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

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 01:34 — 2026-11-17 01:34(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:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,922 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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.10913

Bit-level Perceptron Prediction for Indirect Branches

Elba Garza, Samira Mirbagher-Ajorpaz, Tahsin Ahmad Khan, Daniel A. Jiménez

原文摘要

Modern software uses indirect branches for various purposes including, but not limited to, virtual method dispatch and implementation of switch statements. Because an indirect branch's target address cannot be determined prior to execution, high-performance processors depend on highly-accurate indirect branch prediction techniques to mitigate control hazards. This paper proposes a new indirect branch prediction scheme that predicts target addresses at the bit level. Using a series of perceptron-based predictors, our predictor predicts individual branch target address bits based on correlations within branch history. Our evaluations show this new branch target predictor is competitive with state-of-the-art branch target predictors at an equivalent hardware budget. For instance, over a set of workloads including SPEC and mobile applications, our predictor achieves a misprediction rate of 0.183 mispredictions per 1000 instructions, compared with 0.193 for the state-of-the-art ITTAGE predictor and 0.29 for a VPC-based indirect predictor.

cs.AR

版本更新 · v2arXiv:2605.07317

Amortized-Precision Quantization for Early-Exit Vision Transformers

Rui Fang, Hsi-Wen Chen, Ming-Syan Chen

原文摘要

Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer utilization when modeling quantization error and reveals depth-precision trade-offs. Building on APQ, we propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimizes exit thresholds and bit-widths under explicit risk control to improve inference stability. MAQEE establishes a superior Pareto frontier in the accuracy-efficiency trade-off across classification, detection, and segmentation, with comparisons at predefined task-specific performance targets. On ImageNet, it achieves 79.41% Top-1 accuracy while reducing BOPs by 10.9% relative to utilization-only allocation. Measurements of the deployed models on an RTX 5090 show GPU throughput improvements of $2.26\times$ on ImageNet and $3.06\times$ on CIFAR-100 over full-depth FP32 inference. Source code is available at https://github.com/Rui-Fang/MAQEE.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.18867

EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample

Guohao Chen, Shuaicheng Niu, Geng Li, Yunbei Zhang, Shilin Shan, Chunyan Miao, Jianfei Yang

原文摘要

Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which incurs substantial memory overhead and makes them difficult to deploy on edge devices, quantized models, specialized accelerators, or black-box models. In this work, we study test-time model evolution under a strict two-forward budget, a setting that pushes adaptation toward highly efficient real-world deployment. We reveal three key obstacles in zeroth-order test-time optimization: susceptibility to shortcut solutions, uncontrolled weight drift, and ineffective update direction estimation. To overcome them, we propose EVA-0, a minimal zeroth-order adaptation framework that: 1) keeps the loss scale-invariant to prevent shortcut solutions; 2) devises an anchor-guided optimization strategy to alleviate weight drift; 3) uses sample-wise symmetric two-sided perturbation for update direction estimation and inference. EVA-0 requires no BP and performs both inference and adaptation within only two forward passes per sample. Results on ImageNet-C & ViT-Base show that EVA-0 outperforms both BP-based DeYO and BP-free FOA, while achieving a 14x speed-up over FOA. Code will be released.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10911

Towards A Parametrized Complexity of Determinization

Ivan Baburin, Ryan Cotterell

原文摘要

Given a nondeterministic finite automaton (NFA), we want to estimate the difficulty of finding an equivalent deterministic finite automaton (DFA). We demonstrate that computing the state complexity of an NFA within polynomial precision is \textsf{PSPACE}-hard, and furthermore the same holds for the complexity of the subset construction, Brzozowski's algorithm, or, indeed, \emph{any} determinization algorithm which runs at least as fast. This result implies that making any \textit{a priori} estimate of the running time of the major determinization algorithms is inherently hard. To circumvent this---in the spirit of parametrized complexity---we try to identify complexity measures which can guarantee efficient determinization. Our main idea rests on linking the complexity of the subset construction to transition monoids using the semigroup complexity. We show that the semigroup complexity by itself can be reasonably approximated for certain classes of NFAs, and then introduce \emph{subset complexity}---a refinement of the semigroup complexity which has a tighter connection with the subset construction. In certain scenarios, the subset complexity can be approximated in polynomial time, making it potentially viable for more practical applications.

cs.FL

版本更新 · v3arXiv:2605.07061

Do Joint Audio-Video Generation Models Understand Physics?

Zijun Cui, Xiulong Liu, Hao Fang, Mingwei Xu, Jiageng Liu, Zexin Xu, Weiguo Pian, Shijian Deng 等 11 位作者

原文摘要

Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request physically inconsistent audio-video behavior. Each generation is evaluated along five dimensions: visual semantic adherence, audio semantic adherence, visual physical commonsense, audio physical commonsense, and cross-modal physical commonsense. Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts. We further introduce AV-Phys Agent, a ReAct-style evaluator that combines a multimodal language model with deterministic acoustic measurement tools, producing rankings that closely align with human ratings. Our results identify cross-modal physical consistency and transition-driven scene dynamics as key open challenges for joint audio-video generation.

cs.SD · cs.AI · cs.CV · cs.MM

版本更新 · v2arXiv:2603.26125

CL-SEC: Cross-Layer Semantic Error Correction Empowered by Language Models

Yirun Wang, Yuyang Du, Soung Chang Liew, Yuchen Pan, Feifan Zhang, Lihao Zhang

原文摘要

Achieving reliable communication has long been a fundamental challenge in networked systems. Semantic Error Correction (SEC) leverages the semantic understanding capabilities of language models (LMs) to perform application-layer error correction, complementing conventional channel decoding. While promising, existing SEC approaches rely solely on context captured by LMs at the application layer, ignoring the rich information available at the physical layer. To address this limitation, this paper introduces Cross-Layer SEC (CL-SEC), an LM-empowered error correction framework that integrates cross-layer information from both the physical and application layers to jointly correct corrupted words in text communication. Using a Bayesian combination in product form tailored to this framework, CL-SEC achieves significantly improved performance over methods that process information in isolated layers. CL-SEC shows substantial gains across multiple error-correction metrics, including bit-error rate, word-error rate, and semantic fidelity scores. Importantly, unlike most semantic communication systems that focus solely on recovering the semantic meaning of transmitted messages, CL-SEC aims to reconstruct the original transmitted message verbatim, leveraging the semantic understanding capabilities of LMs for precise reconstruction.

cs.IT · eess.SP

新论文 · v1arXiv:2611.10909

Pole or Vector? Encoders Capture Bangla Compound Verbs, but LLMs Read Them Literally

Md. Asaduzzaman Shuvo, Md Mehrab Karim Antor, Md. Adnanul Islam, Shahanur Rahman Bappy, Sajid Ahamed, Mahfuz Hasan Reza, Md Delwar Shahadat Deepu

原文摘要

In Bangla, a main verb is often followed by one of a small set of vector verbs. These verbs lose their own meaning and add a shade of meaning instead, such as completion. For example, likhe phello means that someone finished writing, not that they wrote and threw something. The same two verbs can also describe two separate events, so only the context shows which meaning is meant. This makes compound verbs a hard test of how language models handle multiword expressions. We present BanglaCV-Probe, a benchmark of 17 vector verbs with 1,044 minimal pairs, 204 entailment items and 197 pairs of correct and incorrect combinations, all checked by native speakers. We test 26 models (encoders, LLMs and translation systems) on four skills: telling the two meanings apart internally, understanding what a vector adds, preferring correct combinations and keeping the vector's meaning in translation. Probes on five encoders tell the two meanings apart and still reach up to 93% accuracy when trained on pairs without surface cues. Prompted models rarely use this knowledge. Entailment accuracy stays between 59% and 81%. Several LLMs answer Yes or No to almost every item, and nine of ten models miss that someone who ate up the rice left none. Most instruction-tuned LLMs translate vectors literally in 15-20% of vector sentences and in up to 55% for mora (die). On correct combinations, a small Bangla-only model (88%) matches BLOOM-7B1 (87%) and both beat Qwen2.5-7B (74%). Data and code: https://github.com/ashuvo25/Pole_OR_Vector

cs.CL

版本更新 · v2arXiv:2611.00022

Diagnosing Prototype Estimation in Few-Shot Class-Incremental Learning: Training-Free Geometry Selection and Unlabeled-Query Prototype Rectification

Md Tanvir Hossain Saikat, Md Akib Haider, Md. Tahmid Islam Tomal, Md Hasanul Kabir

原文摘要

Frozen visual encoders make prototype heads competitive in few-shot class-incremental learning (FSCIL), but it remains unclear how much of the residual head gap is sensitive to noisy novel-class means rather than to the subsequent changes introduced by classifier refitting. On identical features, we construct a retrospective matched counterfactual: first replace each five-shot novel mean with its complete-data counterpart under fixed cosine scoring, then fit a linear probe. Across sixteen strong encoder dataset pairs, mean replacement accounts for the majority of this ordered gap. Shot and classwise diagnostics support a finite-sample mechanism, whereas a weaker base-only encoder does not satisfy the same criterion. This diagnosis motivates ShrinkSel, a support-only selector over prototype radius and covariance shrinkage whose family contains shared LDA as an exact fallback. Across sixteen evaluated pairs, it improves LDA on fifteen by 0.04-1.52 points and selects the exact LDA endpoint on Aircraft. We further introduce Query Prototype Rectification (QPR), a batch-transductive extension that uses gated unlabeled queries to update novel directions while preserving the selected geometry. On CLIP ViT-B/16, QPR adds 1.21-2.03 points; exact query-wise self-exclusion retains the benefit, showing that the gains do not require self-inclusion. The update repairs scarce novel prototypes at a measurable base-class cost and weakens with plentiful supports or very small cohorts. Thus, the evidence available for prototype estimation is a central constraint in frozen-feature FSCIL.

cs.CV · cs.LG

新论文 · v1arXiv:2611.10908

Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment

Xiaoxiao Li, Ruinan Jin, Lili Meng, Miaosen Wang, Athula Balachandran, Pei Cao

原文摘要

Forensic verification has converged on a binary "real vs. fake" label that confates fully synthetic, tampered, and AI-retouched images despite their very different consequences. We argue that GenAI manipulations decompose along two complementary channels: a camera channel of sensor fingerprints (destroyed by neural processing), and a semantic channel of scene-level coherence (disrupted by content edits). Each manipulation type leaves a distinctive two-channel signature. We instantiate this taxonomy in 2CAP (2-Channel Authenticity Protocol), pairing a contrastively-trained camera encoder with a frozen semantic encoder to serve two applications on a shared backbone: (i) four-class authenticity classification via cross-attention fusion with learnable reliability weights; and (ii) evidence generation, where an authentic image serves as a reference for a query and the two encoders produce per-channel alignment scores together with a patch-level saliency map. These signals are supplied as privileged context to a frozen Vision-Language Model (VLM) through an Observe-Generate-Refine loop, yielding explanations with localization without forensic fine-tuning. On a multi-source benchmark, 2CAP attains the best classification performance, including strong retouching detection where existing methods fail, and improves explanation quality.

cs.CV

版本更新 · v2arXiv:2608.12037

Clustered Randomized Smoothing for Stochastic Prediction Functions

Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann, Jens Kober, Arkady Zgonnikov, Luca Laurenti

原文摘要

Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularly against adversarial perturbations. Yet, in stochastic multi-modal regression settings, randomized smoothing often fails due to mode collapse, yielding averaged predictions that do not reflect the underlying distribution. To address this limitation, we propose clustered $α$-smoothing, a framework that (1) partitions noisy samples using an arbitrary clustering algorithm, (2) applies $α$-smoothing locally within each cluster, and (3) combines the resulting predictions into a mixture distribution. By interpreting the smoothing distribution as a mixture of $α$-smoothers, we derive a lower bound on the probability that the smoothed prediction lies within a union of compact regions corresponding to distinct modes. We empirically evaluate our framework on two benchmarks, demonstrating substantial improvements over state-of-the-art methods. In stochastic trajectory prediction on a driving simulator dataset, our approach achieves, on average, a $27\%$ lower Wasserstein distance to the ground-truth distribution compared to $α$-smoothing. In quadrotor control, where modes correspond to distinct feasible paths to a target, our method reduces the collision rate by $90\%$ relative to the state-of-the-art randomized smoothing.

cs.LG · eess.SY

新论文 · v1arXiv:2611.10906

SCorPion: A Strategic, Controllable and Personified Conversational Companion

Luo Ji, Xiyuan Chen, Dan Wang, Qingqing Gu, Teng Chen, Feixiang Guo, Yetao Wu, Jinxian Qu 等 15 位作者

原文摘要

Fixed prompt-based language models face challenges in open-domain conversations, where versatile topics require different expert advice or demonstrations to maximize their universal performance. Motivated by the dynamic prompt studies in language generation, we extract different chatting strategies from varied forms of text corpus, which steer the language model to different styles based on human principles. We design and deploy a conversational companion called SCorPion, which uses GraphRAG to extract and summarize the knowledge graph globally, yield community-summarized strategies, and produce query-focused optimal strategies. SCorPion has strategic thinking, yields personified and stylized responses, and can be controlled by explicit factors. Code and further results can be found in https://bachozean.github.io/scorpion-page/.

cs.CL

版本更新 · v2arXiv:2602.19458

ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making

Ziyang Guo, Yifan Wu, Jason Hartline, Kenneth Holstein, Jessica Hullman

原文摘要

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to inform a final decision. We propose ComplLLM, a post-training framework based on decision theory that fine-tunes a decision-assistant LLM to output signals that complement existing agent decisions, using complementary information as reward. We validate ComplLLM on synthetic and real-world tasks involving domain experts, demonstrating how the approach recovers known complementary information, produces plausible explanations of complementary signals to support downstream decision-makers, and improves human and LLM agent decision performance in controlled studies.

cs.AI · cs.HC

新论文 · v1arXiv:2611.10903

Quantum synchronizable codes, polynomial and quasi-polynomial shifts

Edgar Martínez-Moro, Miguel de los Ríos de Antonio

原文摘要

Quantum synchronizable codes protect quantum information against Pauli errors and against misalignments of the block boundaries. Almost all known constructions use cyclic codes, because the channel shifts the transmitted block cyclically. We study what happens when the algebraic shift of the code differs from the physical one. When one uses a twisted padding, constacyclic codes synchronize at no cost, and they are the only polycyclic codes with this property for a linear padding. For the other polycyclic codes, we measure the cost of each misaligned position, and we show that the phase damage it causes can be corrected as erasures. Using annihilator duality, we extend the construction to quasi-polycyclic codes, in which the cost is confined to a single block. We prove that the usual quasi-cyclic families have a distance bound that does not grow with the length, and show that quasi-polycyclic codes over repeated-root trinomials overcome it, giving synchronizable codes with larger dimension and distance than the known synchronizable codes of the same length.

cs.IT

版本更新 · v2arXiv:2608.24046

Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment

Zachary Wojtowicz, Michelle Si, Finale Doshi-Velez, Ariel Procaccia

原文摘要

When an AI algorithm makes decisions that affect more than one person, aligning it becomes a problem of social choice: how should people's divergent preferences about system behavior be reconciled and aggregated into a single coherent model? The standard approach to aligning frontier AI models - reinforcement learning from human feedback - largely sidesteps this question and has poor social choice guarantees. However, it remains unclear what alternative should replace it. We show that, when agent utilities can be expressed linearly in a fixed feature representation, the alignment problem can be reformulated as linear optimization over a convex impact space, which makes it amenable to the standard toolkit of welfare economics and mechanism design. This reformulation clarifies how alignment protocols translate into welfare consequences and, conversely, how a social planner's desired constraints on welfare consequences can be translated back into alignment protocols. We apply this transformation to show that voting-by-issues and random-dictatorship mechanisms are strategyproof and unanimous. Demonstrating the reverse direction, we also apply the impact representation to derive a family of alignment protocols that maximize utilitarian social welfare subject to various social desiderata, such as bounds on individual or group harm. We illustrate the welfare implications of these alignment protocols empirically using real human preferences over kidney allocation, charitable food distribution, LLM responses, and trolley problems.

cs.AI

新论文 · v1arXiv:2611.10901

How Short Is Too Short? Length-Conditional Calibration and Abstention for Detecting AI-Generated Text

Ritesh Janga, Justin Zhan

原文摘要

Detectors of AI-generated text are usually tuned and tested on passages of several hundred tokens, yet many real cases are short. We study score-based detection as a function of passage length. We give a closed form for how the false-positive rate of a threshold set on long text changes as length falls, and a formula for the number of tokens a detector needs to reach a target true-positive rate. We calibrate thresholds within length bins with conformal p-values, and we add a bin-level rule that abstains when the detector cannot be informative at that length. On synthetic scores the formulas agree with simulation, and binned calibration holds the false-positive rate at its nominal value at every length. On three zero-shot detectors (log-likelihood, log-rank, Binoculars), three corpora and two open-weight generators, binned calibration gives a mean false-positive rate of 5.0% in every detector-length cell from 10 to 200 tokens, averaged over 300 random document-level resplits. A single threshold set at 200 tokens gives 29% for Binoculars at 10 tokens and about 1% for log-likelihood, as the closed form predicts. No detector reaches an 80% true-positive rate, and the best, Binoculars at 200 tokens, reaches 59%, so the rule abstains in every cell at that floor and releases only the 200-token bins at floors of 0.3 and 0.5.

cs.AI

新论文 · v1arXiv:2611.10898

Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy

Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, Lili Su

原文摘要

Real-world deployment of federated learning (FL) requires resilience against adversarial clients and data privacy. Byzantine fault captures the worst-case behavior of adversarial clients, while differential privacy (DP) provides statistical guarantees against privacy loss. In particular, user-level DP guards a client's entire contribution and provides more realistic protection against information leakage. Despite intensive efforts, the minimax-optimal convergence bound of Byzantine-resilient FL with user-level DP remains open. We establish an information-theoretic lower bound for any Byzantine-resilient empirical risk minimization problem under user-level DP and heterogeneous clients. We propose ByzULDP, a central DP algorithm featuring a two-level momentum across the client and server. Client-side momentum mitigates stochastic gradient variance during robust aggregation. Unlike the fault-free case, naively combining non-linear Byzantine-resilient aggregation with central DP noise can be insufficient to guarantee convergence to a bounded neighborhood of a stationary point. Our key contribution is a server-side momentum that leverages a property specific to user-level DP, where privacy sensitivity depends on how client updates are constructed, to empower convergence. ByzULDP achieves the order-optimal convergence bound for strongly-convex objectives, with vanishing error terms decaying at the optimal $O(1/T)$ and $O(1/\sqrt{T})$ rates for strongly-convex and non-convex objectives, respectively. We corroborate our analysis with numerical experiments on real-world datasets across diverse privacy budgets.

cs.LG · cs.DC · math.OC

新论文 · v1arXiv:2611.10895

Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts

Ahmet Faruk Cetinkaya, Enes Agirman, Cem Tekin

原文摘要

Standard ensemble methods can improve robustness by mitigating individual model stochasticity, but they frequently fail to generalize beyond the training distribution, leaving systems vulnerable to out-of-distribution (OOD) data. We introduce the Robust Satisficing Ensemble (RSE), a scalable probabilistic aggregation framework designed to secure model combinations by minimizing their fragility against distributional changes. By bridging a robust satisficing objective with a quadratic risk surrogate, RSE derives an analytical inner adversary. This fundamental reformulation enables highly efficient weight updates without the computational bottleneck of standard minimax optimization, crucially decoupling optimization complexity from sample size to scale effectively to large datasets. In particular, we prove a geometrically decaying truncation error for the fragility approximation via Lagrange-Burmann expansion and establish stationarity guarantees for RSE. We evaluate RSE across a comprehensive spectrum of distribution shifts, including adversarial label shift (SST-5, TREC), natural subpopulation and temporal shifts (CivilComments, HuffPost). Our results demonstrate that RSE consistently outperforms strong robust baselines, including GroupDRO, IRM, and SRM. These findings establish RSE as a practical, theoretically grounded safeguard for reliable model aggregation in dynamic environments.

cs.LG · cs.AI · stat.ML

版本更新 · v3arXiv:2601.07052

RSLCPP -- Deterministic Simulations Using ROS 2

Simon Sagmeister, Marcel Weinmann, Phillip Pitschi, Markus Lienkamp

原文摘要

Simulation is crucial in real-world robotics, offering safe, scalable, and efficient environments for developing a variety of robotic applications. While the Robot Operating System (ROS) has been widely adopted as the backbone of these robotic applications in both academia and industry, its asynchronous, multi-process design complicates reproducibility, especially across varying hardware platforms. Deterministic callback execution cannot be guaranteed when computation times and communication delays vary. This lack of reproducibility complicates scientific benchmarking and continuous integration, where consistent results are essential. To address this, we present a methodology to create deterministic simulations using ROS 2 nodes. Our ROS Simulation Library for C++ (RSLCPP) implements this approach, enabling existing nodes to be combined into a simulation routine that yields reproducible results usually without requiring any source code changes. We demonstrate that our approach produces identical results across various CPUs and architectures when testing both a synthetic benchmark and a real-world robotics system. RSLCPP is open-sourced at https://github.com/TUMFTM/rslcpp.

cs.RO

新论文 · v1arXiv:2611.10894

Zero-Shot VLA Adaptation with Retrieved Guidance

Subin Kim, Anh-Quan Pham, Dinesh Jayaraman

原文摘要

Pre-training large parametric "Vision-Language-Action" (VLA) models on large demonstration datasets has recently yielded promising results for general-purpose manipulation. However, these models still struggle under even small domain shifts relative to the training data, such as changes in camera viewpoint, background, object identity, or robot morphology. Motivated by the success of Retrieval-Augmented Generation (RAG) in language models, we pursue retrieval to boost VLA performance. Specifically, we seek to leverage retrieval from domain-mismatched, "in-the-wild" demonstration datasets like DROID to guide a VLA's behavior in a new target domain. To achieve this, we introduce RAGu, which overcomes robotics-specific challenges for RAG: (1) It incorporates simple geometric calibration to transform source demonstrations into the target setup and reduce cross-domain differences. (2) It uses a coarse-to-fine retrieval strategy that selects, from a large pool of pre-warped candidates, the trajectory most compatible with the base VLA. (3) It guides the VLA's flow-matching inference procedure rather than seeking to retrain the base model or expand its limited context window. We evaluate RAGu across real-world, simulation, sim-to-real transfer, and cross-embodiment humanoid manipulation. We find it improves real-world VLA success rates from 20% to 80% and outperforms the closest-related baselines in sim. Project website: raguvla.github.io

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.10893

Complementarity without ground truth?

Andrea Ferrario, Alessandro Facchini, Federico Cabitza

原文摘要

Human-AI complementarity captures the idea that a human assisted by an AI system can outperform both the human and the AI acting alone. In prediction tasks, this improvement is assessed against ground truth labels produced through a reference construction procedure and intended to represent the state of affairs to be predicted. Many human-AI interactions, including those where medical AI provides treatment recommendations, however, concern tasks other than predicting what obtains. Their relevant output concerns adequacy relative to a practical goal and depends on several evaluative dimensions. In this work, we examine the ground truth dependence of complementarity and extend it to human-AI interactions where ground truth is not the appropriate reference. We show that tasks beyond prediction can still admit a reference construction procedure that generates adequacy labels. We develop a route for extending complementarity to such settings. It replaces ground truth labels with context-dependent adequacy labels generated through a two-step scoring methodology inspired by multi-criteria decision analysis frameworks in healthcare and it makes the normative choices underlying reference construction explicit. Because the construction of adequacy labels embeds evaluative choices, we draw methodological inspiration from computational reliabilism to identify technical, scientific, and social factors relevant to supporting their construction. Our approach expands the empirical study of human-AI complementarity beyond prediction tasks, enabling its quantitative evaluation in decision-support settings where ground truth is not the appropriate evaluative reference.

cs.AI · cs.HC

新论文 · v1arXiv:2611.10891

Approximate Recall, Approximate Forecasts: Recall as a Diagnostic for LLM Forecasting Errors

Prashanth Bhaskara, Shubhaankar Gupta, Seojoon Yeon

原文摘要

Large Language Models (LLMs) exhibit approximate recall: they retain coarse associations about past events while losing fidelity on specific details. Past research on LLMs has quantified different models' forecasting ability in real-world events using prediction markets, but has not studied how losing said fidelity impacts their forecasting abilities. For example: while an LLM correctly recalls that the answer to: ''Did Anna Sawai win the Best Drama Actress in the 76th Emmy Awards?'' is ''Yes,'' it incorrectly states the event date as September 22 rather than September 15. In this paper, we introduce a novel metric called the Recall Fidelity Score to study how imprecision in internalized knowledge propagates to forecasting capability on future events. On resolved historical markets, we find that higher local recall fidelity around semantically similar past events predicts lower forecasting error on resolved markets, and the same signal predicts smaller distance from open markets prices.

cs.AI · cs.CE · cs.LG

新论文 · v1arXiv:2611.10886

The one-step surface-air lag in the EnergyPlus zone heat balance: order of accuracy, correction and consequences

Wooyoung Jung

原文摘要

The order of accuracy sets how fast numerical error falls as the timestep shortens. This study measured that order for the zone heat balance of EnergyPlus 26.2 against exact or converged references and tested a correction on 45 U.S. Department of Energy prototype cases. All three zone air formulas, the third-order default included, give first order or lower, because the surfaces use the previous timestep's air temperature. Solving surfaces, air and HVAC to agreement within each timestep raises the default to about second order, and in a room with an exact solution two extra passes cut the error eightfold at 1.65 times the runtime. In the prototype cases, the correction changed annual site energy by at most 0.45% but an outpatient clinic's heating by 5.1%. Window-upgrade savings changed by 10% or more in 13 of the 34 applicable cases, about as often as under a change of timestep.

cs.CE

版本更新 · v2arXiv:2611.07482

SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards

Yichen Sun, Qirui Liu, Yan Wang, Jianan Lin, Linbo Jiang, Shiyu Wang, Zhibo Wang, Zhixuan Chu

原文摘要

Large Reasoning Models (LRMs) have achieved impressive performance via explicit Chain-of-Thought (CoT) reasoning, yet this process introduces critical safety risks. We formalize LRM safety objectives as requiring non-malicious reasoning and answers, safety consistency, and explicit intent identification. We argue that existing alignment methods suffer from poor adversarial generalization, a significant ``safety tax'' on reasoning, and unfaithful coarse-grained rewards, primarily due to their neglect of the LRM's intrinsic reasoning capabilities for safety. To address these, we propose \textbf{SAVeR$^2$}, a novel \textbf{S}afety \textbf{A}lignment method via \textbf{R}ewards with \textbf{R}easoning capability. SAVeR$^2$ decomposes the safety objective into four fine-grained verifiable reward signals and utilizes a difficulty-aware data selection strategy to stabilize training. Crucially, we introduce a reasoning-preserving gradient projection mechanism that analytically resolves conflicts between safety and reasoning gradients, effectively eliminating the safety tax. Extensive experiments on models ranging from 1.5B to 671B demonstrate that SAVeR$^2$ achieves superior safety performance and significantly lower over-refusal rates across multiple benchmarks without compromising general reasoning capabilities.

cs.AI

新论文 · v1arXiv:2611.10884

Keeping LLM Agents on Procedure: Executable Finite-State Control for Long-Horizon Instruction Fidelity

Yutao Sun, Haokun Li, Mingshuai Chen, Guanyan Li, Zhongyi Wang, Shengchao Qin, Jianwei Yin

原文摘要

Much of the automation handed to language-model agents is procedural: each step needs little intelligence, but a long unattended run must follow a skill or SOP stated once at the start. We show that agents drift from such procedures over long runs, and that restating the instructions or resuming a stopped agent only moves the drift to another shortcut. We study an executable finite-state machine (FSM) that keeps the workflow state outside the model's context and enforces it at three points: tool calls, state transitions and the end of the agent's turn. In a pre-registered experiment on 200-account SOP-Bench batches, Claude Haiku 4.5 with the FSM decided on average 139 accounts correctly and by the procedure, against 48 for the strongest baseline (95% CI of the difference [46, 130]), and kept this rate to the end; across three models, the gain tracked how much the plain agent drifted. Because the runtime, not the model, supplies this long-horizon reliability, the FSM can let small models carry procedural work: Haiku 4.5 with it averaged more such decisions than plain Claude Sonnet 4.6 at 38% of the cost. Analyses on SWE-bench Verified, $τ^2$-bench, and staged and cross-context workflows further suggest that reliable long-horizon automation can come from stronger execution control, not only stronger models.

cs.AI

新论文 · v1arXiv:2611.10882

Guiding future global temperature distributions with simulations and observations

Francesco Immorlano, Elijah Tavares, Felix Draxler, Juan Nathaniel, Violette Launeau, Duncan Watson-Parris, Padhraic Smyth, Pierre Gentine 等 9 位作者

原文摘要

Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes. Climate simulations are costly and biased, while correcting them toward observations risks suppressing inter-model differences. We train a single machine-learning emulator, a conditional diffusion model, on seventeen CMIP6 models and ERA5 reanalysis to generate spatially coherent daily temperature fields conditioned on model identity, date, and CO2-equivalent concentration. At sampling time, diffusion guidance reduces model biases by steering each emulated climate-model distribution toward observations, with its strength selected through perfect-model experiments using withheld simulated futures. Observational influence decreases with projection horizon and forcing. Across seventeen synthetic targets, guidance more than halves median biases in the 1st and 99th percentiles of daily temperature, improves probabilistic scores and reliability, and reduces median annual global-mean temperature RMSE by 32-57% across three emission scenarios. In a detailed benchmark, guidance also outperforms established bias corrections on daily-field probabilistic scores. Efficient sampling generates large ensembles without further climate simulations. For example, our framework corrects CMIP6's roughly threefold historical overestimate of extreme-heat coverage, yet projects that concurrent extremes will affect nearly half of global land on a typical day in the 2080s under SSP3-7.0.

physics.ao-ph · cs.LG

新论文 · v1arXiv:2611.10881

Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration

Juncheol Shin, Byeongho Yu, Semin Kim, Eunhyeok Park

原文摘要

Continual model merging incrementally integrates task-specific models without revisiting past models or data. However, repeated merging entangles past task components and distorts their singular geometry, making balanced task-wise allocation increasingly difficult. We propose Global Singular Subspace Separation and Restoration (GS3R), which augments the merged update with a compact restoration state. At each merge, GS3R restores the retained singular geometry, separates task-wise subspaces, and globally reallocates the available rank across tasks fairly. To reduce merging-time memory overhead, we further introduce Pre-merge Restoration and Flushing (PRF). Experiments on vision, NLP, and multimodal benchmarks show that GS3R provides a strong accuracy-efficiency trade-off.

cs.LG

版本更新 · v3arXiv:2511.08475

Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale

Yangxiao Cai, Ruiyin Li, Peng Liang, Mojtaba Shahin, Zengyang Li, Aldeida Aleti, Chenxing Zhong

原文摘要

As the complexity of Software Engineering (SE) tasks continues to escalate, Multi-Agent Systems (MASs) have emerged as a focal point of research and practice due to their autonomy and scalability. Furthermore, through leveraging the reasoning and planning capabilities of Large Language Models (LLMs), the application of LLM-based MASs in the field of SE is garnering increasing attention. However, there is no dedicated study that systematically explores the design of LLM-based MASs, including the Quality Attributes (QAs) on which designers mainly focus, the design patterns used by designers, and the rationale guiding the design of LLM-based MASs for SE tasks. To this end, we conducted a study to identify the QAs that LLM-based MASs for SE tasks focus on, the design patterns used in the MASs, and the design rationale for the MASs. We collected 106 papers on LLM-based MASs for SE tasks as the source. Our study shows that: (1) Code Generation is the most common SE task solved by LLM-based MASs among ten identified SE tasks, (2) Functional Suitability is the QA on which designers of LLM-based MASs pay the most attention, (3) Role-Based Cooperation is the design pattern most frequently employed among 16 patterns used to construct LLM-based MASs, and (4) Improving the Quality of Generated Code is the most common rationale behind the design of LLM-based MASs. Building on the study results, we presented the implications for the design of LLM-based MASs to support SE tasks.

cs.SE · cs.AI

版本更新 · v2arXiv:2611.07658

ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation

Minh Canh Tu, Quang-Binh Nguyen, Khoi Nguyen

原文摘要

Articulated 3D assets are essential for robotic simulation and training, yet their generation from casual images poses a key challenge: recovering part geometry and kinematics that remain mutually consistent. We present ArtCrafter, a novel feed-forward generative model for controllable generation of articulated 3D objects from a pair of images, one depicting the object in the rest state and the other in the open state. At the core of ArtCrafter is a DiT-based generative model that jointly produces part-level meshes for both articulation states in a single forward pass. Inspired by Slot Attention, its denoising process operates on a $1+2N$ slot layout comprising one shared base slot and $N$ paired rest/open slots, encouraging each pair to bind to the same kinematic part. To ensure geometrically consistent and disjoint part generation, we introduce Triplet Attention to enforce cross-state geometric consistency between paired rest/open slots anchored through the shared base slot, and a repulsion loss $\mathcal{L}_{\mathrm{rep}}$ on decoded part point clouds to prevent inter-part penetration throughout denoising. Given the resulting paired meshes, URDF joint parameters---type, axis, origin, and range---are derived analytically from the rigid transformation between each rest/open pair, providing an interpretable alternative to learned joint-parameter regression. Extensive experiments on both in-distribution and out-of-distribution datasets demonstrate that ArtCrafter outperforms existing method under the same dual-state setting in geometry quality and articulation precision, while remaining competitive with methods operating under different input settings and paradigms.

cs.CV

版本更新 · v3arXiv:2610.14099

Symmetric, rational and infinitely many $(23_4)$ configurations, and the end of the existence problem for geometric $(n_4)$ configurations

Wenhao Lu

原文摘要

A geometric $(n_4)$ configuration is a set of $n$ points and $n$ lines in the real projective plane such that every point lies on exactly four of the lines and every line contains exactly four of the points. The question of which $n$ admit such a configuration was posed by Grünbaum in 2000, and successive work of Bokowski, Grünbaum, Schewe, Pilaud and Cuntz settled every case but $n=23$. We settle this last case by bounding the symmetry of such configurations and classifying the most symmetric ones exactly. We prove that for every prime $n\equiv3\pmod4$ the group of projective symmetries of a geometric $(n_4)$ configuration has order at most four, explaining why symmetric constructions failed at $n=23$, and the same argument bounds the symmetry of $(n_5)$ configurations for primes $n\not\equiv1\pmod5$. Reducing the Klein four-group case to 4021 bilinear polynomial systems and solving all of them exactly with Gröbner bases, we show that exactly two $(23_4)$ configurations reach this bound up to projective equivalence and that there are no others even over $\mathbb{C}$. Both are self-polar; the first has integer coordinates and the second is defined over $\mathbb{Q}(\sqrt{17})$ but not over $\mathbb{Q}$. Consequently geometric $(n_4)$ configurations exist if and only if $n\ge18$ and $n\ne19$. The same classification recovers Cuntz's $(22_4)$ and $(26_4)$ configurations and finds three new combinatorial types at $n=22$ and $94$ at $n=26$. Among self-polar $(23_4)$ configurations with a single involution we find $50$ more, defined over number fields of degree at most $7$. Four of them deform in one-parameter families, and computing three of these exactly, one birational to the modular curve $X_1(11)$, we prove that there are infinitely many geometric $(23_4)$ configurations, among them infinitely many with rational coordinates that are self-polar and have no projective symmetry.

math.CO · cs.CG · cs.DM

新论文 · v1arXiv:2611.10877

Sampling-based Model Predictive Control as Sequential Monte Carlo Inference

Austin Garrett, Muyang Yan, Zachary Kingston

原文摘要

Sampling-based model predictive control (MPC) is treated as a family of distinct algorithms: predictive sampling, MPPI, the cross-entropy method, and their biased, colored-noise, and annealed variants all sample control sequences and reweight them by cost. We show a single Sequential Monte Carlo (SMC) inference algorithm implements them all, specified by three independent axes: the proposal, the update rule that reduces cost-weighted particles to a nominal plan, and the effective-sample-size threshold for resampling. We evaluate SMC-based planning on MuJoCo non-linear control, open-loop navigation through obstacle fields, 7-DoF motion planning, and non-prehensile push-T, in simulation and on a Franka FR3. Resampling combats particle degeneracy at long horizons. At a 28-knot horizon in our navigation domain it cut the collision rate by 30% over non-resampling baselines. Programmable proposals improve push-T success over perturbative baselines, improving from 1% to 100% in simulation and 10% to 90% on hardware.

cs.RO · cs.LG · eess.SY