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
+63已有论文修订
+93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 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 21:05 — 2026-11-16 21:05(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 13:44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6,921 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)
版本更新 · v3arXiv:2605.07384

StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models

Panqi Chen, Yifan Sun, Shikai Fang, Xiao Fu, Lei Cheng

原文摘要

Inferring the evolution of high-dimensional and multi-modal (e.g., spatio-temporal) physical fields from irregular sparse measurements in real time is a fundamental challenge in science and engineering. Existing approaches, including diffusion-based generative models and functional tensor methods, typically operate in offline settings, depend on full temporal observations, or incur substantial inference cost. We propose StreamPhy, an end-to-end framework that enables efficient and accurate streaming inference of full-field physical dynamics from incoming irregular sparse measurements. The framework integrates a data-adaptive observation encoder that is robust to arbitrary observation patterns, a structured state-space model that supports memory-efficient online updates across irregular time intervals, and an expressive Functional Tensor Feature-wise Linear Modulation (FT-FiLM) decoder for continuous-field generation. We prove that FT-FiLM is more expressive than the functional Tucker model, admitting a richer function class for handling complex dynamics. Experiments on three representative physical systems under challenging sampling patterns show that StreamPhy consistently outperforms state-of-the-art baselines, with at least 48\% improvement in accuracy and up to 20--100X faster inference than diffusion-based methods.

cs.LG

新论文 · v1arXiv:2611.01602

When Does Sparse Routing Help? The Geometry of Expert Separation in Mixture of Experts

Huy Nguyen, Dung Le, Alessandro Rinaldo, Nhat Ho

原文摘要

Sparse mixtures of experts combine multiple prediction models while evaluating only a small subset for each input. Although this architecture reduces computation, how expert separation and routing sparsity jointly govern expert recovery remains an open problem. In this paper, we address this question for location Gaussian mixtures of experts with a fixed number of experts by establishing how expert separation and spatial arrangement determine recovery rates. For dense models, our results reveal that when experts form well-separated clusters, the separation geometry is governed by the size of the largest cluster; without a prescribed cluster structure, this geometry is instead driven by the total number of experts. For sparse models, the separation geometry on retained routing regions is determined by the number of active experts, while the contribution of omitted regions is controlled by their total probability. Consequently, activating fewer experts reduces the separation complexity in these bounds. Furthermore, Top-1 routing yields a particularly striking result: experts can be recovered at a rate independent of the separation quantity. Our technical approach combines polynomial interpolation and Gaussian reproducing-kernel Hilbert space (RKHS) test functions with quantitative restriction inequalities that extend pointwise comparisons to expert functions.

stat.ML · cs.LG

新论文 · v1arXiv:2611.01601

Accurate automated photo-identification of Near Eastern and European fire salamanders

Maayan Yesharim, Hava Goldstein, Gabi Kolodny, Assaf Ben-Levy, Tamar Kis-Papo, Dor Gavish, Rotem Vidan, Nirit Lavie-Alon 等 10 位作者

原文摘要

Photo-identification underpins non-invasive capture-recapture monitoring of amphibians, but manual identification becomes slow and error-prone as reference libraries grow. Focusing on the Near Eastern fire salamander (Salamandra infraimmaculata), we developed a pipeline based on zero-shot local-feature matching (SuperPoint and LightGlue) without species-specific training and evaluated it on $2{,}440$ field photographs from Haifa and Tel Dan in northern Israel. We isolated the yellow spot pattern, scored image similarity by the number of high-confidence keypoint matches, which reduced a confound whereby many-spotted individuals accumulate spurious matches, and assigned identities across the database by two-tier clustering. Pipeline-assisted expert review corrected misidentifications, reducing the number of identities by almost a quarter. On held-out individuals, the pipeline ranked the correct individual first for $95.2\%$ of queries and recovered identities with an ARI of $0.958$. Without modification, it reached $95.1\%$ and $91.7\%$ top-1 accuracy on two datasets of the European fire salamander (Salamandra salamandra) and recognised $93.7\%$ of recaptures in one of them, compared with $38$-$77\%$ for five established programs and $93.9\%$ for visual inspection. Zero-shot local-feature matching thus offers amphibian monitoring a re-identification tool that needs no training data, transfers between related species, scales to databases of over a thousand individuals, and can audit existing databases before capture-recapture analysis.

cs.CV · q-bio.QM

新论文 · v1arXiv:2611.01600

SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts

Amir Hossain Raj, Xuesu Xiao

原文摘要

Robots manipulating in cluttered spaces must often plan from partial views where foreground objects occlude the target, surrounding geometry, and usable free space. Reactive policies often miss these hidden constraints, while exhaustive search becomes computationally prohibitive in dense clutter. We present SCOUT, an occlusion-aware planning framework that bridges high-level deliberation with grounded physical rollouts. SCOUT leverages an object-centric scene representation to reconstruct hidden geometry and derive a relational planning state capturing blocker hierarchies and accessibility corridors. To navigate the vast action space in clutter, an LLM proposes structured action candidates which are then rigorously evaluated via Monte Carlo Tree Search (MCTS) using a learned action-conditioned world model. Evaluations on 'Reveal' and 'Placement' tasks show that SCOUT outperforms Vision-Language-Action (VLA) policies, embodied agents, and 3D world models, with significant gains in long-horizon tasks requiring reasoning over occluded geometry. We further validate the framework's robustness through real-world robotic manipulation in a cluttered shelf environment.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.01599

Fresh-Priority Eviction for Cuckoo Filters: Exploiting Latent Randomness Under XOR Hashing

Min Liu

原文摘要

Cuckoo filters are a widely adopted approximate membership query (AMQ) data structure that supports insertions, lookups, and deletions with low memory overhead. At high load factors, however, insertion performance degrades sharply due to the random-walk eviction process, which may require a large number of element relocations. Recent work on bucketized cuckoo hash tables has shown that \emph{fresh-priority eviction}, which preferentially evicts elements whose alternate bucket location has not yet been used, achieves $O(\ell m)$ total expected evictions for bucket size~$\ell$, an improvement over the standard random walk. In this paper, we show that this technique transfers to \emph{cuckoo filters} despite their use of XOR-based partial-key hashing. The key insight is that a fresh element's fingerprint, although stored in the table, is not examined by the eviction policy, so when the fingerprint length satisfies $k = Ω(\log m)$, the alternate bucket hash remains a near-uniform random variable, a property we call \emph{latent randomness}. We prove that under this condition the corruption graph remains subcritical and the total number of evictions is $O(\ell m \log m)$; we conjecture the tighter $O(\ell m)$ bound holds via the full amortized analysis of Bell and Kuszmaul. We further propose encoding the fresh/kicked state implicitly by the element's position within its bucket, requiring no additional per-element metadata. Experimental results on a filter with $2^{22}$ slots and $8$-bit fingerprints demonstrate $1.2\times$ to $2.4\times$ fewer evictions at load factors between $94\%$ and $99\%$ for bucket size $\ell = 8$, and a $1.73\times$ reduction in cumulative evictions to full capacity.

cs.DS

新论文 · v1arXiv:2611.01598

QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board

Ayushman Bhattacharya, Anwesha Chakraborty

原文摘要

Heterogeneous embedded boards pair a Linux application processor with a real-time microcontroller (MCU), which suggests moving a task between the two domains when its timing degrades. We present QFabric, a prototype that treats cross-domain placement as guarded recovery from a violated empirical soft real-time contract: a bounded task is compiled for both domains, monitored in windows with hysteresis, switched only after semantic and capacity admission at a quiescent epoch boundary, and committed or rolled back after probation. On an Arduino UNO Q (Cortex-A53 Linux and a Cortex-M33 running Zephyr), we characterize the stock Bridge RPC interconnect and measure five workloads in both domains under idle, CPU-load, and higher-priority SCHED_FIFO contention, with ordinary and real-time callers. Each MCU invocation costs about 19 ms of dispatch regardless of compute, the MCU runs the heaviest kernel 34x slower, and because every call traverses Linux userspace, Linux contention inflates the MCU path far more than the Linux path (p99 up to 400 ms versus 17.0 ms). Across 30 cells of a four-node chain, Linux meets every contract within 0.8% misses and QFabric correctly never migrates; a controller without hysteresis migrates in 7 cells, raising p95 by up to 177x, and probation rolls back 5 of those moves. On Linux-dispatched heterogeneous boards, migration therefore cannot isolate a task from Linux interference, and recovery guards matter chiefly by preventing harmful moves. This paper supersedes an earlier artifact release whose reported improvement arose from measurement defects that we identify. All source, raw traces, and generators are public.

cs.AR · cs.OS · eess.SY

新论文 · v1arXiv:2611.01594

Autoencoder Based Deep Clustering of Point Clouds

Nader Alfares, Guangmingmei Yang, David J. Miller, George Kesidis

原文摘要

Motivated by a problem in Generative Specification-Producing AIs (SPAIs), we focus on a problem of deep clustering of three-dimensional shapes specified by point clouds. After reviewing clustering and deep clustering, we study the fully unsupervised pipeline in which a FoldingNet autoencoder is first trained for reconstruction and then K-means++ is then applied to the resulting codewords. We report clustering accuracy (ACC), normalized mutual information (NMI) and adjusted Rand index (ARI) on ModelNet10 and ModelNet40 datasets, as a function of the number of clusters K. We also provide t-SNE visualizations of the codewords, and discuss the choice of K.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01590

6G Uplink Waveform and Rank Selection under Distributed Reception

Yewen Cao, Fen Hou, Yulin Shao

原文摘要

The development of 6G uplink is expanding waveform and spatial transmission options, while distributed reception makes their relative merits depend on the spatial and frequency structure of the aggregate channel. We study the joint selection of cyclic prefix orthogonal frequency-division multiplexing and discrete Fourier transform spread OFDM at rank 1 and noncoherent rank 2 under common user equipment power constraints and centralized linear minimum mean-square error reception. We derive waveform switching thresholds at both ranks and a rank selection margin, establishing conditions for selecting among the four modes based on available transmit power, DFT despreading loss, and spatial multiplexing gain. We then characterize how port gains and correlations at individual access points (APs) form aggregate spatial separation and influence mode selection. At fixed port gains and available transmit powers, improving spatial separation without reducing it on any subcarrier increases the rank selection margin, while its effect on the preferred waveform within rank 2 depends on the frequency distribution of the improvement. Numerical results show that different AP deployments can favor different waveforms and ranks, even with the same receive antenna budget and comparable aggregate channel gains, including waveform switches at a fixed preferred rank.

cs.IT · eess.SP

新论文 · v1arXiv:2611.01587

Attack Patterns in Cross-chain Bridges: A Trust-based Empirical Analysis

Ishraq Samiha, Yasir Rahman, Rahma Mukta

原文摘要

The rapid growth of multiple blockchain ecosystems has made cross-chain bridges essential for transferring assets and information across independent blockchains. Their multi-component architectures, cross-chain trust assumptions, and concentration of valuable assets expose them to diverse security threats. This paper presents an empirical study of cross-chain bridge attacks based on 48 evidence-supported real-world incidents from January 2022 to August 2026. We propose a behaviour-based attack pattern architecture comprising six trust-violation attack patterns, each defined by the primary trust assumption violated by the attacker: Proof Forgery,Logic Exploitation, Event Injection, Economic-State Manipulation, Credential Seizure, and Infrastructure Hijacking. The architecture further maps these patterns to five functional domains of cross-chain bridges: Deposit, Relay, Verification, Execution, and Governance and Operations, separating how a trust assumption is violated from where the compromised trust boundary lies. The 48 incidents correspond to $2.676 billion in gross bridge-specific losses, with the ten largest incidents accounting for 92.4% of total losses. Measured on the primary loss basis, Proof Forgery and Credential Seizure make up 86.2% of all losses, and the Verification and Governance and Operations domains hold 93.9%. A handful of very large incidents drives this concentration, yet it still holds when we switch to other loss bases or reclassify the boundary cases. By tying what attackers do to the bridge functions and security assumptions they target, the architecture gives threat modelling for cross-chain bridges an empirical footing.

cs.CR

新论文 · v1arXiv:2611.01585

StateGate: A Behavioral-Fidelity Prompt Optimization Method for Long-Chain LLM Agents

Shicheng Huang, Cai Fu, Jianqiang Lyu, Yifan Zhang, Xianmao Ji

原文摘要

Currently, long-chain LLM agents commonly suffer from behavioral degradation in complex tasks, where prompts are written in full but steps are not executed in full. To address this issue, existing approaches face three major challenges. First, constraints are strongly bound to their textual carriers; once natural-language constraint sentences are removed, their binding force vanishes. Second, the execution process lacks independent verification, as the evidence for judgment is often supplied by the executing party itself, leading to the failure of self-referential validation. Third, existing remediation schemes are difficult to generalize, and hard-coded mechanisms cannot be transferred across tasks. In this paper, we propose StateGate, a novel prompt-optimization scheme that transforms semantic constraints into symbolic gates enforced by an external deterministic runtime. By decoupling the content of a constraint from its carrier of efficacy, StateGate achieves behavioral fidelity in long-chain tasks without losing the binding force of the prompt. Specifically, we first propose four independent compression strategies (deduplication, generalization, externalization, and text-to-gating) together with their corresponding decision chains, enabling principled prompt symbolization. Second, we design a three-component architecture consisting of a state file, a validator, and an orchestrator, which thoroughly separates judgment authority from execution authority. Third, we formally prove that the compliance of symbolic constraints is independent of context size. Finally, we validate the framework on a vulnerability-discovery task in the security domain; the results show that StateGate achieves 100% execution closure and accurate vulnerability detection.

cs.CR

新论文 · v1arXiv:2611.01584

Smoothed analysis of stability radii for the assignment problem

Michael P. Friedlander

原文摘要

Every linear program can tolerate small changes to its costs and still yield a solution of the original problem. The size of this tolerance measures how robust an optimal decision is to noise or numerical error, and how much regularization the problem can support. Classical sensitivity analysis can determine this tolerance only from an optimal solution. This paper provides a priori lower bounds on two measures of this tolerance -- the optimality gap and the $\infty$-norm stability radius -- for the $n$-by-$n$ linear assignment problem over the Birkhoff polytope. The bounds derive from a smoothed analysis, which adds Gaussian noise with standard deviation of at least $σ$ in every direction to an arbitrary base cost. At every fixed confidence level, uniformly over the base cost, both quantities are at least of order $σ/(n\sqrt{\log n})$. The radius bound is asymptotically sharp. Under isotropic noise, the worst case occurs when every assignment has equal cost, and in this case, a scaled stability radius converges in distribution to a standard exponential variable.

math.OC · cs.DS · math.PR

版本更新 · v2arXiv:2609.05345

Moral Advice as Interactional Negotiation: Framing, User Pressure, and Social Position in Large Language Model Responses

Minne Chen, Yourong Yao

原文摘要

As conversational AI becomes a source of everyday guidance, LLMs increasingly participate in the interpretation and legitimation of morally contested choices. We examine LLM moral advice as an interactional negotiation shaped by framing, sustained user pressure, and the moral subject's social position. Using GPT-4o-mini as an illustrative case, we conducted a factorial vignette experiment with a pre-specified three-round protocol. The model received eldercare dilemmas that varied in framing and persona, followed by two user challenges. We analyzed 1,620 configuration-framing cells, each repeated three times, yielding 4,860 conversational runs. Caregiving affirmation produced near-uniform endorsement, whereas non-caregiving framing produced more variable baseline stances. When users challenged caregiving endorsement, 90.1% of configurations shifted after one round. Non-caregiving framing produced more resistant and unstable trajectories. Never (27.9%) and Late (25.6%) accommodations were more common than Early accommodations (16.5%), and only 14.32% of configurations achieved perfect trajectory consistency, compared with 62.72% under caregiving framing. Advice also varied with social position. Female personas received more support for non-caregiving decisions, while the presence of sisters increased accommodation. The GPT-4o-mini case shows that LLM moral advice can develop through a partially stable negotiation between normative response tendencies and user pressure rather than express a fixed ethical framework. The framework and design support comparative research across models and moral domains. Such instability raises social, ethical, and technical concerns, as users may treat advice that is difficult to scrutinize as objective.

cs.CY

新论文 · v1arXiv:2611.01583

Second-Order Asymptotics for the Scalar Gaussian Broadcast Channel

Vincent Y. F. Tan

原文摘要

This paper characterizes the second-order coding region of the scalar Gaussian broadcast channel along the curved boundary of its capacity region. The characterization holds under both average and maximal error criteria and allows correlation between the receiver noises. At each interior point of this boundary, the second-order region is a halfspace, as in the work of Scarlett and the author on Gaussian multiple-access channels with degraded message sets. Achievability follows from spherical superposition coding with a blocklength-dependent power allocation. The main innovation lies in the converse. Using Ornstein--Uhlenbeck entropy dissipation and Gaussian functional inequalities, we construct an auxiliary observation through an additive Gaussian noise channel and establish quantitative relative entropy bounds for the channel output distributions conditioned on this observation. The strong functional representation lemma of Li and El Gamal then allows us to select a realization of its independent random seed to obtain a deterministic partition of the retained receiver-1 message set. The component label plays a role analogous to the auxiliary random variable in the capacity characterization, while providing the distributional control needed at the second-order scale. These properties guide the construction of auxiliary output measures whose likelihood ratios admit the cancellations and normal approximation needed to evaluate an information spectrum converse.

cs.IT

新论文 · v1arXiv:2611.01582

Measuring User Success in Randomized Search Experiments: Interpreting Good Abandonment in Generative AI Search

Minha Hwang, Shavak Agrawal, David Chen, Carto Wong, Xin Du, Tiannan Wang, Georg Buscher, Zheng Chen

原文摘要

Randomized search experiments increasingly evaluate experiences in which large language models answer information needs directly on the results page. Click status alone cannot identify success: a click may lead to an unsatisfactory result, while no click may indicate successful answer consumption, or "good abandonment." Prior research has shown that good abandonment is difficult to detect because dwell, scrolling, and reformulation are meaningful only in context. We present Session Success Rate (SSR), a human-grounded, interpretable outcome metric designed for online controlled experiments. Trained judges label complete session experiences using privacy-protected interaction evidence and video recordings; these offline labels train models scored online from query events, viewport behavior, result-page interactions, and semantic reformulations. Out-of-sample evaluation on 6,904 labeled queries yields 0.75 balanced accuracy overall and 0.68 within abandoned queries; session-level balanced accuracy is 0.68. The sample shows why interaction status is not an adequate outcome: 53.2% of abandonments were successful and 6.5% of clicked queries were unsuccessful. In a validation portfolio of seven ranking and five non-ranking experiments, SSR agreed with Sessions per User in seven cases, was inconclusive in four, and disagreed in one under a common p < 0.05 rule. Separately, across approximately 4,000 production experiments, SSR produced about 2.5 times the binary sensitivity of Sessions per User; in the studied workflow, this supported lower traffic allocations and greater experiment throughput under a fixed traffic budget.

cs.IR

版本更新 · v2arXiv:2610.39564

Constant-Factor Approximation for Non-Splitting Coflow Scheduling in Heterogeneous Parallel Networks via Iterative Relaxation

Chi-Yeh Chen

原文摘要

Coflows capture the collective communication requirements of data-parallel applications, and scheduling them well is essential to the performance of modern data centers. We study non-splitting coflow scheduling in a heterogeneous parallel network whose $m$ network cores may be Electronic Packet Switches (EPS), not-all-stop Optical Circuit Switches (OCS), or all-stop OCS, where every flow must be transmitted entirely through a single core. Previous approximation algorithms for this setting have guarantees that grow linearly with the number of cores $m$ or with the maximum flow degree $τ$ of a port, and therefore become weak as data centers deploy more cores. The source of this dependence is the rounding step: rounding each flow to the core holding its largest fractional value can inflate the load of a port by a factor of $m$. We replace this step with an iterative relaxation rounding scheme that handles the input-port and output-port capacity constraints simultaneously. For minimizing the makespan, this yields approximation ratios of $\min\{τ, 3\}$, $2\min\{τ, 3\}$, and $4\min\{τ, 3\}$ for pure EPS, pure not-all-stop OCS, and pure all-stop OCS networks, respectively. For minimizing the total weighted coflow completion time, we obtain approximation ratios of $8\min\{τ, 4\}$, $16\min\{τ, 4\}$, and $32\min\{τ, 4\}$ for the same three architectures. In a hybrid network, the guarantee is governed by the weakest architecture present, so the overall ratios are at most $4\min\{τ,3\}\le 12$ and $32\min\{τ,4\}\le 128$, respectively. Unlike all previous guarantees for non-splitting coflow scheduling in heterogeneous parallel networks, these bounds are absolute constants that do not grow with the number of cores $m$ or with the flow degree $τ$. We also show that the integrality gap of the underlying linear program is at least $2$.

cs.DS

新论文 · v1arXiv:2611.01581

Recursive Self-Improvement of Exoskeleton Assistance Policies through Human-in-the-Loop Feedback

Muyuan Ma, Shuo Jiang, Lijun Han, Xinpan Meng, Zhenghua Ma, Xiuze Xia, Houcheng Li, Long Cheng

原文摘要

To reduce reliance on manual design and extensive parameter tuning, a framework for the autonomous evolution of exoskeleton assistance policies through human feedback is proposed. Assistance policies are autonomously generated as executable control code by an intelligent agent and evaluated in experiments with human participants. Subjective user feedback, movement performance, and muscle activation measurements are incorporated into policy assessment. Based on these assessments, policy deficiencies are autonomously identified and the control code is revised by the agent for subsequent trials. A closed loop of policy generation, human feedback, evaluation, and autonomous refinement is thereby established. The framework is evaluated using GPT, DeepSeek, GLM, and Kimi, and initial assistance performance and refinement outcomes are compared across models. Despite differences in initial performance, effective assistance is achieved with all four models after a single autonomous refinement iteration under the tested conditions. Across three tasks, biceps and triceps muscle activation levels are reduced by 29.4% and 35.2%, respectively, compared with those measured without an exoskeleton. However, limited adaptability to unexpected situations is observed, indicating that further improvements in robustness and safety are required.

cs.RO

新论文 · v1arXiv:2611.01578

Recoverability-Aware Evaluation of Diffusion Video Inpainting and Object Removal

Yanliang Qi, Jiacheng Ding, Cong Guo, Peihua Mai

原文摘要

Video inpainting for object removal is scored over the whole hole, although the background behind the object is visible in other frames of the shot for some hole pixels and in no frame for others. A whole-hole score therefore mixes copying with generation and cannot show which of the two a remover does well. To separate the two, we propose recoverability-stratified evaluation, in which a point tracker run on the clean video labels each hole pixel by whether and how far away it is observed, so that fidelity and temporal stability can be reported per stratum against a copy reference. To reuse the observed content, we also propose evidence-guided sampling (EGS), which blends tracked colors into the clean-latent prediction of a video diffusion remover without training. On DAVIS, the perceptual advantage of three diffusion removers over flow propagation shrinks where the content is visible a few frames away (LPIPS difference-in-differences +0.046 to +0.056 against E2FGVI-HQ), and real paired captures show the same pattern for two of them. Their DAVIS hole warping error is two to four times that of ProPainter, and copying along clean-video tracks lowers their recoverable LPIPS by a quarter to two fifths. EGS closes 43% and 56% of the gap to this copy reference on held-out DAVIS when its colors come from clean-video tracks. With colors tracked on the masked input, a pre-registered confirmation finds no gain on MiniMax-Remover and a loss on ROSE. Diffusion removers thus leave observed content unused on DAVIS, and training-free reuse does not yet hold with tracked evidence.

cs.CV

版本更新 · v2arXiv:2610.34103

T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding

Shahriar Kabir Nahin, Xiao Ye, Muhao Chen, Ben Zhou, Anshuman Chhabra

原文摘要

Speculative decoding significantly accelerates autoregressive text generation in Large Language Models (LLMs), but its efficacy depends largely on two key factors: the distributional alignment between the draft and the target model, and the draft model's latency during inference. However, existing approaches typically utilize independently pretrained small draft models or seek to prune the target model to a manually chosen architecture, thereby failing to explicitly balance the trade-off between draft model alignment and token generation efficiency. To address this gap, we formulate draft model design as an optimization problem and propose T2D, a framework that constructs draft models directly from the target model using latency-aware structured pruning and knowledge distillation. In this manner, T2D obtains draft models that are jointly optimized for both measured inference latency and cross-entropy loss on the target model's responses, resulting in superlative speculative decoding performance. Through extensive experiments on multi-domain speculative decoding benchmarks and across several target model families of differing scale, we demonstrate how T2D prunes up to 92\% of the target model to obtain highly performant draft models compared to competitive baselines. Moreover, draft models obtained via T2D can also be utilized by other speculative decoding token-alignment and knowledge distillation methods in a plug-and-play fashion, leading to further gains. Our findings underscore the importance of jointly navigating the draft model architecture-alignment frontier to unlock the full potential of speculative decoding for LLMs.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.01573

Spend the Bits Where the Tiny Objects Are: Rate-Utility Region Coding for Aerial Detection

Yanliang Qi, Jiacheng Ding, Cong Guo, Peihua Mai

原文摘要

Bandwidth-limited aerial cameras must compress their images before a remote detector can find the many tiny objects in them. Threshold-based region-of-interest (ROI) coding sends only confidently detected regions, and because tiny objects provide limited visual evidence and often score low, it can discard the regions that contain them. We propose rate-utility region coding (RUO), which sends a region when its expected detection utility justifies its measured byte cost, choosing to drop it or to send it at low or high quality with one multiplier shared across images. RUO trains no model, uses a standard image codec and decodes in a few milliseconds. On all 1,610 VisDrone-DET test-dev images, RUO uses 42.4% fewer bits than a tuned threshold-based ROI coder, averaged over their shared tiny-object average precision (AP) range. RUO also needs fewer bits for tiny objects than the AV1 Image File Format (AVIF), High Efficiency Video Coding (HEVC) and three published learned codecs, and its advantage over threshold-based ROI coding persists when the sender and receiver use different detectors. For AP over all object sizes RUO needs 25.4% more bits than the tuned ROI coder, because its allocation drops large regions first at low rates, so it suits tasks that target tiny objects. We plan to release the code.

cs.CV

新论文 · v1arXiv:2611.01572

Impossible Code, Barely Changed Score: A Replay Study of Judge-Based Evaluation

Masoud Fetanat

原文摘要

Language models are often used to judge generated code without running it. A useful evaluation should reveal substantial changes in the answers it scores. We examine this requirement by repeating an earlier evaluation on 421 coding problems, comparing Qwen-2.5-7B-Instruct with two versions trained using Group Relative Policy Optimization (GRPO). One receives rewards from execution tests (CE-trained), and the other from a strong language-model judge (SLJ-trained). The base model's syntax-failure rate remains stable, but the trained checkpoints produce invalid Python on 63%-67% of attempts. Despite this change, the strong judge's Pass@32 scores fall by only about 3 percentage points, from 96.67% to 93.95% for SLJ-trained. Within the later run, allowing more attempts makes the base and trained checkpoints look increasingly similar under the judge. With 128 attempts per question, the judge accepts at least one SLJ-trained answer on 96.44% of problems, compared with 28.27% under execution tests. We recommend reporting the share of answers that pass Python's syntax check alongside every judge-based score. This check requires no tests or code execution and flags invalid answers that the judge accepts, although it cannot establish functional correctness. Our findings show how a high judge-based score can hide substantial output damage and motivate checking an evaluation's sensitivity to change. Project page and code: https://curiousorbitnotes.github.io/evorobust-replay-audit/

cs.SE · cs.AI

新论文 · v1arXiv:2611.01569

A logarithm-free subexponential algorithm for minimum quartet inconsistency

Chuang-Chieh Lin

原文摘要

We give a deterministic algorithm for complete, unweighted minimum quartet inconsistency (MQI) with time and space $2^{O(k^{1/4})}+n^{O(1)}$, where $n$ is the number of taxa and~$k$ is the allowed number of quartet disagreements. This removes the logarithmic factor from the exponent of the MQI bound announced in 2009. The algorithm combines low-error anchoring, chromatic coding, and dynamic programming that accounts for disagreements with all input quartets, with a refined count of colorings and merging states. We also record a generic ETH-based lower bound. The optimality of the fourth-root exponent remains open.

cs.DS

新论文 · v1arXiv:2611.01568

Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation

Rongfeng Guo, Zhuang Zhuang, Ji Dai, Peng Zhao, Shijie Li, Jie Chen, Teng Long, Vincent Tao Hu 等 9 位作者

原文摘要

Generative recommendation retrieves items by autoregressively generating semantic IDs, typically via beam search. On-policy self-distillation (OPSD) enhances training supervision by transferring privileged self-teacher knowledge at student-generated states. However, beam-search retention depends on competition among prefixes: visited states differ in importance, and initially reliable decisions may approach the pruning boundary as training evolves. Moreover, conventional distribution matching couples target-token confidence with preferences among competing continuations, potentially weakening relational supervision when the self-teacher strongly favors the target. To address these challenges, we propose Search-Aware On-Policy Self-Distillation (SA-OPSD), a framework that transfers privileged self-teacher knowledge to the states visited during the student's own beam search. Specifically, we introduce Evolving-Boundary Sampling, which prioritizes search-critical states by considering both current pruning-boundary proximity and initial-reference retention-margin decline under a controlled distillation budget. Furthermore, we develop Confidence-Decoupled Branch Distillation, which separates target-probability calibration from informative sibling relations to better preserve the teacher's preferences among competing branches. Experiments on Industrial, Office, and Instruments demonstrate strong performance for SA-OPSD.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01566

Principled Human-AI Collaboration in Agentic Workflows

Young Hyun Cho, Will Wei Sun

原文摘要

Organizations adopting AI face the challenge of deciding which outputs can be released without human review while meeting the quality standards of human experts. We develop a statistical framework for delegating tasks between experts and black-box generate-verify workflows, in which AI-generated answers are verified and revised over multiple rounds. Before deployment, human experts evaluate selected outputs, and their judgments are used to calibrate the verifier threshold and number of attempts. Our method selects the policy with the highest estimated automation rate among statistically approved candidates, without modifying the generator or verifier. We establish finite-sample control of the error rate among released outputs, characterize the expert evaluations sufficient to attain a target automation rate, and derive a minimax lower bound establishing rate optimality in the quality margin and required confidence. In a MultiHiertt financial question-answering case study, average held-out automation increases from 2.50% to 24.17% as expert evaluations accumulate, while released-output error rates remain around 1.20%. In contrast, heuristics that release answers after consistently high verifier scores either violate the 5% error tolerance or automate at most 1.30% of tasks. Synthetic experiments further examine these theoretical predictions under controlled settings.

stat.ML · cs.AI · cs.LG · stat.ME

新论文 · v1arXiv:2611.01565

Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining

Zhanyi Sun, Max Simchowitz, Shuran Song

原文摘要

In modern robot learning, generative robot policies are first pretrained through supervised learning from demonstrations, then refined through reinforcement learning, supervised finetuning, or other forms of posttraining. Yet conventional pretraining metrics, such as validation loss and average task success, provide an incomplete account of which policies support both effective direct deployment and subsequent posttraining. In this work, we study closed-loop pass@k, which evaluates the probability that k rollouts from the same initial condition attain at least one success. Thus, pass@1 measures mean task success; large-k pass@k measures whether success remains reachable under repeated sampling. Across a wide range of posttraining recipes, we show that large-k pass@k reveals posttraining differences not captured by pass@1. In particular, checkpoints with similar pass@1 but different large-k pass@k have different posttraining performance. Moreover, we show pass@k peaks at different checkpoints during supervised pretraining, revealing a coverage-reliability tradeoff over the course of training. Based on these observations, we propose two practical interventions: (1) a purely offline checkpoint-selection criterion that balances coverage and reliability without closed-loop evaluation, and (2) a generative data augmentation procedure that expands supervision beyond the finite demonstration set, preserving large-k pass@k while maintaining or improving pass@1 and raising the observed coverage-reliability Pareto frontier. Together, our results motivate evaluation, checkpoint selection, and training procedures that explicitly account for posttraining. Blog post, visualizations, and code are available at https://zhanyisun.github.io/robot-policy-learning-dynamics/.

cs.LG · cs.RO

新论文 · v1arXiv:2611.01564

Meta-memorization and memorization scaling laws in transformers

Alex Nguyen, Kenneth A. Norman, Gautam Reddy

原文摘要

Larger transformers can memorize more data, with a capacity (in bits) that scales roughly linearly with the number of parameters. Counterintuitively, larger models also memorize faster, requiring fewer repetitions of a sequence during training before it is memorized. We reproduce both memorization scaling laws in transformers trained on random binary sequences, showing that rapid memorization can arise even when data contain no semantic or compositional structure. Rapid memorization is due to a meta-memorization effect, where models trained to memorize a large set of random sequences learn to memorize novel sequences more quickly. The rate $r(t)$ at which models memorize grows with training time $t$ as a power-law $r(t) \sim t^β$ with a fixed exponent $β$ but an increasing upper cutoff across model scales. Meta-memorization enables even one-layer transformers to few-shot memorize a 100-bit sequence. This effect is partly explained by the formation of structured attention heads that convey position-invariant sequence information to MLPs where memorized sequences are stored. Meta-memorization is recapitulated in a simplified model of a dense associative memory where retrieval is constrained by an attentional bottleneck. Our results suggest transformers, through pre-training, acquire reusable mechanisms that enable highly efficient storage and retrieval of memories.

cs.LG · cs.AI

版本更新 · v2arXiv:2602.04007

Boost+: Equitable, Incentive-Compatible Block Building

Mengqian Zhang, Sen Yang, Kartik Nayak, Fan Zhang

原文摘要

Block space on the blockchain is scarce and must be allocated efficiently through block building. However, Ethereum's current block-building ecosystem, MEV-Boost, has become highly centralized due to integration, which distorts competition, reduces blockspace efficiency, and obscures MEV flow transparency. To improve equitability and economic efficiency in block building, we propose $\textsf{Boost+}$, a system that pools submitted order flows inside an attested execution environment and gives all participating block-building algorithms equal access to them. The core of $\textsf{Boost+}$ is the mechanism $M_{\textsf{Boost+}}$, built around a baseline block-building algorithm. $M_{\textsf{Boost+}}$ aligns incentives for both searchers (intermediaries that generate or route transactions) and builders: Truthful bidding is a dominant strategy for all builders. For searchers, truthful reporting is dominant whenever the baseline algorithm dominates competing builders, and it remains dominant for all conflict-free transactions, even when builders may win. We further show that even if a searcher can technically integrate with a builder, non-integration combined with truthful bidding still dominates any deviation for conflict-free transactions. We also implement a concrete baseline algorithm informed by empirical analysis of real-world transactions and evaluate its efficacy using historical data.

cs.CR

版本更新 · v2arXiv:2609.23056

Bridging Static and Agentic RAG for Taiwanese Historical Question Answering

Kai-Hsin Chen, Wei-Yu Chen, Xuanjun Chen, Su-Ling Yeh, Jyh-Shing Roger Jang

原文摘要

Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear whether such adaptive orchestration consistently outperforms well-designed static pipelines. We conduct a controlled comparison of agentic and static RAG for Taiwanese historical question answering, sharing the same generator and hybrid retrieval backend. Despite similar aggregate performance, the two pipelines differ on 70.83% of questions, with their advantages largely canceling out when averaged. An oracle that selects the better response per question improves the composite score by 0.2417 over the better individual pipeline, revealing substantial headroom for question-level selection. We therefore introduce a post-hoc selector that compares the two responses and their cited evidence, significantly outperforming either individual pipeline and recovering 60.34% of the oracle headroom. These results show that aggregate comparisons can obscure meaningful question-level differences between retrieval strategies, suggesting that exploiting their complementarity may be more fruitful than seeking a universally superior pipeline.

cs.CL · cs.AI · cs.IR

版本更新 · v2arXiv:2610.38311

Detecting Incorrect LLM Explanations for Automated Program Repair

Lam Nguyen Tung, Chenxi Gu, Xiaoning Du, Haoye Tian, Aldeida Aleti, Neelofar Neelofar

原文摘要

LLM-generated explanations help developers understand automated program repair (APR) rationale and assess patch quality. Incorrect explanations can mislead developers about a repair's reliability, making their detection important. However, manually inspecting the growing volume of generated repairs is impractical, motivating automated detection. Existing methods mainly target incorrect answers from general question-answering LLMs, often by sampling multiple responses and detecting contradictions. Applied to APR, they face two limitations: (1) they may depend on external verifiers that are unavailable or lack APR-specific reasoning; and (2) sampling strategies such as paraphrasing or re-prompting the same input often yield superficial, redundant responses that repeat the original error rather than expose it. We propose MetaReJ, the first method designed to detect incorrect APR explanations using metamorphic testing. Inspired by debate and viva examinations, MetaReJ challenges explanations through an argumentative strategy without requiring external verifiers. It applies novel metamorphic relations (MRs) to recursively question the LLM under equivalent and non-equivalent repair scenarios and detect contradictions. To obtain diverse samples, MetaReJ transforms the buggy program into variants that preserve or alter the underlying bug, then asks the LLM how to repair each variant. Contradictions among responses are encoded as MR violations, which indicate that the original explanation is incorrect. We evaluate MetaReJ on a manually labelled dataset of 1,756 explanations from multiple LLM-based APR systems. MetaReJ achieves an MCC of up to 0.43, outperforming prior methods by up to 333.3% in MCC.

cs.SE

新论文 · v1arXiv:2611.01562

Finite-Time Online Sample Complexity for Conditional Diffusion Models

Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli, Amrit Singh Bedi, Vaneet Aggarwal

原文摘要

We study the finite-time training and sampling error of conditional diffusion models trained by online stochastic-gradient denoising score matching. Rather than assuming access to an exact empirical or population risk minimizer, we analyze the score network produced after a finite number of stochastic-gradient updates under an explicit localized Polyak--Łojasiewicz (PL) condition, stochastic-gradient regularity, and a trajectory-containment assumption. Our analysis separates the network approximation complexity from the online training-sample budget and propagates both errors through the reverse diffusion process. Under anisotropic smoothness, a joint intrinsic-dimensional structure for the data and conditioning variables, sub-exponential tails, and explicit approximation-class compatibility, we obtain a conditional score approximation error of order \[ \widetilde{\mathcal O}\!\left(M^{-η_{\mathrm{app}}}\right), \qquad η_{\mathrm{app}} = \frac{2α_x} {2α_x+d_x'+(α_x/α_y)d_y'}, \] where \(M\) denotes the approximation complexity, \(d_x'\) and \(d_y'\) are the intrinsic response and conditioning dimensions, and \(α_x,α_y\) are their corresponding smoothness exponents. For \(N=RB\) online denoising samples used by SGD, the finite-time optimization error is controlled explicitly in terms of the PL, smoothness, gradient-noise, and initialization constants. Combining these ingredients with reverse-process stability yields a total-variation bound that decomposes into terminal-initialization, time-discretization, approximation/localization, and finite-time optimization errors.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01559

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

Mudit Gaur, Prashant Trivedi, Shuchin Aeron, Amrit Singh Bedi, George K. Atia, Vaneet Aggarwal

原文摘要

Flow matching has emerged as a promising alternative to diffusion-based generative modeling, offering a continuous-time ordinary differential equation formulation with fast sampling and a simple regression-based training objective. Despite its empirical success, some theoretical analyses idealize the learning procedure by assuming that the velocity field is obtained by exact empirical risk minimization. This assumption does not reflect the practical finite-dataset setting, where the empirical flow-matching loss is only approximately minimized by a finite number of stochastic-gradient updates. We develop an empirical-risk-minimizer-free analysis for flow matching that explicitly accounts for both finite-sample statistical error and finite-time empirical optimization error. Our analysis considers a finite dataset of \(N\) flow-matching samples and a learned parameter \(θ_T\) obtained after \(T\) stochastic gradient updates on the empirical objective. Under regularity assumptions on the interpolation path, sub-exponential source and target distributions, approximation by a bounded-parameter smooth neural velocity class, empirical-loss optimization, and uniform flow stability, we prove a guarantee that holds with high probability over the finite training dataset and in expectation over the stochastic-gradient randomness. The resulting bound separates approximation error, statistical error from the finite dataset, tail error from unbounded source and target distributions, and empirical optimization error from approximate minimization of the finite-sample objective.

cs.LG · cs.AI