Clustering enables the discovery of structural relationships, behavioral patterns, and evolutionary trends, and is widely used to group unknown samples, infer malware family boundaries, and identify novel variants. However, existing research remains fragmented, employing a wide range of clustering techniques with no unified perspective that systematically organizes prior work or clearly identifies gaps in the literature. This survey addresses this gap by organizing previous malware clustering research into seven categories: centroid-based, hierarchical-based, density-based, distribution-based, mixed- type, fuzzy, and AI-driven approaches. In addition, this survey summarizes publicly available malware datasets commonly used in clustering research and examines the feature representations derived from these datasets. Our goal is to clarify the current landscape and outline promising avenues for future research on malware clustering, including how AI-driven methods may shape large-scale and reproducible analysis.

cs.CR · cs.AI

版本更新 · v3arXiv:2603.27101

PRUE: A Practical Recipe for Field Boundary Segmentation at Scale

Gedeon Muhawenayo, Caleb Robinson, Subash Khanal, Zhanpei Fang, Isaac Corley, Alexander Wollam, Tianyi Gao, Leonard Strnad 等 13 位作者

原文摘要

Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illumination, spatial scale, and changes in geographic location. We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation using the Fields of The World (FTW) benchmark. We evaluate 18 models under unified experimental settings, showing that a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics. We propose a new segmentation approach that combines a U-Net backbone, composite loss functions, and targeted data augmentations to enhance performance and robustness under real-world conditions. Our model achieves a 76% IoU and 47% object-F1 on FTW, an increase of 6% and 9% over the previous baseline. Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference. We release all models and model-derived field boundary datasets for five countries.

cs.CV · cs.LG

新论文 · v1arXiv:2611.21924

GridDriver: On-Board BEV-Based Language Planning and Reasoning

Katharina Winter, William Engel, Zain A. Alishammat, Fabian B. Flohr

原文摘要

Bird's-Eye-View (BEV)-conditioned large language models (LLMs) enable language-interactive driving, but onboard deployment requires efficient perception and continuous planning alongside autoregressive language generation. We present GridDriver, an efficient BEV-conditioned LLM framework combining trajectory prediction, structured driving indicators, natural-language navigation, driving explanations, and scene question answering. Lightweight spatio-temporal BEV perception and spatially structured tokens provide scene context to a shared LLM, while frame-wise scheduling interleaves trajectory prediction with asynchronous language generation. GridDriver achieves competitive performance on public benchmarks, reaching 87.9% PDMS on NAVSIM and 57.6% accuracy on nuScenes-QA with a shared planning and QA checkpoint. Spatial representation analyses demonstrate improved geometric information retention and trajectory prediction compared with Q-Former compression. The system achieves 32.7 ms standalone planning latency and 9.4 plans/s in an onboard ROS 2 pipeline. We further evaluate planning on our own data recordings and demonstrate open-loop onboard operation on a research vehicle. Across public benchmarks and real-world evaluations, we identify strengths and limitations of the BEV-based approach.

cs.CV

新论文 · v1arXiv:2611.21923

Wrong Input, Wrong Threshold: Re-evaluating Adversarial Facial Privacy

Tunahan Parlayıcı, Erchan Aptoula, Yücel Saygın

原文摘要

Published face-privacy methods report protection above 90% against black-box recognition models. That number comes from an evaluation protocol with two independent defects, reported in a measure that cannot size either one. The input is wrong: methods published since 2022 feed the network the whole photograph, or a detector's box, where deployed systems detect, align to a landmark template and crop. Re-scoring the same files through a realistic front end costs a standard transfer attack 56% of its dodging protection and a budget-allocating attack 7%, with no image regenerated. The measure is wrong: that loss is a difference of success rates, so it saturates, moving by 8.2x over a budget sweep while the effect beneath it moves by 1.34x. We therefore report the paired cosine shift, in which both thresholds cancel algebraically, so the input defect holds without committing to a calibration. Measured that way it is 2.2x and 10.7x larger on three unseen recognizers, and at matched budget it reverses the L-infinity transfer ranking: the one surveyed method that aligns at evaluation gains 0.18 where MI-FGSM loses 0.05. The cause is a resampling mismatch, not perturbation lost outside the crop; optimising through a differentiable alignment operator largely removes it, adding +24 to +58 points on unseen recognizers and a commercial system, with a residual on one of them. The thresholds are wrong: the four constants inherited since 2021 hold the false-accept rate near its nominal 1% on aligned crops but admit 2.3-5.4% on whole images, with an opposite-signed bias across dodging and impersonation, the two tasks reported side by side. Differentiable alignment and gallery scoring are not new: the first generation of this literature used both, and we show what dropping them cost.

cs.CV · cs.CR · cs.LG

新论文 · v1arXiv:2611.21922

A Forensic Analysis of Metadata and Information Leakage in Swedish Public Documents

Noor Abo Hasan, Kajsa Linderoth, Monia Lönn

原文摘要

This study investigates metadata and structural content leakage in publicly available PDF documents from 30 Swedish public-sector authorities. Using an automated collection pipeline and ExifTool-based extraction, 2,876 documents were analyzed and classified using an R0-R3 risk taxonomy. Results reveal that 48.4% of documents exhibit significant metadata exposure (R2 or R3), with significant variation across institutional tiers (p < 0.001). Longitudinal analysis across three legislative periods reveals a statistically significant reduction in metadata exposure between the baseline and post-enactment periods, yet 44.9% of documents published after the enactment of the Swedish Cybersäkerhetslagen continue to leak sensitive metadata. Furthermore, 41.6% of documents contain incremental update layers; forensic analysis recovered verifiable text alterations, including deleted personal data and internal identifiers, from 228 of these cases. These findings highlight persistent regulatory lag and a systemic reliance on default, unsanitized document publication workflows within the Swedish public sector.

cs.CR