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

+1959新增论文
+1550其中 AI 相关
+212已有论文修订
+89新增 AI 导读

arXiv 最近完成扫描:2026-11-17 23:20 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 00:09 — 2026-11-18 00:09(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:2026-11-17 23:20最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 17,069 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 23:19(北京时间)
新论文 · v1arXiv:2611.21608

潜在格语言模型

Latent Lattice Language Models

Shivam Duggal, Zongze Wu, William T. Freeman, Antonio Torralba, Richard Zhang, Eli Shechtman

AI 速读 基于摘要

作者提出在Transformer每层增加沿时间循环的横向潜在流(Lattice of Latents),以增加活跃计算状态而非深度或循环层数,在20B FineWeb-Edu token上降低验证困惑度。

cs.LG · cs.AI · cs.CL

查看原文摘要

Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the number of active computational states a model maintains. We introduce the Lattice of Latents, a set of per-layer horizontal latent streams that run recurrently along time, alongside the vertical residual stream that flows through depth. Like hyper-connections, mHC, and attention or value residuals, the Lattice enhances the residual stream, but rather than adding or rerouting residual pathways through depth, it provides companion computational states that persist across tokens. Unlike hybrid Transformer-SSM architectures, whose recurrent states primarily serve as internal memory for sequence mixing, these latents directly condition the vertical stream's attention, KV-cache writes, MLP computation, and decoding. On Transformers trained on 20B FineWeb-Edu tokens, a 406M-parameter Lattice model lowers validation perplexity from 15.41 to 14.40 over a parameter-matched Transformer. These gains extend across architectural variants. The Lattice composes with prior residual-stream enhancements: with hyper-connections and input residuals, it lowers validation perplexity from 15.41 (base Transformer) and 14.22 (Transformer with the same enhancements) to 13.61. On Gated DeltaNet, Mamba-2, Triadic GDN, and GDN-Mamba-2 hybrids, it improves perplexity at every tested native state size, with Lattice-GDN and Lattice-Triadic-GDN variants outperforming pure baselines with 4x larger native states. These results identify persistent per-layer state as a complementary axis for scaling language-model computation.

版本更新 · v3arXiv:2605.18476

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

Jungang Zou, Alex Ziyu Jiang, Qixuan Chen

原文摘要

Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become increasingly complex and existing probabilistic programming systems remain limited in model support, extensibility, and composability. We introduce AI4BayesCode, an extensible LLM-driven system that translates natural-language Bayesian model descriptions into runnable, validated MCMC samplers. To improve reliability, AI4BayesCode adopts a modular design that decomposes models into modular sampling blocks and maps each block to a built-in sampling component, reducing the need to implement complex sampling algorithms from scratch. Reliability is further improved through pre-generation validation of model specifications and post-generation validation of generated sampler code. AI4BayesCode also introduces a novel recursively stateful coding paradigm for MCMC, allowing modular sampling components, potentially developed by different contributors, to be composed coherently within larger MCMC procedures. We develop a benchmark suite to evaluate AI4BayesCode for sampler-generation. Experiments show that AI4BayesCode can implement a wide range of Bayesian models from natural-language descriptions alone. As an open-ended system, its capability can continue to expand with improvements in the underlying AI agent and the addition of new built-in blocks. The software is available at https://ai4bayescode.com/.

stat.CO · cs.AI · cs.LG

新论文 · v1arXiv:2611.21605

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization

Huawei Lin, Jinting Liu, Tongyan Wang, Xuyang Chen, Ruihua Shi, Zhichao Xu, Jiaxin Qin, Guoshenghui Zhao 等 12 位作者

原文摘要

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answer cannot correct this, because a guess earns the same reward as reading. We propose Cross-Input Relative Policy Optimization (CrossRPO), which trains agents on contrast sets. A contrast set asks one question about several versions of an image that differ only in a small region with the evidence and have different answers, so only reading the evidence solves the whole set. CrossRPO rewards solving the whole set, and we prove that it does not reinforce a set answered from common sense. We build contrast sets for training (ViRA-Train) and evaluation (ViRA-Bench) by editing one small object in images of 21 to 120 megapixels, and we photograph further sets with real changes (ViRA-Bench-Real) to exclude editing traces. We train two Visual Reasoning Agents, ViRA-9B and ViRA-27B, with CrossRPO on only about 3,500 items of ViRA-Train each. CrossRPO achieves 63.3% set accuracy on ViRA-Bench at the maximum resolution, against 59.3% for GRPO. ViRA-9B is the most accurate open model of its size on all benchmarks, and ViRA-27B outperforms Claude Haiku 5.5 and GPT-6-Luna, both at their highest thinking level, on most benchmarks.

cs.CV · cs.AI

新论文 · v1arXiv:2611.21600

视觉语言模型如何规划下一步

How VLMs Plan What's Next

Rohit Gandikota, Arnab Sen Sharma, Adam Belfki, David Bau

AI 速读 基于摘要

作者通过因果修补在 Qwen3-VL 中刻画了 VLM 在描述图像时决定“先看哪里、再看哪里”的四部分机制。

cs.CV · cs.CL · cs.LG

查看原文摘要

When a vision-language model describes an image, it names one object at a time and it rarely repeats itself, yet how the model plans this order is far from obvious. We characterize the mechanism a VLM uses to decide where to look before it looks. The mechanism has four main parts. First, binding heads match the relevant text tokens against the image and resolve them into pointers to the matched image region. Second, the same binding heads bind each written answer to the region it came from, and the model turns it into a progress signal: a cursor, the position in the image up to which the list has been written. Third, a select step chooses the nearest unwritten region after the cursor, or stops. Finally, gaze heads execute the chosen pointer and return a concept of what is drawn there, which language heads and the late MLPs turn into a word in the language of the question. We validate each part of this mechanism through causal patching in Qwen3-VL models on a synthetic visual retrieval task, and test our mechanisms against alternative hypotheses. We further show that the mechanism holds across input formats, natural photographs, and languages, and that its binding, relay, and gaze heads appear at every model size from 2B to 32B. This work allows us to investigate how a VLM turns a question and an image into a sequence of answers, layer by layer and token by token. More broadly, it opens a way to study how models plan over complex multi-step tasks with long rollouts. Our project is available at https://plan.baulab.info/

新论文 · v1arXiv:2611.21598

Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent

Blas Eugenio Vicco Zarate, Miguel Hernán Vicco

原文摘要

Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable memory when combined with environment detection and failure-driven search. The Evolutionary Neuroplastic Agent (ENA) evolves small neural networks without gradients, archives selected policies by detected dynamic regime, and retrieves them through Bayesian policy reuse. The architecture was evaluated in non-stationary CartPole and HalfCheetah environments. In the 30-replicate CartPole ablation, the complete architecture achieved a mean success rate of 83.2% across the five test environments. Among variants that learned the harder CartPole environments, the complete architecture showed the most consistent retention. A selection ablation also showed that the retrieval rule affected performance. In the evaluated sequences, ENA adapted more slowly than PPO on CartPole and achieved lower returns than SAC on HalfCheetah. The evidence concerns the complete architecture and does not isolate gradient-free optimization as the cause of retention or establish superiority over other continual-learning methods.

cs.LG · cs.AI · cs.NE

新论文 · v1arXiv:2611.21586

Beyond Job Titles: Interpreting Early-Career Job Advertisements with Sparse Autoencoders and Semantic Clustering

Yisong Cao, Leah Kim, Brian Wright, Ali Rivera

原文摘要

Job titles and job descriptions alone provide limited insight into how technical roles differ in a changing job market. To assess how such roles differ in their work and industry applications, we design and compare two methods based on deep learning and transformer representations using 36,081 early-career job postings collected from LinkedIn in the United States between December 2025 and October 2026. We first apply PERC, short for Preprocessing (P), Embedding (E), Dimensionality Reduction (R) and Clustering (C). We employ GPT-6 Luna to classify job description passages into Team context, Role task and Qualifications. We then create combinations of these sections and examine whether embedding and clustering the segmented passages produce meaningful semantic clusters about different job roles. We use Maximum Mean Discrepancy (MMD) to rank observed differences between embedding distributions and employ a pretrained sparse autoencoder (SAE) to extract features from layer-19 representations of Llama-3.1-8B-Instruct. Lastly, we employ GPT-6 Luna to come up with hypotheses about job roles' feature patterns, and GPT-6.1 Terra to investigate whether those patterns exist in held-out job descriptions from unseen companies. Some example findings include Data Scientist advertisements placing more emphasis on machine learning model development, Data Analyst advertisements on reporting business performance, and Machine Learning Engineer advertisements on applying developed models in real-world settings. We also observe differences in the applications described by Data Analyst and Business Analyst advertisements across selected months, although our dataset's scale and uneven coverage limit their interpretation. Overall, we present a realistic application of SAEs and PERC to unstructured textual data and examine how automated insight extraction could support manual analysis of job descriptions.

cs.CL

新论文 · v1arXiv:2611.21584

CertiSum: Bitwise-Identical MXFP4 Training Across Platforms and Parallelism Layouts

Steve Rhyner, Yubo Gao, Stefan de Lasa, Sankeerth Durvasula, Nandita Vijaykumar

原文摘要

Training with MXFP4, a 4-bit microscaling format, is non-deterministic: identical inputs can produce different results across parallelism layouts and GPU vendors. These differences complicate debugging and training audits and can cause training and inference engines to disagree. We present CertiSum to make MXFP4 training bitwise invariant across runs, parallelism layouts, and GPU vendors. Its key insight is that native FP32 accumulation of MXFP4 products is often already exact for every summation order. CertiSum collects statistics during quantization to certify native matrix multiplication results, recomputes uncertified outputs exactly, and uses exact kernels directly where certification rarely succeeds. CertiSum keeps quantization blocks unchanged across layouts and merges partial sums without rounding, including in attention and weight-gradient computation. In 200-step Qwen3-8B-Base experiments, CertiSum preserves training states bit for bit across AMD MI350X and NVIDIA GB200 and across changes in data, tensor, and context parallelism on MI350X. Across three 8B--14B models on FineWeb-Edu using MI350X, it adds 11.8--60.5% to training-step latency relative to its non-exact MXFP4 counterpart at the larger evaluated input shapes, with speedups of up to $1.24\times$ over BF16 and $1.70\times$ over deterministic BF16.

cs.LG · cs.DC

版本更新 · v2arXiv:2609.32116

Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

Marco Biroli

原文摘要

Best-of-$N$ jailbreaking (BoN) bypasses safeguards of aligned models by drawing $N$ independent augmentations of an unsafe prompt and sampling $M$ completions of each. Previous works have shown that the attack success rate (ASR) seems to follow a power-law in $N$, which we challenge. The exponent drifts with $N$, and the reported exponential crossover is consistent with a finite-size effect of the adversarial dataset. Little work has been done to explore the entire two-budget ($N, M$) attack surface as well as its dependence on the generation temperature $T$. We introduce a simple barrier model where each prompt has a baseline safety level and each augmentation a random thermally activated barrier. Then five numbers, each backed by an interpretable safety mechanism, determine the entire ($N, M$) attack surface. They extrapolate predictions from $N \leq 100$ to $N = 10^4$, collapse five distinct models on the same scaling function and predict ASR at different temperatures from the one they were fitted at. The extrapolation holds under two automated judges and on held-out prompts.

cs.AI · cond-mat.stat-mech

版本更新 · v4arXiv:2511.11934

A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts

Claudio César Claros Olivares, Austin J. Brockmeier

原文摘要

We present a systematic benchmark of out-of-distribution (OOD) detection confidence scoring functions (CSFs) through a representation-centric lens. Our study spans CNN and ViT backbones, multiple training paradigms, four image-classification source datasets (CIFAR-10, CIFAR-100, SuperCIFAR-100, and TinyImageNet), and OOD datasets grouped into near, mid, and far regimes based on CLIP-derived semantic distances. To compare CSFs across these settings, we employ a rank-based pipeline of Friedman and Conover tests that identifies top cliques of statistically indistinguishable winners under threshold-free ranking metrics (AURC and AUGRC). The main empirical finding is that the family of CSFs that are competitive detectors correlates with characteristics of the learned representation. For both CNNs and ViTs, simple probabilistic scores dominate misclassification detection. On CNNs, margin-based scores are strongest in near-OOD regimes, while geometry-aware scores such as NNGuide, fDBD, and CTM become more competitive as shift severity increases. On fine-tuned ViTs, the top cliques are led mainly by reconstruction- and residual-based scores. To interpret these ranking shifts, we analyze the last-layer representation using Neural Collapse (NC) metrics. The resulting picture is consistent across architectures: prototype- and boundary-aware scores become stronger when the representation is more collapsed and better aligned with classifier weights, whereas weaker-collapse regimes favor gradient- and manifold-based scores. Building on these insights, we propose two contributions: a simple PCA-based projection-filtering procedure that improves detector performance, and an approach that uses only the NC measurements of a trained classifier to predict its competitive out-of-distribution detector shortlist, without OOD data for that classifier and without knowledge of the shift.

cs.LG · cs.CV

新论文 · v1arXiv:2611.21579

ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises

Jaime C. Acosta, Anantaa Kotal, Aritran Piplai

原文摘要

Cyber-range and capture-the-flag scenario construction remains labor-intensive because authors must coordinate infrastructure, vulnerable services, attack paths, artifacts, and success conditions. LLMs can propose detailed exercises, but plausible descriptions do not guarantee deployable software or verifiable objectives. We present ScenarioForge, which turns high-level requirements into resource-grounded topologies, services, traffic, segmentation, and challenge chains, then instantiates and validates them in the Common Open Research Emulator (CORE). The ScenarioForge Execution Dataset contains 226 materialized scenarios covering 294 Vulhub images and all 85 custom-built challenge-resource generators developed with our AI-assisted scaffolding. All 226 passed construction, preview, sequencing, deployment, strict runtime validation, and live artifact checks; their 867 steps, each an individually verifiable challenge objective, comprise 457 vulnerability-backed and 410 generated-resource-backed instances. In a separate 50-prompt matched benchmark, ScenarioForge+Qwen3.8 and ScenarioForge+GPT5.6 each achieved 50/50 (100%) topology/build success and 160/160 intent fields; direct frontier generation reached 41/50 builds and 147/160 fields only with the full cumulative scaffold: structure, vocabulary, policy, and container-image guidance. The test still omitted ScenarioForge's downstream challenge-resource generation, dependency/flag sequencing, deployment, and live validation. The artifacts support operationally rich, reproducible exercises for training and evaluation.

cs.CR · cs.AI

新论文 · v1arXiv:2611.21577

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

Zeynab Anbiaee, Sajjad Dadkhah, Ali A. Ghorbani

原文摘要

Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessarily bound to a verified provider identity. This paper studies this gap as tool-provider misbinding: a failure in which a request intended for a legitimate provider is instead resolved to an attacker-controlled tool. The attacker does not compromise the host, LLM, legitimate server, or network channel; it only operates another MCP server that advertises tools with chosen metadata. We formulate tool provider misbinding as an attacker-controlled tool-selection optimization problem and evaluate it in a controlled MCP environment across five LLM-based clients. The results show that interactions drive misbinding. The strongest failures occur when exact-name collision, task-aligned description, and compatible schema reinforce one another, but authority-enhanced descriptions with compatible schema can also cause wrong-provider execution or unresolved provider ambiguity without name collision. Different models expose the same provider-binding weakness differently, including attacker-controlled provider selection, clarification requests, and unstable or inconsistent provider resolution.

cs.CR · cs.AI

新论文 · v1arXiv:2611.21571

DynSurvX: Time-Resolved Explanations for Dynamic Survival Predictions

Van Tuan Nguyen, Agathe Guilloux

原文摘要

Recent survival models integrating longitudinal data achieve strong predictive performance, but their predictions are often difficult to interpret, limiting their clinical use. We propose DynSurvX, a model-agnostic explainability framework for dynamic survival prediction with mixed static and longitudinal covariates. Based on Shapley values, DynSurvX introduces a hierarchical two-phase strategy that first identifies influential longitudinal features and then adaptively refines their temporal importance, enabling fine-grained explanations while reducing computational cost. The framework provides time-resolved explanations that evolve as new patient data become available. Experiments on simulated and two clinical datasets show varying agreement with theoretical importance across prediction models, with closer agreement for better-performing models, alongside clinically interpretable insights in real-world settings. It remains robust across prediction settings and reduces computation time by 41--80\% relative to the temporal explanation baseline, making dynamic explanations practical.

cs.LG

版本更新 · v2arXiv:2607.01191

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Hongxing Li, Xiufeng Huang, Dingming Li, Wenjing Jiang, Zixuan Wang, Haolei Xu, Hanrong Zhang, Haiwen Hong 等 14 位作者

原文摘要

Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typically do not explicitly distinguish perception from reasoning. In this paper, we propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process: the model first localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner based on the annotated image and cropped regions. To better align training with this decoupled formulation, we further introduce Perception-Reasoning Alternating GRPO (PRA-GRPO), a role-aware reinforcement learning strategy that alternates between perception-focused and reasoning-focused updates using only final-answer supervision. Built on top of Qwen3-VL-Instruct-2B/4B/8B, P2R consistently improves performance across model scales. In particular, P2R-4B achieves 93.2% on V-Star, 81.9% on HR-Bench-4K, and 80.5% on HR-Bench-8K, substantially outperforming its corresponding backbone. Further experiments show that the benefits of P2R extend beyond high-resolution benchmarks to broader multimodal reasoning tasks. These results suggest that explicitly decoupling perception from reasoning provides an effective framework for fine-grained visual reasoning.

cs.CV

新论文 · v1arXiv:2611.21565

When Do Histology Foundation Models Need Geometric Test-Time Augmentation?

Lars Chen, Valentino F. Foit, Dorry Segev, Michal Mankowski

原文摘要

Test-time augmentation (TTA) aggregates model predictions across multiple transformed views of an input during inference. Because histology images lack a canonical orientation, $D_4$ TTA---pooling across the 8 rotations and reflections of a square---is a standard default in computational pathology. However, the rise of self-supervised histology foundation models (FMs) with inherent rotational invariance calls its continued utility into question. We benchmark 9 histology FMs and 6 general-purpose models across four patch-level and two whole-slide image (WSI) datasets. We find that $D_4$ TTA remains a reliable post hoc improvement, but benefits diminish from $+1.98$ percentage points (pp) for general-purpose backbones to $+0.50$ pp for histology FMs on TCGA-UT, and shrink further for the largest models. To eliminate computational overhead, our experiments demonstrate that entropy routing---applying TTA selectively to uncertain predictions---recovers most of the gain while augmenting only ${\sim}13\%$ of samples. Finally, we show that patch-level TTA improvements do not transfer to slide-level multiple instance learning (MIL). Code: https://github.com/lars-chen/histology-tta

cs.CV · cs.LG

新论文 · v1arXiv:2611.21563

Wildfire-SSR: Geolocation-Aware Multimodal Fusion for Structure-Level Wildfire Risk Assessment

Yu-Hsuan Ho, Yiming Xiao, Hao-En Lai, Ali Mostafavi, Samuel D. Brody

原文摘要

Structure-level wildfire vulnerability assessment is critical for reducing losses in wildland-urban interface communities, yet existing methods often fail to combine parcel-scale ignition pathways with community-scale geographic coverage. This study introduces Wildfire-SSR (Satellite and Street-view for wildfire Risk), a geolocation-aware multimodal framework that integrates macro-scale satellite context with micro-scale street-view evidence. A Vision-Language Model extracts wildfire-relevant building and site attributes from pre-event street-view panoramas and converts them into structured semantic text. These features are spatially aligned with satellite imagery through a decoupled cross-attention fusion decoder, while a frozen satellite-pretrained DINOv3 encoder captures overhead visual context. Alternative geolocation embedding strategies are evaluated to anchor text-derived features within each satellite patch. The framework is tested on approximately 37,000 structures affected by the 2025 Eaton and Palisades fires in Los Angeles, using wildfire risk labels derived from relative post-event damage patterns to better represent inherent structural vulnerability. Rotary Positional Embedding provides the strongest spatial grounding, achieving a building localization F1 score of 0.6735 and a harmonic mean F1 score of 0.2476 for five-class pixel-level risk classification, outperforming unimodal baselines and an unanchored multimodal configuration. The model also shows a conservative bias in higher-risk classes, reducing severe-risk underestimation, and completes end-to-end assessment of the study area in 37 minutes on a single GPU. Wildfire-SSR reframes cross-view fusion as localized semantic alignment and provides a scalable tool for mitigation prioritization, resilience planning, and insurance-oriented wildfire risk assessment.

cs.CV

新论文 · v1arXiv:2611.21562

Severe but Harmless: Stress-Testing Shift Severity for Frozen Time-Series Forecasters

Korede R. Bishi, Dominic Okonkwo, Adetayo Okunoye

原文摘要

Zero-shot time-series foundation models (TSFMs) have become attractive alternatives to task-specific models because they handle diverse downstream tasks, including anomaly detection and forecasting, without per-series training. However, time-series data undergo distribution shifts, and the dissimilarity between two regimes is commonly scored with statistical measures such as Wasserstein-1, where a higher score is read as a more severe shift. In systematic experiments using three established severity measures on nine regime shifts from three standard traffic datasets, we show that these measures do not reliably predict degradation for instance-normalized TSFMs. The regimes rated most severe are not the regimes that degrade the models most, and degradation reaches 29% in the lowest-scoring regime. In most cases, the audit shows no positive relationship between measured severity and model degradation. We provide an equivariance-based stress-testing analysis that explains why severity readings can become decoupled from model degradation.

cs.LG · cs.AI

新论文 · v1arXiv:2611.21559

Reference Forcing: Long Video Generation with Region-Guided Drift Correction

Sheng Zhao, Haitian Zheng, Weikai Lin, Junjie Zhao, Yuhao Zhu

原文摘要

Long video generation should keep the subject and background consistent while supporting rich, natural motion. However, autoregressive models are often distilled with distribution matching distillation (DMD) over short windows, which does not train them to keep this consistency over long ranges. As a result, the subject and background can drift over time. Methods that manage the key-value (KV) cache retain or retrieve history to reduce drift. Yet this history may itself have drifted. We propose Reference Forcing, which uses the initial frames as an appearance reference. We first build a teacher that uses attention masks to force each region of a new frame to attend to the same region in the initial frames. The teacher finds these regions with off-the-shelf segmentation models. We then distill this behavior into a separate attention path of the student, which needs no external models at inference. We further introduce value correction, which corrects drifted values in the KV cache toward the matching values of drift-free initial frames. Experiments show that Reference Forcing achieves state-of-the-art subject and background consistency among long-video methods on different base models, and its advantage grows with video length. Ablations show both components are needed to gain consistency without losing motion. More visualizations and code are available at https://zhaosheng-thu.github.io/reference-force/

cs.CV

版本更新 · v2arXiv:2611.07222

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Woosang Lim, Yeseul Chang, Jaewoo Lee

原文摘要

Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an action goes can instead be read from the tools' typed returns: an email's sender or a payment's account arrives in a typed field, while injected instructions arrive as free text. SPILLWAY turns this observation into a deterministic floor with no per-task plan. The check admits a call when each target value that appears in tool output but not in the user's task was returned by a read-only tool in a typed field or is covered by a fixed delegation rule. A deterministic sanitizer removes instruction-like regions its fixed rules match before the model reads them and retains the removed spans as evidence, and a local judge may restore a refused call, never one whose target lies in the removed text. Across three backbones, and seven task suites on one of them, no standard templated injection redirects an action to an attacker's target under SPILLWAY, at the highest observed mean utility and composite scores (NRP, ERS) of the defenses we run under that attack. A forged chat template also produces a raw zero, and mean in-scope attack success under a released reinforcement-learning attacker is .005. SPILLWAY reaches this floor with no defense-triggered backbone re-run and almost no added model call. As personal AI agents act on users' email, files, and payments, SPILLWAY gives them an auditable refusal floor on where their actions go that keeps them useful and holds across backbones.

cs.CR · cs.AI

新论文 · v1arXiv:2611.21554

Reading or Remembering? Measuring Temporal Contamination in Language Models

Arunkumar V, Gangadharan G. R., S. Senthilkumar

原文摘要

Language models are now used to read central-bank text for economic forecasting, but most were trained on text written after the documents they read. A model reading a 2021 FOMC statement may already know that inflation rose in 2022, so part of its apparent skill can be memory of the outcome, a temporal form of test-set contamination. We measure this memory on FOMC statements and minutes from 2000 to 2026 by comparing modern open models with chronologically consistent models, which are trained only on text from before a fixed date. Asked about past GDP outcomes given only a date, models that cannot know the answer still reach an AUC of up to 0.64 from priors on dates and eras, so chance is the wrong baseline. Against these memory-free models on the same questions, most modern models recall which years had strong growth. Membership-inference scores sort documents by era and document type rather than by whether a model saw them, as exact counts in an open pretraining corpus show. In real-time nowcasts, every lookahead premium we estimate on US GDP is smaller than the forecast comparison can detect at macroeconomic sample sizes, and none on GDP or inflation survives correction for multiple testing. Lookahead audits should therefore measure memory directly against memory-free models on the same items.

cs.LG · cs.CL

新论文 · v1arXiv:2611.21553

BLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video Agents

Kanchana Ranasinghe, Honglu Zhou, Dominick Reilly, Le Xue, Shusheng Yang, Juan Carlos Niebles, Silvio Savarese, Ran Xu

原文摘要

Streaming video understanding is becoming increasingly important for real-world interactive systems. Such systems must be proactive for natural and useful human interaction: they should respond as soon as sufficient evidence becomes available while avoiding premature, redundant, or incorrect responses. We present BLIP-Live, a framework unifying data, metrics, harness, and training around a shared formulation of proactivity as effective causal response decisions balancing the two competing objectives of responding vs silence. First, we construct BLIP-Live-780K dataset containing human annotations of proactive response content and timing, which defines this desired behavior. We then propose PAUC-F, a metric to effectively measure our desired proactive behavior. PAUC-F combines existing response timeliness metrics with firing precision to reward early useful responses without rewarding excessive firing. With our desired behavior defined and measurable, we finally investigate model-agnostic inference harnesses that draw out proactive streaming capabilities of offline vision language models (VLMs), together with training pipelines that learn to further improve their proactive responsiveness. Across both settings, we find that combinations of sliding visual windows, online interaction memory, and structured response outputs consistently yield strongest proactive performance. Our experiments result in two models, with our BLIP-Live-Qwen model achieving state-of-the-art performance across four proactive streaming benchmarks, with gains up to 44% over baselines and outperforming multiple closed API models. Our code and data will be released publicly.

cs.CV

新论文 · v1arXiv:2611.21552

Benchmarking memory and nonlinear processing capacity of quantum recurrent neural networks for time series prediction

José Daniel Viqueira, Andrés Gómez, David Mera

原文摘要

Quantum machine learning has emerged as a promising approach to time series prediction. While quantum reservoir computing has been widely explored for this setting, variational quantum models tailored to sequential data remain comparatively understudied, largely because they are difficult to train. In this work, we present a rigorous benchmark of variational quantum recurrent neural networks (QRNNs) on time series prediction tasks, focusing on two key capabilities: memory and nonlinear processing. We introduce a task-driven methodology that quantifies model capacity, enabling an intuitive and fair comparison across architectures, including classical recurrent baselines. We evaluate the proposed framework on two generic benchmark tasks and on a synthetic dataset describing a chaotic system. Overall, the quantum models achieve performance comparable to their classical counterparts, but classical models scale better with the memory size within the range studied. Notably, one QRNN variant shows higher average capacity on the task designed to jointly probe memory and nonlinear capacity. Moreover, our results show that quantum models offer better capacity when we are able to find a good parameter initialization. However, the increasing sensitivity to initialization leads to a lower probability of finding good solutions as the model size increases. These results provide a principled starting point for designing richer quantum recurrent architectures and for assessing where they may offer practical benefits.

quant-ph · cs.LG

新论文 · v1arXiv:2611.21550

ONAM: Fitting Orthogonal Neural Additive Models for Post-Hoc Interpretability of Black-Box Predictions

David Köhler, Matthias Schmid

原文摘要

Modern machine learning models, such as artificial neural networks, achieve high predictive performance through increasingly complex black-box architectures, limiting their use in settings where transparency, interpretability, and fairness are required. Here we present the R package ONAM, which provides a novel and practical implementation of functional decomposition, a technique to facilitate the interpretability of black-box models through structured effect representations. ONAM implements an algorithmic framework for the post-hoc decomposition of predictions into components associated with different input features. The package is designed for usability and efficiency, including functionalities for visualization as well as quantitative measures to assess interpretability. As a model-agnostic method, it can be applied to a wide range of prediction models. We describe the mathematical foundations, algorithmic design, and software architecture of ONAM. A central result of the proposed methodology is that the resulting decomposition satisfies the condition of hierarchical orthogonality, thereby guaranteeing that all components are identifiable and uniquely defined.

stat.ML · cs.LG · stat.ME

新论文 · v1arXiv:2611.21548

TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings

Sydney Johns

原文摘要

Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRACE learns from benign system-activity graphs by combining message-passing and topological representations, then assigns anomaly scores in the same projected embedding space optimized by the contrastive objective. This design captures both local interactions and graph-scale structural deviations without using attack labels during representation learning. A labeled validation set containing benign and malicious graphs is used only to calibrate the anomaly threshold. We evaluate TRACE on StreamSpot, GraSec-IoT, and Unicorn Wget against a supervised graph neural network and the benign-only GraphCL baseline. TRACE obtains F1 scores of 0.923, 0.790, and 0.583, respectively. Compared with GraphCL, this is higher on StreamSpot (0.450) and Unicorn Wget (0.203), but lower on GraSec-IoT (0.975). The supervised model leads on StreamSpot and GraSec-IoT, whereas TRACE has the highest F1 on Unicorn Wget. The mixed results show that topology-aware benign-only learning can improve detection in some graph settings but does not provide a uniform advantage.

cs.CR · cs.AI

版本更新 · v3arXiv:2611.09822

Discovering formally verified quantum programs with AI

Sergey Shirobokov, Ben Jaderberg, Katerina Hristova, George Tsoukalas, Johannes Bausch, Eric Wieser, Francisco J. H. Heras, Nicholas C. Rubin 等 25 位作者

原文摘要

The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human collaboration. In mathematics and computer science, large language models have accelerated progress through automated discovery loops. However, quantum algorithms can only be evaluated by classical computers on restricted or small instances. Here we demonstrate automated discovery of quantum programs beyond these regimes including order-of-magnitude improvements on scientific applications. To achieve this, we build a quantum program library in the Lean theorem prover in which Gemini 4 agents synthesize novel programs against formal problem specifications and verify their correctness and cost. Agent teams collaborate, sharing results and knowledge through wikis and discussing ideas at organized conferences. Our results improve on prior baselines for parallel search (up to 2.57x), quantum arithmetic (290x), and simulations relevant to fusion, photochemistry and drug-metabolism by 12x, 8x and 2.5x respectively. Combining human and artificial intelligence at scale, under the rigor of mathematical proof, lets researchers design algorithms that today's classical and quantum computers cannot test, shortening the path to practical quantum computation.

quant-ph · cs.AI · cs.PL

新论文 · v1arXiv:2611.21545

Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests

Arunkumar V

原文摘要

Language models increasingly write the explanations people receive when a rule system denies their request. If several rules deny the request independently, an explanation can name a true reason and still leave the person denied after they fix it. We call the missing property recourse validity: changing what the explanation cites, without changing what was asked for, can flip the decision. We compute it exactly, and a hitting-set argument predicts from the policy alone when a correct reason fails. In six of seven rule systems ported from access control and US benefit eligibility, a single correct reason almost never gives recourse when several reasons apply. Across 20 LLMs, checks of whether the cited reasons are correct, computed or asked of an LLM judge, are close to chance at spotting this failure, as the argument predicts. A strong judge asked whether acting on the explanation would work does spot it. Stronger and reasoning models do better but still fail on many denials with four or more independent reasons. Asking for every rule helps every open model with room to improve. Explanations of eligibility decisions should be built from the decision function and judged by whether acting on them works.

cs.AI · cs.CL · cs.CY

新论文 · v1arXiv:2611.21542

The cost of enforcing long-run coverage: a phase transition in online conformal prediction

Yu Gui, Rina Foygel Barber, Cong Ma

原文摘要

Consider an online prediction setting, where at each time, we are given a new feature vector and asked to provide a prediction interval or prediction set that will likely contain the corresponding response. In this setting, if the data points are i.i.d. (or more generally, exchangeable), conformal prediction provides a mechanism for building valid prediction sets around the output of any trained model, offering coverage probability $\geq 1-α$ at each time $t$. In practice, however, issues such as distribution drift, changepoints, or other challenges may cause violations of the i.i.d. assumption. In this adversarial setting, online conformal prediction methods can still offer guarantees on long-run empirical coverage. However, there is a trade-off between these two types of goals: enforcing tight constraints on long-run empirical coverage to protect against the adversarial setting can lead to unstable oscillations in the instantaneous training-conditional coverage in the i.i.d. setting. In this work, we seek best-of-both-worlds algorithms that aim to minimize cumulative error in instantaneous training-conditional coverage when in the i.i.d. setting, while also offering long-run empirical coverage guarantees in the adversarial setting. Specifically, consider a condition that requires long-run empirical coverage to deviate from the target level $1-α$ by at most $\mathcal{O}(T^{-β})$, for some $β\in[0,1]$. We prove that this family of conditions can be described with a phase transition. For $β\in[0,\frac{1}{2}]$, it is possible to construct algorithms satisfying such a constraint in the adversarial setting, while offering the same instantaneous coverage performance as split conformal prediction if the data is in fact i.i.d. On the other hand, for $β\in(\frac{1}{2},1]$, this type of condition comes at a cost, and does not achieve best-of-both-worlds behavior.

math.ST · cs.LG · stat.ML

新论文 · v1arXiv:2611.21541

SciResearch-Eval: Evaluating Scientific Judgment in Autonomous Experimental Agents

Brian T. Weston, Alondra Torres Contreras, Aldair E. Gongora

原文摘要

We introduce SciResearch-Eval, an interactive benchmark of scientific judgment built on a standard laboratory problem: measuring a material's thermal properties by heating it and fitting a heat-conduction simulator. An agent designs its own experiments, uses a supplied simulator that may be under-resolved or physically wrong, and reports each property with a 95% interval. To our knowledge it is the first benchmark to combine agent-designed experiments, a deliberately flawed simulator, and proper scoring of calibrated intervals against exact ground truth. On a held-out split (93 tasks, 9 models, 2,511 episodes), models handle procedural traps. When the simulator is missing physics, most report wrong values while stating they are 95% sure: their ranges contain the truth in 20-62% of cases, against 94% for GPT-6 Astra and 99% for Claude Fable 5.2. At default effort the failing Claude 5.5 models rarely diagnose the missing physics (Opus in 35% of episodes, against 66% for Astra), and even when they do, their ranges often miss; Astra and Fable design experiments in which the flawed simulator is accurate, such as gentle heating, which keeps Astra calibrated even when it does not name the cause. Asking for wider intervals does not help; stating the strategy improves interval scores 1.6-2.5-fold, replicated on a pre-registered fresh split, but coverage barely moves. A pre-registered effort ablation shows that the correction is latent in the Claude 5.5 models: at maximum effort Opus improves more than tenfold and is no longer detectably behind Astra at default, but only with 13-31 times more reasoning; older and open-weight models gain nothing. Fable 5.2 is the most accurate model at default effort (interval score 1.9 times better than Astra's) but writes 6 times as many tokens, and at Astra's token count it falls short. We release the environment, graders and harness.

cs.AI · cs.LG · physics.comp-ph

新论文 · v1arXiv:2611.21539

Seen but Unsaid: Locating and Repairing Cross-Image Comparison in Vision-Language Models

Zhaoning Zhang

原文摘要

Vision-language models (VLMs) often fail to match a point or an object across two images, even when the answer can be decoded from their own hidden states. We trace this failure from the visual tokens to the answer letter, in Qwen3-VL (2B-32B), InternVL3.5-8B, and Gemma-3-12B, on synthetic shape matching, same-instance point correspondence (HPatches), and semantic correspondence (SPair-71k), and find two distinct failure points, a small set of attention heads that carries the comparison, and a repair that touches 0.02% of the parameters. Two failure points: exact copies are compared but not read out. An answer-position probe exceeds the calibrated output by 15 to 25 points in every family, for nameable and unnameable shapes alike, and steering along the probe's direction moves no more answers than random directions. Semantic correspondences are present in the visual tokens but never reach the answer. One pathway: redistributing the cross-image attention of 16-32 heads, with its mass preserved, removes 17-22 points of synthetic and 15-32 points of HPatches accuracy, against at most 7 for random or attention-matched heads. A lever that training finds on its own: training only these heads' query and key projections raises SPair-71k accuracy by 28.3 points (Qwen3-VL-8B) and 25.1 points (InternVL3.5-8B), beats both layer-matched and attention-matched heads, and transfers to HPatches and BLINK. An unconstrained all-layer adapter routes 21-51% of its gain through the attention of the same heads, against at most 7% for random heads, and does so by changing what they read (83-86% of the effect) rather than their weights. Every decision rule was frozen before its run, and every reported number is recomputed by independent verification scripts.

cs.CV · cs.CL · cs.LG

新论文 · v1arXiv:2611.21538

Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle

Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar

原文摘要

Reinforcement learning from verifiable rewards inherits whatever its verifier gets wrong. Outside mathematics and code the verifier is a proxy, a rubric, a learned judge or a hand-written checker, and its distance from the true objective is never measured, so a rising reward cannot be told apart from a hack. We build a setting where the true reward is exactly computable at the process level: executable authorization policies over 124,416 contexts admit an oracle that lists every minimal sufficient reason for every decision. We compile these policies into exact process rewards, degrade the verifier along seven realistic axes (outcome-only, sufficiency, recall-only, extraction noise, coarse taxonomy, stale policy, LLM judge), and train against each while the exact verifier scores every rollout. Four phenotypes appear. Optimistic verifiers are hacked by padding: the sufficiency proxy ends at 0.940 while true faithfulness falls from 0.731 to 0.667 on 96 held-out episodes. Outcome-only verifiers saturate and stop teaching, noise dilutes, and ranking-preserving gaps do no harm. A model-free audit of the verifier, its selection error and gap sign, together with a short saturation pilot, anticipates which phenotype a run will produce. Across nine configurations spanning two frameworks, two model vendors, two adapter sizes, three precisions, two initialisations and two seeds, the phenotypes recur, sufficiency damage is positive in all 10 replication cells and beyond two standard errors in 7, and optimistic gaps remain the steeper branch. The damage magnitude does not replicate, and five pre-registered attempts to explain it are reported as they fell. We release the testbed, the training instrumentation, and 14 real public policies (Cedar, OPA, Gatekeeper) ported to executable oracles.

cs.LG · cs.AI · cs.CL

版本更新 · v2arXiv:2611.17466

Use-case-driven ontology modeling with the NeOn methodology for ambient assisted living

Daniele Spoladore, Marco Sacco, Alberto Trombetta, Edoardo Battisti Sironi

原文摘要

Research on smart homes and ambient assisted living (AAL) has grown steadily over the last decade, driven largely by the ageing of the population. A smart home has to coordinate heterogeneous smart objects in order to offer services tailored to its dwellers, and this requires a shared formal description of both the dwellers and the devices. We present the ontology developed as the semantic data layer of the Virtual Home Framework in the Italian Design For All project. Its requirements are derived from two use cases: a frail elderly woman who exercises at home on a cycle-ergometer, and a designer who configures a kitchen for users with different impairments. The requirements are collected in an Ontology Requirements Specification Document and the ontology is built with the NeOn methodology, reusing and reengineering existing ontologies where possible. The resulting modular ontology describes users through the International Classification of Functioning, Disability and Health (ICF) and through their cardiorespiratory fitness; it also describes smart objects, their programs, the measurements they produce, and the comfort dimensions of the home. SWRL rules classify fitness levels, suggest exercise loads, assess indoor comfort, and identify the smart objects suited to a given impairment.

cs.DB · cs.AI