跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 15:33 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 16:33 — 2026-11-08 16:33（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：2026-11-08 15:33最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 12,919 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 15:31（北京时间）
版本更新 · v2arXiv:2605.18099

Fluid Antenna-Aided Robust Secure Uplink Transmission in LEO Satellite Constellations

Suhong Luo, Pan Tang, Jianhua Zhang, Ji Wang, Yixuan Li, Xingwang Li

原文摘要

Secure uplink transmission in low-earth orbit (LEO) satellite constellations faces significant challenges due to the time-varying spatial distributions of serving and potential eavesdropping satellites, particularly when their angular separations are small and eavesdropper channel state information (CSI) is imperfect. To address these challenges, this paper investigates fluid antenna (FA)-aided robust secure uplink transmission in LEO satellite constellations. To avoid frequent antenna reconfiguration, the FA positions are optimized over an observation interval and remain fixed throughout the interval, while transmit beamforming dynamically adapts to the time-varying satellite channels. We formulate an average worst-case secrecy rate maximization problem by jointly optimizing FA positions and time-varying beamforming under norm-bounded eavesdropper CSI uncertainties and per-slot secrecy rate constraints. Two new alternating optimization (AO) algorithms are developed to solve the resulting non-convex problem. For robust beamforming optimization, the S-procedure, semidefinite relaxation (SDR), and first-order approximation are employed to construct a tractable convex problem, followed by Gaussian randomization for rank-one recovery. For FA position optimization, we derive concave surrogate functions for successive convex approximation (SCA) and develop a differential evolution (DE)-based search strategy to reduce computational complexity. Numerical results demonstrate that both FA-aided schemes consistently outperform conventional fixed-position antenna arrays across different constellation configurations and CSI uncertainty levels. Moreover, the two algorithms exhibit different performance-complexity tradeoffs as the number of FA elements increases, with DE offering a computational advantage for larger arrays while SCA can achieve higher secrecy rates.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.25008

No Escape from the Quadratic Barrier: Adaptive Attacks on Linear $\ell_2$ Sketches

Edith Cohen, Uri Stemmer

原文摘要

Linear sketches estimate properties of high-dimensional inputs from a fixed low-dimensional projection. At constant accuracy, randomized Euclidean-norm sketches, notably the Johnson-Lindenstrauss transform, support exponentially many nonadaptive queries in sketch dimension $k$. For adaptive black-box queries, known privacy-based defenses guarantee $\widetildeΩ(k^2)$ and it remained open whether stronger guarantees were possible. Prior attacks used more queries, restricted the responder, or provided weaker failure guarantees. We show that the quadratic guarantee is optimal up to logarithmic factors, even with a computationally unbounded responder that knows the matrix, attack algorithm, history, and query distributions and may change its randomized rule after every query. For every fixed hidden $A\in\mathbb{R}^{k\times n}$ with $n>40k$ and target accuracy $α\in (0,1]$, our black-box attack uses $O(k+α^2k^2\log(2+α^2k))$ queries in $\widetilde{O}(1+α^2k)$ adaptive rounds to force, with constant probability, a round in which a constant fraction of answers have $Ω(α)$ relative error. This fraction can be taken arbitrarily close to one half. Our results clarify the limits of defending a fixed compressive linear representation by adapting the prediction rule.

cs.DS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07339

DiagDBench: Evaluating Agentic LLMs on Interactive Database Diagnosis and Anomaly Remediation

Xinxin Zhao, Rong Kang, Tieying Zhang, Cuiping Li, Hong Chen, Jing Zhang

原文摘要

Database diagnosis and anomaly remediation are essential to reliable database management system (DBMS) operation. Despite advances in large language model (LLM)-based database agents, constructing live DBMS environments that reproduce diverse anomalies at scale remains challenging, limiting the availability of executable samples for database agent training and evaluation. To this end, we introduce DiagDBench, a large-scale benchmark for training and evaluating database agents on interactive diagnosis, anomaly remediation, and optional workload performance optimization across diverse, realistic anomaly scenarios. Each sample pairs a user request, comprising an issue description and an anomaly-verified workload under which the issue was observed, with a self-contained, executable DBMS environment that supports real-time monitoring, interactive diagnosis, remediation, and workload execution. To construct these samples at scale, we propose an LLM-based framework with two complementary pipelines: Manual-Guided Anomaly Synthesis, which sequentially synthesizes user requests, database modifications, and anomaly-injection scripts grounded in DBA manuals and official DBMS documentation; and Incident-Guided Anomaly Reproduction, which reconstructs anomaly samples end to end from real-world enterprise online diagnosis incidents. Built using this framework with sample filtering, expert review, and refinement, DiagDBench comprises 6,940 synthesized training samples and a held-out test set of 454 expert-annotated samples, spanning three hardware configurations, two DBMSs, and three database schemas. Extensive evaluations of database agents powered by multiple LLMs demonstrate that even the best-performing agent, ReAct with GPT-6 Astra, scores only 56.24, whereas most agents score below 45, underscoring the difficulty of DiagDBench.

cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.34804

Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure

Jeff Nijsse, Shu Su, Benjamin Oholeguy, Sreenivas Sremath Tirumala

原文摘要

Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. However, existing defences operate strictly in update space, leaving aggregators blind to data poisoning; model updates derived from fabricated telemetry remain indistinguishable from honest contributions. We repurpose process invariants, physical relations that always hold in normal operation, such as conservation of mass, from runtime detection heuristics into a verifiable admission requirement for federated updates, mined automatically from clean operational data. We evaluate this admission gate across two physical water testbeds (SWaT, WADI) and a distribution benchmark (BATADAL), testing seven aggregation rules against telemetry fabrication, exposure-only replay poisoning, and an invariant-aware adaptive adversary. Across three testbeds the mined invariants reject none of 25 honest shards except every cross-channel fabrication on SWaT and BATADAL, including optimised perturbations that the similarity based FoolsGold admits in full. On real telemetry, five mined invariants detect 12 of SWaT's 35 attacks, while nine invariants detect 20. With nine invariants, the admission gate removes 78% of the targeted-attack recall lost to replay poisoning (95% CI 57--97%, $p < 0.001$ over 20 seeds) across five standard aggregators, and 82% under FedAvg. To reconcile physical admission control with federated data privacy, we show invariant compliance using zero-knowledge proofs (zk-SNARKs) to allow clients to prove batch adherence without revealing operational telemetry.

cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.38005

Diagnosing and Improving Probabilistic Reasoning in Large Language Models

Huaman Sun, Dingcheng Wang, Jason Hartline, Jessica Hullman

原文摘要

Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic framework that decomposes LLMs' decision loss into two components: forming accurate beliefs from provided evidence and translating those beliefs into actions that optimize a provided utility function. Using a synthetic benchmark with known ground truth, we apply the decomposition to characterize probabilistic reasoning in frontier and open-sourced models. We further evaluate whether RL interventions targeting beliefs, decisions, or both improve these components across three domains, whether improvements transfer across components and elicitation formats, and whether decision performance can improve without improvement in belief formation. We find that targeting one component of probabilistic reasoning redistributes decision loss, improving the target without necessarily transferring to others, and that jointly targeting belief formation and decision-making improves both but hinges on matched formats between training and evaluation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07336

Energy-Time Optimal Decoding Using Expander-Graph LDPC Codes and Mesh Network Architecture

Christopher Blake

原文摘要

Within the Thompson VLSI model, the first energy optimal decoding schemes (up to polylogarithmic factors) that also reach clock cycle lower bounds are constructed. Let $N$ be block length. Then, there is an exponential error scaling function and a binary symmetric channel, such that for all $f(N)$ that scales to zero more slowly than this, there is a decoding scheme for this channel with error probability that scales as $O(f(N))$ that has number of clock cycles $T\le O(\sqrt{-\log(f(N)})\text{polylog}(N))$ and energy $E\le O(N\sqrt{-\log(f(N))}\text{polylog}(N))$. This matches fundamental lower bounds up to polylogarithmic factors. The technique uses expander-graph based LDPC codes, a mesh network architecture, and a parallelization technique. The key technical result needed for this is a lemma in graph theory. This lemma is used to show that communication graphs of bounded node degree can be routed through two- and three-dimensional mesh networks without overflowing the memory of any mesh node. Upper bounds are also extended to three dimensions.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07329

Where Do Reported Long-Video QA Gains Come From? A Controlled Audit of Frame Selection, Evidence Injection, and Expert Routing

Shih-Yao Lin

原文摘要

Long-video question answering is usually studied as frame selection: which few frames should a vision-language model see? We introduce VideoRouteAudit, a controlled audit that separates this choice from two alternatives, injecting non-visual evidence and routing to another answering model. It holds the backbone, frame budget, decoding, prompt and grader fixed while varying one decision at a time. On the full Video-MME long bucket (n=900, K=8), no tested selector significantly improves over uniform sampling. The largest selection-only estimate is +1.9 pt (95% CI [-1.2,+5.0]) and our cascade is +1.2 pt [-1.7,+4.1]; all are equivalent to uniform within +/-5 pt. The same contrasts are unstable at the n=200 subset scale commonly used: three of four are up to 3.8x larger, one reverses sign, and resampled 200-item subsets reverse the full-bucket effect's sign in 35.8% of draws. The audit also corrects our own first results. The anomaly-domain "+ASR" arms injected no text, so the pooled +4.7 pt gain was selection plus a development prefix. With transcripts, ASR lowers XD-Violence accuracy by 10.0 pt when appended after the question and not at all when placed before it, and lowers UCF-Crime by 13.0 pt either way; on Video-MME, placing it first adds about 4 pt (7 on Qwen2-VL) to uniform sampling and to the cascade alike (post hoc, unadjusted). Swapping the answering model gives the largest contrast (+15.1 pt on MUSIC-AVQA, +33.3 pt on its worst type), but the same audio-visual expert with its soundtrack silenced keeps 92% of the gain (69% with a mismatched soundtrack), so the contrast is mostly a model swap. Code, per-item predictions and scripts that recompute every statistic are available at https://github.com/mikeslin-ir/long-video-qa-audit.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07328

DC-SQEM: Medial Mesh Extraction by Dual Contouring with Spherical Quadric Error Metric

Bingchuan Li, Ruilong Liu, Tianhao Hu, Congyi Zhang, Ningna Wang, Junfeng Yao, Xiaohu Guo

原文摘要

The medial axis, as a compact representation, describes not only the boundary but also the interior of the shape, and has been widely used in analyzing and simplifying shapes. However, approximating feature-preserving medial axis from unstructured data, such as oriented point clouds, remains challenging due to the lack of explicit connectivity and the presence of noise in the source. We propose DC-SQEM, a dual-contouring-based framework that computes medial meshes (an explicit representation of the medial axis) directly from oriented point clouds without relying on watertight manifold surfaces or volumetric structures. With the help of an adaptive octree, our method fits local medial spheres for each cell based on the Spherical Quadric Error Metric (SQEM). We address several long-standing robustness issues in dual-contouring and mesh extraction, including out-of-cell solutions, unstable feature classification, and redundant topological connections. To this end, we introduce virtual nodes, a feature-downgrading strategy, and a geometry-driven topology-aware cleanup procedure, enabling robust SQEM-based medial dual contouring with clean mesh outputs. Unlike prior point-cloud-based methods that produce either only 1D skeletal structures or incomplete medial features, our method preserves sharp geometric features from the input and reconstructs a complete medial structure, including sheets, curves, seams, and junctions. Compared to restricted-power-diagram-based approaches, our algorithm can handle point clouds as input, without having a strong requirement on water-tightness or manifoldness.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07327

Permanent and Transient Representations for Continual Reinforcement Learning

Nishanth Anand, Doina Precup

原文摘要

Continual Reinforcement Learning (CRL) agents struggle to adapt to new situations while retaining prior knowledge, leading to a stability-plasticity trade-off. One approach to solving this problem is by using complementary learning systems: one for slow, long-term learning and another for quick, transient adaptation. Anand & Precup (2023) instantiated this idea using permanent and transient value functions, but used the same features in both systems. Intuitively, long-term learning should rely more on parametric representations for broad generalization, while transient learning would be best served by non-parametric representations for situation-specific adaptation. In this paper, we explore this idea both theoretically and empirically. By introducing a novel non-parametric approximation for estimating the transient value function in complex tasks, we demonstrate that our method enables online learning and outperforms competitive baselines on image-based tasks and Craftax-Classic, underscoring the effectiveness of our system-level decomposition.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07325

Functional Converses for Private Matrix-Product Retrieval under Library-Wide Decoder-Side Correlation

Malihe Aliasgari, Yousef Nejatbakhsh

原文摘要

We consider private retrieval of the matrix product $A^\top B^{(θ)}$ from replicated $P_c$-colluding servers when $B^{(\ell)}=A+N^{(\ell)}$, with the innovations mutually independent and independent of the user-held $A\in\mathbb{F}_q^{m\times m}$. The servers store the full library, correlated with $A$, which changes both the communication problem and the security definition: a secrecy condition including the stored library cannot hold, as the library itself partly reveals $A$. We therefore measure only additional leakage and require index privacy conditioned on $A$; both reduce to classical notions under independence. For $A$ of rank $k<m$ we prove, with no structural hypothesis on the map, $D^*\geq H(A^\top B^{(θ)}\mid A)/C_{\mathrm{PIR}}(N,P_c,L)-o(km)$, where $C_{\mathrm{PIR}}(N,P_c,L)$ is the replicated $P_c$-colluding private-information-retrieval capacity. The proof rests on a colluding converse for servers storing arbitrary refinements of the demanded messages, whose answers need not be measurable functions of the functional-message library, and a privacy-transfer characterization. Publishing a canonical row-space representative makes the bound achievable for arbitrary independent and identically distributed innovations under a public-setup measure. Under a strengthened observational model (exact correctness, common conditional library support, and full-transcript security), concealment forces $D\geq H(G_m N^{(θ)})/C_{\mathrm{PIR}}$, where $G_m$ spans the linear join of all row spaces in the support of the operand distribution; this extends to vanishing error under a simultaneous-decodability assumption. In the full-rank case product recovery reduces to innovation recovery: $D^*=H(N^{(θ)})/C_{\mathrm{PIR}}+o(m^2)$.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07323

Rethinking Data Selection: The Importance of Coverage over Difficulty in LLM Fine-Tuning

Lalchand Pandia, Kanishka Misra, Allyson Ettinger

原文摘要

Selecting high-quality training data can reduce computation cost for LLM fine-tuning. Prior work on data selection developed a variety of difficulty-based scores, motivated by the intuition that harder examples are more informative. While effective for smaller classification models, we find that such methods often fail to outperform random selection for LLM fine-tuning. Our analysis reveals that random selection performs better because it is more representative of the underlying input space---i.e., has better coverage. To validate the importance of coverage, we implement a simple clustering-based selection method which selects data that is more representative of the underlying input distribution. On a set of diverse single-domain tasks, this method yields performance at or above that of random selection. On the diverse, multi-domain Tülu 3 mixture, where random sampling no longer guarantees a balanced subset, our method outperforms all methods. Overall, our results indicate that prioritizing coverage over difficulty leads to more effective data selection for LLM fine-tuning.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07319

WeightLoop: Weight-Space Programming with Experimental Feedback

Mengran Li, Bo Li, Weijing Zhao, Chengyang Zhang, Boyu Zhang, Jinfeng Xu, Zelin Zang, Victor C. M. Leung 等 9 位作者

原文摘要

Weight-space programming (WSP) shows that language models can reason about and rewrite neural network weights; recursive self-improvement (RSI) motivates feedback-driven improvement. Models guiding experiments receive concrete feedback: completed assays reveal prediction errors and inform what to test next. We introduce WeightLoop, a framework that turns experimental feedback into persistent updates to deployed predictors. GPT-6 Astra inspects a task specification and the model implementation, then writes a bounded, reusable parameter-editing program. As new measurements arrive, the program identifies prediction discrepancies, validates candidate edits using observed outcomes, and writes the selected changes back to the original model. The editor remains fixed while the predictor evolves, enabling repeated updates without further LLM calls or gradient retraining while preserving the original inference interface. In offline replay, targeted edits improve mean ranking utility in seven of eight endpoint-budget settings (all eight versus random edits) and mean final discovery across three sequential tasks. WeightLoop connects WSP with an RSI-inspired improvement loop, making experimental evidence a direct driver of model change and subsequent decisions.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.12266

Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models

Weimin Wu, Xuefeng Song, Yibo Wen, Qinjie Lin, Zhihan Zhou, Jerry Yao-Chieh Hu, Zhong Wang, Han Liu

原文摘要

We introduce Genome-Factory, the first integrated Python library for tuning, deploying, and interpreting genomic foundation models. Our core contribution is to simplify and unify the workflow for genomic model development: data collection, model tuning, inference, benchmarking, and interpretability. For data collection, Genome-Factory offers an automated pipeline to download genomic sequences and preprocess them. For model tuning, Genome-Factory supports both full and parameter-efficient fine-tuning across diverse genomic models. For inference, Genome-Factory enables both embedding extraction and DNA sequence generation. For benchmarking, we include two existing benchmarks and provide a flexible interface to incorporate additional benchmarks. For interpretability, Genome-Factory introduces an open-source biological interpreter based on a sparse auto-encoder. We validate the utility of Genome-Factory across three dimensions: (i) Compatibility with diverse models and fine-tuning methods; (ii) Benchmarking downstream performance using two open-source benchmarks; (iii) Biological interpretation of learned representations with DNABERT-2. These results highlight its practical value for real-world genomic analysis. GitHub: https://github.com/WeiminWu2000/Genome_Factory.

q-bio.GN · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2507.17892

DiNAT-IR: Exploring Dilated Neighborhood Attention for High-Quality Image Restoration

Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu

原文摘要

Transformers, with their self-attention mechanisms for modeling long-range dependencies, have become a dominant paradigm in image restoration tasks. However, the high computational cost of self-attention limits scalability to high-resolution images, making efficiency-quality trade-offs a key research focus. To address this, Restormer employs channel-wise self-attention, which computes attention across channels instead of spatial dimensions. While effective, this approach may overlook localized artifacts that are crucial for high-quality image restoration. To bridge this gap, we explore Dilated Neighborhood Attention (DiNA) as a promising alternative, inspired by its success in high-level vision tasks. DiNA balances global context and local precision by integrating sliding-window attention with mixed dilation factors, effectively expanding the receptive field without excessive overhead. However, our preliminary experiments indicate that directly applying this global-local design to the classic deblurring task hinders accurate visual restoration, primarily due to the constrained global context understanding within local attention. To address this, we introduce a channel-aware module that complements local attention, effectively integrating global context without sacrificing pixel-level precision. The proposed DiNAT-IR, a Transformer-based architecture specifically designed for image restoration, achieves competitive results across multiple benchmarks, offering a high-quality solution for diverse low-level computer vision problems.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30983

Can BEV Perception Gracefully Degrade under Sensor Failures?

Haifa Zhang, Yijing Wang, Zhiqiang Zuo

原文摘要

Despite the remarkable success of multi-modal bird's-eye view (BEV) perception in autonomous driving, standard fusion models can be highly brittle to sensor corruptions, causing catastrophic performance degradation. This vulnerability arises when corrupted features contaminate the shared BEV representation and the detector fails to preserve a usable visual fallback. To this end, we present Grace-BEV, a lightweight framework for robust fusion in Lift-Splat-Shoot (LSS)-based detectors. Operating in the aligned BEV space, Grace-BEV complements a LiDAR-guided image-BEV expert with a LiDAR-independent visual expert. A TrustGate Router learns a sample-level mixture of their outputs, while the FailSafe Fusion Block recalibrates the routed image representation together with raw LiDAR features. Furthermore, we devise a Three-Phase Training strategy with Modality Dropout to establish the visual fallback before learning routing and fusion, followed by joint fine-tuning. Extensive experiments on nuScenes-R and nuScenes-C across three LSS-based detectors show that Grace-BEV maintains robust performance across diverse corruption settings. Under complete LiDAR loss, where the corresponding baseline models exhibit a collapse to 0.0 mAP, Grace-BEV restores performance to as high as 34.7 mAP. It also improves clean accuracy by up to 1.4 mAP points with 1.2M additional parameters per detector. Component and training ablations support the complementary roles of visual initialization, expert routing, and adaptive fusion.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.23379

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

Tobias Bersia, Tatiana Gaintseva

原文摘要

Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations. They offer a flexible interface for reading hidden information from model states, especially when relevant information is internally represented but absent or incomplete in visible behavior. However, AOs are themselves learned systems: their answers are shaped by training data, objectives, and learned reporting behavior, rather than being neutral readouts of represented information. We study this in a controlled Taboo Word Guessing setting, where subject models are fine-tuned to internally use a hidden concept while avoiding direct disclosure. Contrary to the expectation that an AO trained on such a subject becomes a specialist reader, we find that fine-tuned AOs can become concept-specific anti-readers: they selectively fail to recover the concept persistently present during their own training. This failure is not simply explained by absence of the concept from the subject or oracle representations: the target remains decodable inside the oracle, while LogitLens and layer-ablation analyses indicate that the failure arises in the AO readout pathway. Our results show that behavioral leakage, representation-level decodability, and AO-verbalizability can come apart, raising a reliability concern for learned interpretability interfaces.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.10342

AgentServe: Algorithm-System Co-Design for Efficient Agentic AI Serving on a Consumer-Grade GPU

Yuning Zhang, Yan Yan, Nan Yang, Dong Yuan

原文摘要

Large language models (LLMs) are increasingly deployed as AI agents that operate in short reasoning-action loops, interleaving model computation with external calls. Unlike traditional chat applications, these agentic workloads require inference serving systems to balance low latency, stable token emission, and throughput under multiple request arrivals from different AI agents. Recent deployments highlight a shift toward running small language models (SLMs) locally on consumer-grade GPUs, driven by privacy, compliance, and cost constraints. When heterogeneous requests overlap on a single GPU, long prefills and short decodes contend for resources, creating head-of-line blocking that destabilizes interactive performance. By analyzing agent workloads, we observe that their execution naturally separates into cold prefills, which process long system prompts, resume prefills, which append tool outputs to cached contexts, and short decodes, which are latency-critical. This mix intensifies contention compared to conventional chatbot serving. We present AgentServe, a single-GPU serving system that ensures stable multi-agent execution under such conditions by isolating prefills from decodes, applying dynamic budgeting to resume prefills, and allocating GPU resources through pre-established CUDA Green Context slots with adaptive control. Evaluation results show that AgentServe significantly improves latency stability while sustaining competitive throughput, achieving up to 2.8x TTFT improvement and 2.7x TPOT improvement over state-of-the-art baselines across different settings.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07301

ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation

Caorui Li, Yangguang Ji, Shuxia Lin, Yu Chen, YiCheng Xiao, Yongliang Wu, Zhenxiang Jiang, Licheng Tang 等 15 位作者

原文摘要

Reinforcement learning has become an effective approach for improving video generation, but its success depends heavily on reliable reward models. Existing methods either map videos directly to opaque scalar scores or generate free-form rationales that are not explicitly optimized as the basis of the final judgment. We propose ArtiVidRM, a verifiable, artifact-as-rubrics video reward model that follows an observe-then-score paradigm. It first identifies visible generation artifacts and organizes them into a structured artifact list, then uses these artifacts as explicit rubrics for quality assessment. This intermediate representation grounds each score in concrete video-level evidence, making the reward more interpretable and informative for optimization. We further introduce a multi-reward reinforcement learning strategy to jointly optimize artifact prediction and quality assessment. The reward decomposes into complementary objectives that evaluate artifact prediction quality, including semantic coverage and prediction efficiency, together with a pairwise preference objective that supervises quality ranking through score differences. By jointly optimizing the intermediate artifact representation and the downstream preference prediction, the model learns to produce informative artifact lists while improving the accuracy of video quality assessment. Experiments show that ArtiVidRM achieves state-of-the-art performance on video preference benchmarks, provides effective signals for video diffusion optimization, and enables artifact-guided refinement of closed-source video generators.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07298

Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens

Seongtae Hong, Youngjoon Jang, Jungseob Lee, Chanjun Park, Heuiseok Lim

原文摘要

Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual token-level information, such as artifacts arising from attention sink behavior. We propose a simple method that prepends trainable [DUMP] tokens to the input during embedding model training. The method keeps the model architecture, pooling strategy, and training loss unchanged, while optimizing the added tokens through the standard contrastive retrieval objective. By introducing trainable prefix positions that interact with regular tokens during encoding, [DUMP] tokens help reduce the influence of residual or uninformative token-level signals on the final retrieval representation. Experiments on standard retrieval and long-context benchmarks show that our method consistently improves over finetuned baselines across encoder and decoder embedding models. Further analysis shows that [DUMP] tokens alter token-level activation and attention patterns associated with low-information tokens. These results suggest that trainable prefix tokens provide a lightweight way to improve retrieval representations.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07297

Code, Commits, and Complexity in the GenAI Era: A Longitudinal Study of Team-Based Capstone Projects

Asma Shakil, Claus Brabrand, Paul Denny

原文摘要

Generative AI tools are now widely available to students, but little is known about how team-based project codebases have changed since they appeared. This matters when project courses use repository activity as evidence of progress and learning. Existing studies have largely examined self-reports, controlled tasks, or short individual assignments, leaving open questions around how student codebases evolve in authentic project settings. We present a ten-semester analysis of N=260 capstone team repositories from 2021 to 2025, spanning pre- and post-AI cohorts. We examine three dimensions: code size (lines of code), code characteristics (comment density, error-handling density, and cyclomatic complexity), and development behaviour (commit volume, edit size, and commit frequency). We find that end-of-semester codebases roughly triple, from about 3.4 KLOC in 2021--2023 to about 10 KLOC in 2024--2025. Code characteristics show a clear decoupling: cyclomatic complexity and error-handling density increase, while comment density does not. Later cohorts commit far more often and in greater volume, but individual commit sizes are largely unchanged, suggesting a shift in development rhythm rather than edit granularity. Most changes appear from 2024 onwards and are not uniformly monotonic. We did not directly observe AI use, so we report these as changes that coincide with increased GenAI availability rather than as effects of AI use. Our findings highlight the need to reconsider how student-produced artefacts are used and assessed in project courses.

cs.CY · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07296

Robust Ranking of Port Impacts from Impending Tropical Cyclones: A Two-Stage Recommendation System

Chenchen Kuai, Shixuan Tang, Chaolun Ma, Xiaoqiang Kong, Xiubin Bruce Wang, Yunlong Zhang, Zihao Li

原文摘要

When a tropical cyclone (TC) threatens several ports, preparedness planning depends on anticipating which ports are likely to be affected and where disruptions may last longest. Limited historical observations at individual ports and uncertainty in landfall location make these relative impacts difficult to estimate. We use a two-stage recommendation framework that first selects candidate ports based on their proximity to the expected landfall location and then ranks them by their estimated number of impact days. Using AIS-derived impact days for 37 ports and 31 TCs in the Gulf of Mexico study region, we compare three ways of representing port--cyclone interactions: pairwise feature interactions, tree-based feature combinations, and explicit feature crosses combined with learned embeddings. In tests on Hurricanes Nicole and Ian, the retrieval stage consistently identifies all observed affected ports under landfall uncertainty. Among the ranking models, Wide & Deep Learning achieves the closest agreement with the observed port rankings. Its mean ranking agreement exceeds that of the distance-based baseline by 85.5% for Nicole and 55.5% for Ian and is less sensitive to uncertainty in the landfall location. These rankings could help port authorities prioritize post-cyclone inspections and allocate recovery resources across ports threatened by the same event.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.17783

Variational Estimators for Node Popularity Models

Jony Karki, Dongzhou Huang, Yunpeng Zhao

原文摘要

Node popularity is recognized as a key factor in modeling real-world networks, capturing heterogeneity in connectivity across communities. This concept is equally important in bipartite networks, where nodes in different partitions may exhibit varying popularity patterns, motivating models such as the Two-Way Node Popularity Model (TNPM). Existing methods, such as the Two-Stage Divided Cosine (TSDC) algorithm, provide a scalable estimation approach but may have limitations in terms of accuracy or applicability across different types of networks. In this paper, we develop a computationally efficient and theoretically justified variational expectation-maximization (VEM) framework for the TNPM. We establish label consistency for the estimated community assignments produced by the proposed variational estimator in bipartite networks. Through extensive simulation studies, we show that our method achieves superior estimation accuracy across a range of bipartite as well as undirected networks compared to existing algorithms. Finally, we evaluate our method on real-world bipartite and undirected networks, further demonstrating its practical effectiveness and robustness.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07295

Provably Efficient Representation Learning for Low-Rank CMDPs

Kaixuan Liu, Guojun Xiong, Shengpu Tang, Wanyun Si, Jian Li

原文摘要

We study representation learning in low-rank Constrained Markov Decision Processes (CMDPs), where both value and reward functions are approximated by a set of unknown representation vectors, and the transition dynamics admit a low-rank factorization. The objective is to maximize expected cumulative rewards while complying with constraints on the expected cumulative utility. To achieve this, we propose \texttt{MFRLC} (Model-Free Representation Learning for Low-Rank CMDP), a model-free algorithm that uses a primal-dual scheme to effectively balance reward regret and constraint violations. To the best of our knowledge, \texttt{MFRLC} is the first representation-learning method for low-rank CMDPs that combines the Least-Squares Value Iteration with Upper Confidence Bound (LSVI-UCB) and primal-dual techniques. \texttt{MFRLC} further enhances value function estimation with bonuses for function approximation and learns the mapping from representations to value functions directly, avoiding explicit estimation of the transition kernel. We prove that, with high probability, \texttt{MFRLC} achieves $\widetilde O(K^{3/4})$ reward regret and cumulative constraint violation over $K$ deployment rounds, independent of the size of the state space. To our knowledge, these are the first sublinear regret and violation guarantees for CMDPs with unknown features.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07294

Householder Motion Embedding: Noise Modulation for Motion-Controllable Video Generation

Tao Jun Lin, Jinhong Ni, Ruyi Zha, Yifu Wang, Xibin Song, Pan Ji, Hongdong Li

原文摘要

Diffusion models for video generation have achieved remarkable success, yet precise motion control under explicit user guidance remains challenging. Recent noise-warping methods introduce temporal correlations by warping the noise according to the user-provided motion signal. However, standard spatial warping generally disrupts the noise's i.i.d. Gaussian structure, requiring distribution correction, such as Jacobian-based correction, but at a substantial computational overhead. We propose Householder Motion Embedding (HME), which encodes the motion signal into the noise through a sequence of Householder reflections that together form an orthogonal transformation applied to each location's channel vector. HME exactly preserves the spatial Gaussian structure within each frame while introducing cross-frame correlations that promote temporally consistent video. HME is agnostic to the network architecture and integrates directly into standard video diffusion fine-tuning pipelines. Experiments on different scenarios show that HME matches or outperforms the state of the art, while achieving a 2.7x speedup over noise warping. These results demonstrate that channel-space Householder transformations offer a principled and efficient alternative to noise warping for motion-controllable video generation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07291

How do Transformers Perform Low-Level Control In-Context?

Ebonye Smith, Aidan Andrews, Phoenix Wilson, Alexis Frias, Ayush Pandey, Gireeja Ranade

原文摘要

One of the remarkable abilities of Transformer-based neural networks is in-context learning. This motivates us to think about "in-context" control. Can we control a system knowing only (1) that it belongs to a particular family of systems and (2) some data on system evolution (provided as the context trajectory) but no specific parameter information? Specifically, we investigate the ability of Transformer-models to perform "in-context" control of unstable, nonlinear dynamical systems, where context consists only of the unforced system dynamics. We leverage a multi-head, GPT-2-style architecture, and we evaluate performance for two classical nonlinear systems -- the cartpole system and the two-link acrobot system, where the system parameters are unknown to the Transformer. We consider a setting where trajectories from an expert controller are available at training time but not at inference time. Here, we identify training techniques that are essential to train Transformers to perform low-level control. Through an analysis over checkpoints, we show that in-context control is possible, and the learned policy performance generally improves as context increases. Furthermore, the Transformer models can generalize to stabilize systems that are out-of-distribution.

cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07289

Patch-Based Generalized Neural Texture Upscaling

Shin Fujieda, Takahiro Harada

原文摘要

We propose a lightweight neural texture upscaling method. A single generalized MLP is trained on a diverse collection of texture patches and integrated into the texture sampling stage, upscaling low-resolution textures on-the-fly at rendering time. Because the model is generalized rather than overfit to specific content, no per-asset training is required - the same model applies to any existing scene without modifying texture data or the asset pipeline. Storing lower-resolution base textures reduces disk footprint, upscaling at sampling time eliminates the need to store high-resolution textures in VRAM, and sharing a single set of model weights across all textures ensures non-divergent GPU execution. We evaluate our method across multiple texture classes, demonstrating consistent improvement over analytic upscaling methods in perceptual quality.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07286

How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering

Melika Sepidband, Jiho Shin, Song Wang, Hadi Hemmati

原文摘要

LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still access repositories through raw files, lexical search, and shell commands, treating code primarily as text. This paper investigates map-based code-representation workflows as a design variable in agentic software engineering, examining how different repository views change agents' retrieval behavior, task success, token use, and latency. In this paper, we study five code-representation workflows: abstract syntax trees, call graphs, module dependencies, documentation-enriched search, and a hybrid workflow that combines them. Each workflow exposes a repository map that the agent can query during a task. We evaluate Claude Code with Haiku 4.5 against a raw-tool baseline on four repository-level tasks: fault localization with LinuxFLBench, repository-level code generation and repair with SWE-bench Pro, test generation with SWT-bench, and security patching with SecBench. The results show that representation workflows are most useful as token-saving tools when localization is the bottleneck, while their success gains narrow when the decisive step is patch or test authoring. On LinuxFLBench, all five workflows improve recall@10 over the baseline (0.757-0.829 vs. 0.717) and reduce token usage by 25-39%. On SWE-bench Pro, resolution remains close to the baseline (44.3-50.6% vs. 49.0%) while token usage drops by 17-26%. On SecBench, Callgraph has the highest patch-resolution rate in this sample (34.3% vs. 28.9%) and uses fewer tokens, but all workflows increase latency. On SWT-bench, Hybrid and Docs have the highest reproducing-test rates in this sample (47.8% and 47.2% vs. 44.7%), but all workflows use more tokens and take longer. Overall, map-based workflows change both what the agent inspects and how much it spends, but their benefits are task-dependent rather than universal.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07283

Encoding and Propagation of Grammatical Number in Large Language Models

Jacob Solinsky, Serguei Pakhomov

原文摘要

Sparse autoencoders (SAEs) have become an increasingly popular means of translating Large Language Model (LLM) hidden state vectors into a human-comprehensible list of features or symbols. As such, SAEs may provide insight into an LLM's knowledge representation and internal ``mental'' grammar - topics of pragmatic interest for mechanistic interpretation of AI behavior and of theoretical interest for the study of in silico representations of human language. Language models with fewer than 100M parameters, trained on small corpora, nonetheless exhibit strong grammatical competence and discourse coherence, despite producing content of limited reliability. We use SAEs that we trained on one such model (Pythia-70M) to conduct an in-depth examination of how a single grammatical phenomenon, number agreement, is represented and processed in an LLM. We demonstrate the mechanism and the methodology by which SAEs can be used to find and propagate ``plural noun'', ``plural matrix subject'', and ``generate a plural verb'' features which cause the LLM to produce plural verb forms such as ``are'', ``do'', or ``have'' instead of ``is'', ``does'', and ``has'' in response to prompts such as ``the men in the park''. We show that intervening to remove these features from the hidden states of plural subject noun tokens causes the model to produce singular verbs instead, and vice versa. We also show that corresponding ``singular noun'' and ``generate a singular verb'' features are not as effective for this task. This asymmetry suggests that Pythia-70m makes use of a privative representation of grammatical number in English. These findings replicated with larger LLMs Gemma-2-2b and Llama-3.1-8b yielded similar results. Our main contribution is a novel approach to the use of SAEs to understanding how LLMs encode human language that addresses a number of technical and methodological challenges.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07282

Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion

Mahdi Arab Loodaricheh, Anita Raja, Indranil SenGupta

原文摘要

Extreme market movements are scarce, heterogeneous, and difficult to learn from imbalanced historical data. We study whether generative augmentation can improve the representation and classification of CVaR-labeled rare financial windows while retaining the complementary structure exposed by different financial representations. Each market window is expressed through three aligned modalities: structured market variables, a spatial image transformation, and a sequence of portfolio returns. Separate variational autoencoders map the modalities to compact latent codes, and a class-conditional diffusion model learns their joint latent distribution. Conditional Value-at-Risk (CVaR) provides a risk-aware definition of rare windows and directs generation toward the minority regime. Across four window lengths on U.S. technology equities, the resulting synthetic samples improve fidelity and support relative to tabular diffusion baselines. An XGBoost classifier trained with real and generated samples attains AUCs of 0.953 - 0.960, exceeding both tabular generators and the corresponding real-only baselines. These results show that multimodal latent generation can provide useful synthetic stress scenarios for data-scarce financial risk models.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07280

Degree profiles of uniform polynomial consequences: Linear lower bounds for Nullstellensatz and Polynomial Calculus

Søren Riis

原文摘要

This paper proves asymptotically optimal linear degree lower bounds for Nullstellensatz and Polynomial Calculus, yielding a four-way polynomial-versus-exponential proof-size classification for uniform polynomial consequences over fields of positive characteristic. The size bounds use full, explicit coefficient lists, including zeros. Apart from a fixed finite initial range, exactly one of four cases occurs: $\mathrm T_1$, bounded degree; $\mathrm T_2$, degree at least linear in the universe size $n$; $\mathrm T_3$, constant degree on some residue classes and at least linear degree on the others; or $\mathrm T_4$, infinitely many recurring finite degrees, with bounded-degree subsequences and finite $Ω(n)$ peaks at arbitrarily large sizes. Thus the size patterns are polynomial bounds, exponential lower bounds, a periodic mixture, or polynomial subsequences with finite exponential peaks, respectively. Underivable targets have degree $\infty$, and both proof systems assign the same type. The result strengthens my 2008--2009 refutation classification and extends it to uniform consequences. The proof uses degree-preserving lifting with onset and period bounds linear in the degree. A common $p$-adic hardness spectrum describes the four types topologically. Distinguishing any two types is undecidable already for refutations. The linear degree bounds, four-way classification and pairwise undecidability results have been formalised and verified in Lean. The Lean formalisation, verification records and an accompanying tutorial are available in the supporting materials (https://doi.org/10.5281/zenodo.23965838).

cs.CC · cs.LO · math.LO

查看论文
arXiv ↗PDF ↗