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

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 05:40 — 2026-11-17 05:40(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58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。

24,106 已收录论文20,158 AI 相关7,049 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 24,106 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.04405

DR-LiteNet: A Lightweight Explainable Hybrid CNN Framework for Imbalanced Diabetic Retinopathy Grading via Adaptive SMOTE Fusion

Nishi Kanta Paul, Md Shihabul Islam Shovo, Audrija Chowdhury, Israt Jahan Esha

原文摘要

Automated diabetic retinopathy (DR) grading from colour fundus photographs is held back by two compounding challenges: severe class imbalance across five severity grades and the heavy computational cost of large scale architectures in resource constrained clinical settings. We introduce DR-LiteNet, a dual branch hybrid convolutional neural network that tackles both problems at once. The CNN branch extracts 1,280 dimensional deep features through EfficientNetB0, while the handcrafted (HC) branch produces a compact 51 dimensional lesion descriptor capturing vessel density, exudate intensity, texture entropy, and HSV colour histograms. Concatenating both branches yields a 1,331-d hybrid embedding, on which Adaptive SMOTE (ADASYN) is applied during training to synthesise minority class feature vectors, correcting distributional skew without touching the image space. A two phase training protocol first warms up the classification head on balanced features, then fine tunes the full network end to end. Grad CAM saliency maps deliver post-hoc clinical explainability. Tested on APTOS 2019 under five fold stratified cross validation, DR-LiteNet reaches 88.77% +/- 0.61 accuracy, a quadratic weighted kappa (QWK) of 0.884 +/- 0.010, and a macro F1 of 0.792 +/- 0.008 with only 4.69 M parameters beating ResNet50 (23.5 M) by DeltaQWK = 0.022 while staying practical on a single Google Colab T4 GPU. The source code of this project is available at: https://github.com/Nishi-Kanta-Paul/DR-LiteNet.

cs.CV

版本更新 · v3arXiv:2511.16145

Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection: An Empirical Study and Minimalist Baseline

Zhijie Zhong, Zhiwen Yu, Kaixiang Yang, Yongheng Liu, Jun Jiang, C. L. Philip Chen

原文摘要

Time series anomaly detection (TSAD) research predominantly focuses on unsupervised architectures to model normal data dynamics under label scarcity. However, practical deployments frequently archive historical operational incidents, questioning whether continuous unsupervised architectural scaling remains the most cost-effective pursuit. In this paper, we empirically quantify the trade-offs between supervisory signals and model complexity. We introduce STAND, a deliberately minimalist supervised baseline based on bidirectional recurrent encoding. Across five benchmark datasets evaluated under a strictly disjoint out-of-sample temporal protocol, minimalist supervised models achieve competitive or superior accuracy relative to complex unsupervised alternatives. Furthermore, controlled label-scaling and few-shot evaluations confirm that these supervisory advantages persist under constrained historical event budgets, while STAND exhibits higher prediction certainty and sharper event delineation than reconstruction-based baselines. These findings encourage the TSAD community to complement algorithmic complexity with data-centric label utilization when annotations are accessible. The source code, benchmark datasets, and an extended Supplementary Document are publicly available at https://emorzz1g.github.io/STAND.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.02791

PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models

Junyu Lin, Mengjie Wu, Yonghao Dong, Yuchuan Fu, Jinfeng Li, Xiaodan Li, Xiaohan Yuan, Yicheng Liu 等 14 位作者

原文摘要

As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the generation process has become a critical challenge. We introduce PGuard, a native, streaming, and plug-in guardrail that transforms safety monitoring from an external serving dependency into an integrated capability of the backbone model. PGuard directly leverages the backbone's intermediate representations for token-level safety detection, without altering its original inference pathway or generation behavior. Specifically, dynamic layer gating selectively aggregates residual-stream representations across layers to extract safety-relevant signals during both prefill and autoregressive decoding. To balance detection accuracy and computational efficiency, PGuard supports multiple representation-modeling architectures, including a lightweight stateless variant and sequence-aware variants built on multi-scale causal EMA-attention and GRU-based recurrent modules. Its design also accounts for the execution characteristics of LLM serving frameworks, such as SGLang, optimizing computation and data access to minimize additional runtime and synchronization overhead. As a result, PGuard incurs only 0.82-2.26% end-to-end overhead on the hundred-billion-parameter backbone Qwen3.5-122B-A10B served by SGLang. Extensive evaluations across more than 30 benchmarks spanning text and multimodal safety, jailbreaks, cyber and CBRN risks, multilingual scenarios, and real-world traffic demonstrate state-of-the-art performance among native guardrails. On text queries with Qwen3.5-9B, PGuard achieves an average F1 score of 0.836, approaching dedicated external guardrails, while supporting deployment-time configuration of category-specific thresholds and enforcement actions.

cs.CL

新论文 · v1arXiv:2611.04401

LiquidCP: Decoupling Attention Tasks from Communication and Kernel Boundaries in Context Parallelism

Hongyu Chen, Yikang Ruan, Yuhai Long, Ziyu Huang, Yiyu Luo, Liukun Yu, Yangjie Zhou, Zihan Liu 等 17 位作者

原文摘要

Context parallelism (CP) partitions long sequences across GPUs for LLM training and inference. For variable-length training and full prefill, attention-balanced placement can leave token loads uneven, while ring execution repeats overhead at each computation and communication step. In stage-serialized decode CP (DCP), long-running tasks delay dependent work and leave substantial GPU hardware idle. We propose LiquidCP, which unifies training and inference through a common model of Transfer, Compute, and Reduction tasks with tile-level dependencies, decoupling attention tasks from communication and kernel boundaries. For training and full prefill, MegaRing incorporates BuddyRing placement to balance attention and token loads, and coalesces ready KV regions during forward attention to amortize overhead. For decoding and mixed batches, MegaDCP selects history-KV splits by jointly modeling the completion of attention and its dependent reductions. A shared persistent GPU-resident engine executes both designs. Compared with the fastest baseline per configuration on eight H100 GPUs, MegaRing achieves geometric-mean core-attention speedups of $1.23\times$ forward and $1.18\times$ backward, and accelerates a Transformer layer by $1.08$--$1.16\times$. MegaDCP achieves geometric-mean core-attention speedups of $1.20\times$ for decode-only and $1.35\times$ for mixed batches. In vLLM serving with KV prefix cache, it achieves an average time-to-first-token speedup of $1.22\times$.

cs.DC

新论文 · v1arXiv:2611.04400

Averaging Collusion Breaks Traceability in Personalized Neural Audio Watermarking

Yangming Liu, Haiyun Li, Dongfu Song, Ziang Xu, Jiehui Luo, Yining Zhang, Zhiyong Wu

原文摘要

Personalized neural audio watermarking systems embed user-specific payloads into audio to trace the user associated with a leaked or misused copy. Existing evaluations mainly assume access to a single personalized copy, but real-world distribution may expose multiple copies of the same recording. We find that simple sample-wise averaging breaks traceability: averaging only two copies produces tracing-failure rates of 87.7-99.7% across the five systems while largely preserving audio quality. Decoder outputs show distinct responses to coalition payload composition across systems, with high majority agreement in TimbreWM but substantially lower agreement in WMCodec. In a more sophisticated payload-aware setting, mixture weighting can further steer the decoder toward a selected nonmember, achieving a target success rate of 92.3% in TimbreWM. Preliminary confidence screening rejects many collusion-induced assignments while retaining most valid single-copy outputs. Code and results are available at https://github.com/Silwan5z/neural-audio-watermark-collusion-attack. This work highlights multi-copy traceability as an additional evaluation dimension for personalized neural audio watermarking alongside conventional single-copy robustness.

cs.SD · cs.CR

新论文 · v1arXiv:2611.04399

Silent Instrument Errors Reorder Agent Leaderboards

Yangze Liu

原文摘要

On a public agent leaderboard, a general-purpose agent trails a scaffold built for an airline customer-service benchmark by 13 points on the tasks that touch its database, and a reader could conclude that generality costs accuracy. The gap comes from the grader. The general agent often ends its conversations in a way that never triggers grading, so only about half of its episodes were scored and the rest were stored as failures. Grading the ungraded half under the benchmark's own rule closes the pooled gap, without rerunning any agent. We audit two carefully maintained public leaderboards, HAL and tau2-bench, from their published artifacts alone and find three more instrument errors. A cost column counts nested model calls twice, unevenly across rows. Archived trajectories record grader-written actions as agent actions. Re-grading saved trajectories under a newer evaluator is itself a new measurement: a correct and announced fix reorders a leaderboard, and a mode check that misreads four files collapses their scores by 59 to 82 points while printing no error. Each produced a plausible number, and the HAL maintainers confirmed their three within five weeks. Together the cases show that the infrastructure of agent evaluation, meaning the code that grades, logs, replays and versions an evaluation, is part of the measurement and fails silently, so scores and orderings can move with no visible sign. These failure modes follow from how agent evaluation pipelines are built, and those pipelines change as fast as the agents they measure, so we expect more of them elsewhere. We propose cheap checks that expose the instrument: report the graded fraction, aggregate cost from root spans, tag the provenance of every recorded action, and pin evaluator versions with a published re-grade diff.

cs.AI · cs.SE

版本更新 · v3arXiv:2509.10080

BEVTraj: Map-Free Multimodal Trajectory Prediction with Sensor-Derived BEV Context and Sparse Goal Reasoning

Minsang Kong, Myeongjun Kim, Sang Gu Kang, Hejiu Lu, Yupeng Zhong, Sang Hun Lee

原文摘要

Trajectory prediction is a key task in autonomous driving, where a model must forecast plausible future motions of surrounding agents from dynamic histories and scene context. Many recent methods use high-definition (HD) maps to provide explicit road topology and semantic constraints, but such maps are costly to maintain, geographically limited, and difficult to update in changing environments. This paper presents Bird's-Eye View Trajectory Prediction (BEVTraj), a map-free trajectory prediction framework that directly uses BEV features constructed from raw multi-sensor data. Since sensor-derived BEV features are dense and only implicitly structured, BEVTraj employs deformable attention to selectively aggregate agent-relevant spatial context from sparse locations rather than processing the entire BEV grid uniformly. In addition, a Sparse Goal Candidate Proposal module combines overlapping mode-wise anchor clusters with attention-based goal prediction to generate compact, scene-adaptive goal hypotheses. These goals are decoded and iteratively refined into multimodal trajectories, while trajectory-aware mode scoring and temporal consistency modeling improve confidence estimation and suppress abrupt, physically implausible refinement updates. Experiments on nuScenes and Argoverse 2 Sensor show that BEVTraj achieves competitive results under a map-free setting without using pre-built HD maps, while ablation studies and qualitative analyses illustrate the roles of BEV context aggregation and sparse goal reasoning. The source code is available at https://github.com/Kongminsang/bevtraj.

cs.CV

版本更新 · v3arXiv:2610.27550

Lower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low Curvature Trace

Yuxing Peng, Zhiqing Tang, Weijia Jia

原文摘要

Low curvature trace, an effective rank condition, is a common explanation for why randomized zeroth-order methods scale to high-dimensional tasks such as language model fine-tuning. Can deterministic methods achieve the same savings? We show that they cannot. We study finding $\varepsilon$-stationary points of $L$-smooth nonconvex functions on $\mathbb{R}^d$ from exact function values, assuming that below the starting value the Hessian is dominated by a fixed matrix with trace at most $LE$; this is a fixed-matrix form of the effective rank condition used to explain zeroth-order fine-tuning. When $ET\le d$, the Gaussian two-point method that such fine-tuning uses needs only $O(ET)$ calls if it rejects steps that raise $f$, where $T=LΔ/\varepsilon^2$ is the iteration count of gradient descent from initial gap $Δ$, and we prove that every randomized method needs $Ω(ET)$ calls, so this cost is optimal up to constants. In contrast, every deterministic method needs $\widetildeΩ(d\min\{T,\sqrt{ET}\})$ calls, and adaptive subspace search attains $O(d\min\{T,\sqrt{ET}\})$: a deterministic method pays about $d$ calls per discovered direction, and the trace budget allows about $\sqrt{ET}$ directions. Determinism thus multiplies the cost by a factor of order $d/(E+\sqrt{ET})$ up to logarithmic factors, which grows linearly with $d$ for fixed $E$ and $T$; once $E$ exceeds $T$ by a logarithmic factor, deterministic methods need $Ω(dT)$ calls, as without any trace budget. Our lower bounds hold for $C^\infty$ functions with the matrix bound on all of $\mathbb{R}^d$, even when each call also returns gradient projections priced by rank.

cs.LG

新论文 · v1arXiv:2611.04397

Auditing Targetless Camera-LiDAR Extrinsic Correction before Recursive Use

Bo Ma, Weiqi Yan

原文摘要

Camera-LiDAR fusion repeatedly uses an extrinsic transform in projection, association, and recursive state estimation. We study whether a targetless correction should be admitted to a downstream consumer only after separate audits of correction quality, confidence ranking, and recursive risk. Our log-disjoint protocol evaluates these stages under synthetic extrinsic drift on Argoverse 2 and treats cross-dataset and odometry experiments as bounded diagnostics. On 27 test-split logs, single-frame Canny alignment is harmful in the mild tier. Multi-frame alignment improves severe-tier rotation by 2.52 degrees but worsens translation by 0.177 m; its declared joint error-magnitude improvement is also negative (-0.158, 95% CI [-0.223, -0.098]), so the rotation gain is not a six-degree-of-freedom correction success. A zero-injection check moves away from the true extrinsic, and solver-disagreement AUROC on selected splits does not yield a validated nonzero-coverage risk-coverage operating point. In a 15-log final system role, the locked conservative policy admits no candidate and equals Raw, whereas Always-correct increases trajectory error. These results support an auditable separation of correction, confidence, and recursive contamination; they do not establish a deployable calibration gate, positive odometry or SLAM improvement, map consistency, or closed-loop safety.

cs.CV

新论文 · v1arXiv:2611.04395

Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior

Renee Jia, Jinzhou Wu

原文摘要

Fine-tuning data can include metadata that predicts the correct answer, such as a reward-model score or a quality label. We ask whether a model learns to rely on this metadata even when every training label is correct. We fine-tune 7-9B open-weight models from three families on multiple-choice questions in which (Reward: 5) always marks the correct option; when this annotation is moved to a wrong option at test time, models select that option on 97-100% of CommonsenseQA items. Removing it leaves most answers correct, so evaluation without it misses the dependence. Cue-following rises sharply with training-time reliability and develops even with neutral or nonsense annotation words, although test-time wording affects its strength. A Qwen3 experiment also finds cue dependence in option-letter scores after direct preference optimization. Audits can test for this dependence by moving or removing visible annotations while holding the task and correct answer fixed.

cs.AI

版本更新 · v2arXiv:2611.01048

Infinite Worlds from One Example: What Local Generators Must Share

Amin Najafgholizadeh, Mohsen Afsharchi

原文摘要

Seeded noise lets games generate any region of an unbounded world on demand. We ask what such a generator needs when every small window must come from one example, the constraint behind Wave Function Collapse. The difficulty is that local constraints can require agreement over arbitrary distances: in a brick wall, each row keeps its place between the mortar lines. We study local generators, each cell a fixed function of the randomness near it. When the constraints carry a quantity that varies across the example, no generator that applies one rule, ignoring position, to independent randomness at every cell can be both exactly valid and faithful to the example's statistics, however far each cell reads. At radius r, staying faithful forces forbidden windows at a density of at least order 1/r, and a construction attains this order. To vary the quantity between exactly valid worlds, a generator needs randomness shared along its direction. We give a finitely checkable condition under which row types drawn from the seed and the position modulo a fixed period suffice for exact validity without learning. A search over the example's patches certifies these quantities and names the input each needs. Across 52 public examples of Wave Function Collapse and 27 from other implementations, it certifies only examples where a learned generator on independent randomness stays far from valid after repair. Given that input, a neural cellular automaton and a diffusion model become valid on 10 and 8 of the 12 certified examples that receive one, and on none from independent randomness. Valid means at most one forbidden window in a thousand after repair. With octaves of seeded noise elsewhere, the automaton is valid on 45 of the 52 public examples and 21 of the 27 from other implementations, and repair keeps random access.

cs.LG · cs.GR

版本更新 · v3arXiv:2610.33381

The Cost of an Unknown Horizon for the Last Iterate of Clipped SGD under Heavy-Tailed Noise

Yuxing Peng, Zhiqing Tang, Weijia Jia

原文摘要

We study the last iterate of clipped SGD, and of every rule that queries its current iterate and steps along the resulting stochastic gradient, when training is stopped at a data-dependent time, so that guarantees must hold at all times simultaneously. On smooth convex objectives under heavy-tailed noise with a bounded central $p$th moment, $1<p\le2$, we determine the optimal time-uniform rate of these rules. A clipped SGD schedule without horizon or confidence inputs attains $\tilde O(t^{-β_p})$ at all times, with $β_p=2(p-1)/(3p-1)$, also almost surely, and no such rule attains $\tilde O(t^{-r})$ for any $r>β_p$, even with adaptive step sizes and thresholds. This rate lies between the optimal rate $O(T^{-α_p})$ for a known horizon $T$, $α_p=(p-1)/p$, and the previous time-uniform rate $\tilde O(t^{-2(p-1)/(3p)})$ (Chezhegov et al., ICLR 2026); under finite variance, the exponents are $1/2$, $2/5$, and $1/3$. Their conjecture that a better schedule reaches the optimal rate thus holds with a known horizon (Liu; Jiang et al.) but fails without one. Querying gradients at the running average attains $\tilde O(t^{-α_p})$ at all times, whereas heavy-ball momentum with geometric forgetting and polynomially bounded steps cannot improve on $β_p$.

cs.LG

新论文 · v1arXiv:2611.04393

Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents

Ilan Zendel, Matan Levy, Stav Cohen, Avi Mendelson, Amit LeVi

原文摘要

LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security literature models this threat as instruction injection, in which an adversary writes a command into retrieved content and deployed defenses learn to recognize command syntax. We show that an attacker can instead steer an agent through the agent's own harm-avoidance. A single fabricated hazard, written as an ordinary review, leads the agent to disqualify the legitimate options and select the attacker's target by its own reasoning, with no command for a detector to recognize. We call this voluntary servitude. These payloads steer agents about as often as instruction injection (60.4% vs. 66.0%), and deployed injection detectors score them as benign, so behind a filter they are 1.7-4.4x more effective. We measure this at the generation stage across six models and ten consumer-service domains, for three attack families, and show that it transfers to production browser agents, outperforming instruction injection, and to a retrieval pipeline (1.0-57.0% end-to-end success, depending on the retriever). We then show that a corroboration requirement added to the agent's instructions removes roughly 95% of the exposure against a non-adaptive attacker without retraining. With the requirement in place, the agent still reads the planted hazard and no longer acts on it.

cs.CR · cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.04392

Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware

Yeonseok Lee

原文摘要

Vision-Language-Action (VLA) models generalize across tasks, but their autoregressive decoders need sequential forward passes in proportion to the action horizon, each bounded below on embedded aerial platforms by streaming billions of parameters from memory. We present Aero-VPA, a lightweight Vision-Predictor-Action architecture for 3D navigation on edge hardware. A compact RGB-D Vision Transformer and a five-head ensemble predictor, trained without pixel reconstruction, forecast the next latent state; a Conditional Flow Matching solver generates a velocity and yaw-rate chunk in two Euler steps, so each decision takes five sequential network evaluations; and the ensemble dispersion drives an uncertainty fallback. Version 1 specified the architecture, deployment and protocol without results. This version reports the first closed-loop evaluation: PX4 software-in-the-loop simulation of quadrotor missions in procedurally generated forests. Behaviour cloning failed on all 60 missions despite open-loop errors of 0.02-0.04 m/s: the policy copies its last command, a copycat form of causal confusion. DAgger with a privileged, safety-gated supervisor gave the first successes but plateaued at 11.1-21.1% across six checkpoints. A map-free runtime shield with a 15 s depth memory, barrier constraints, a cap on motion outside the 73-degree field of view and backoff along the flown path raised the first DAgger policy's success on 180 paired missions from 21.1% to 52.2% (95% CI [45.0, 59.4]; exact McNemar p = 1.2 x 10^-10) and cut its crashes from 72.2% to 22.2%, while timeouts rose from 2.8% to 23.3%. All six checkpoints gained 30.0-34.4 percentage points, at mean speeds of 1.16-1.36 m/s. The code (https://github.com/ylee-sling/Aero-VPA), the trained policy (72.6 MB, https://huggingface.co/ylee-sling/aero-vpa) and the full benchmark dataset are public.

cs.LO · cs.LG · cs.RO

新论文 · v1arXiv:2611.04391

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

Junhyeong Park, Wook Jung, Taeyoung Kim, Huiwon Jang, Jinwoo Shin

原文摘要

Pretrained Vision-Language-Action (VLA) policies provide a strong starting point for deployment, but adapting them to a target robot and environment still requires costly embodiment-specific demonstrations. Human demonstrations are far easier to collect, yet directly leveraging them is challenging due to the substantial human-robot embodiment gap, particularly when the underlying VLA has been pretrained primarily on robot data. We introduce H2RB (Human-To-Robot Bridge), a human-robot co-training framework for adapting pretrained VLA policies from unpaired human and robot demonstrations. H2RB bridges the embodiment gap at both interfaces: geometry-anchored alignment grounds human and robot observations in a compatible representation, while a decoupled-decoder tokenizer shares action latents without forcing both domains through a single action mapping. This design allows human demonstrations to provide useful behavioral supervision while retaining the rich visual, semantic, and control priors of the pretrained VLA. Across real-world tasks, H2RB substantially improves object transfer performance from 8.0 to 51.8 and enables skill transfer to score 62.7, in settings where co-train baselines totally fail to transfer human-demonstrated skills. The benefit also persists under object-placement shifts, improving out-of-distribution transfer from 6.0 to 45.3. H2RB suggests a way for human demonstrations to serve as a scalable supervision source for adapting pretrained robotic policies, reducing the dependence on costly target-robot data collection.

cs.AI

版本更新 · v2arXiv:2602.00879

Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs

Hao Mark Chen, Zhiwen Mo, Royson Lee, Qianzhou Wang, Da Li, Shell Xu Hu, Wayne Luk, Timothy Hospedales 等 9 位作者

原文摘要

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is constrained by an expert explosion: as the number of tokens generated in parallel increases, the number of distinct experts activated grows nearly linearly. This results in substantial memory traffic that pushes inference into a memory-bound regime, negating the efficiency gains of both MoE and parallel decoding. To address this challenge, we propose Dynamic Expert Sharing (DES), a novel technique that shifts MoE optimization from token-centric pruning and conventional expert skipping methods to sequence-level coreset selection. To maximize expert reuse, DES identifies a compact, high-utility set of experts to satisfy the requirements of an entire parallel decoding block. We introduce two innovative selection strategies: (1) Intra-Sequence Sharing (DES-Seq), which adapts optimal allocation to the sequence level, and (2) Saliency-Aware Voting (DES-Vote), a novel mechanism that allows tokens to collectively elect a coreset based on aggregated router weights. Extensive experiments on MoE dLLMs demonstrate that DES reduces unique expert activations by over 55% and latency by up to 38%, while retaining 99% of vanilla accuracy, effectively decoupling memory overhead from the degree of parallelism.

cs.LG

新论文 · v1arXiv:2611.04390

Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark

Jiaming Zhou, Pei Zhang, Shiwan Zhao, Zhijun Wang, Baosong Yang, Yong Qin

原文摘要

Successful multi-turn voice interaction requires models to retain information from earlier turns, follow persistent instructions, and track revisions to conversational state. These abilities are usually evaluated from transcripts, leaving open whether successes demonstrated from text carry over when the same turns are spoken, and whether this transfer is consistent across languages. We introduce Omnilingua-AudioMC, a strictly parallel multilingual extension of Audio MultiChallenge, to study this question. The benchmark contains 354 conversations and 1,404 rubric items across ten languages, with content, turn structure, cross-turn dependencies, and evaluation criteria aligned across transcript and speech conditions. Across six speech-language models, the shift from reference transcripts to direct speech input is strongly model- and language-dependent: models with similar transcript performance can diverge substantially under speech, and their relative strengths across languages can change. Paired rubric-level analysis shows that aggregate transcript-speech gaps can obscure which conversational requirements are preserved, because losses of transcript-demonstrated successes can be offset by gains on other items. Replacing preceding user turns, the current turn, or both with model-generated transcripts localizes recoverable degradation: for the two models with the largest gaps, history substitution yields a larger macro-level improvement than current-turn substitution in all ten languages, while the strongest direct-speech model gains little from either. These results show that transcript performance is an unreliable proxy for multilingual spoken conversational ability and identify the representation of preceding spoken context as an important source of recoverable degradation. Our code is publicly available at https://github.com/QwenLM/Omnilingua-Bench/tree/main/Omnilingua-AudioMC.

cs.CL

新论文 · v1arXiv:2611.04389

Spin Spherical Fourier Neural Operators: Efficient Equivariant Learning for Vector and Spin Fields on the Sphere

Kevin Mulder, Matthew A. Price, Eirini Leftaki, Jason D. McEwen

原文摘要

Many fields of physical interest on the sphere, such as wind, the polarisation of the cosmic microwave background and the shear of weak gravitational lensing, are spin fields, whose values change phase when the local frame rotates. We extend spherical Fourier neural operators (SFNOs) to fields of any spin, through lifted spherical convolutions that are exactly rotationally equivariant. Lifting spin fields to Mackey functions on the rotation group provides the conceptual framework, while computation is performed exactly and efficiently through their harmonic representation and by appealing to sampling theorems on the sphere and rotation group. We construct spin SFNOs (S$^2$FNOs) from these building blocks. We demonstrate empirically that rotational equivariance holds to machine precision for these layers. We achieve state-of-the-art performance on existing benchmarks, and introduce new benchmarks on which spin-aware models outperform their scalar counterparts.

cs.CV · astro-ph.IM · cs.LG

新论文 · v1arXiv:2611.04386

StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models

Chenru Wang, Xuanyang Zhang, Yucheng Han, Wenbo Nie, Wei Cheng, Xianfang Zeng, Gang YU, Chi Zhang

原文摘要

A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through multi-teacher on-policy distillation, then serves as a fixed teacher for step distillation. Every full-step model we evaluate scores lower once compressed, and the second stage cannot begin until the first finishes. We introduce StepX-OPD, which merges the two stages: one student acquires every capability while learning to sample in a few steps, so frozen specialists supervise it on the states its own rollout visits rather than on a longer trajectory it never runs. Because a decomposition of the rollout's KL weights velocity mismatch most heavily near the clean end, we also regress the student's velocity on the low-noise part of the rollout. Separately, we find that capability integration makes models write prompt words into images on prompts that never asked for text, and we give a variant that lowers it. We evaluate on SD3.5-Medium and FLUX.1-dev across instruction following, text rendering, image quality and human preference. On both architectures, StepX-OPD attains the highest normalized average score among the four-step methods compared and exceeds the forty-step Flow-OPD model, and on SD3.5-Medium it trains with about 37% fewer GPU-hours than sequential DiffusionOPD followed by step distillation.

cs.CV

版本更新 · v2arXiv:2610.33020

Mine or Yours? Self-Other Confusion in Latent LLM Communication

Yunlong Xu

原文摘要

If two minds were linked, would each still know which thoughts are its own? Language models are increasingly linked in this way: instead of exchanging text, one model reads another's key-value cache. Systems that join a foreign cache to the receiver's own use one of two layouts: the cache lies over the receiver's own context, at the same token positions, or in front of it. We give two copies of one model different private priorities and link them in both layouts. With the cache over its own context, the receiver gives a fact found only in its partner's cache in every answer. Yet in about half of its answers it gives the partner's priority as its own, in both Qwen3-4B and Llama-3.1-8B: as often as a receiver that ignored whose priority was whose, although the text in the cache names its owner. With the same cache moved in front, this falls to 5% in Qwen but only to 43% in Llama, although both models nearly stop naming the partner's priority as the one they are using. Where the cache sits matters, yet neither layout in use protects both models. Fewer such errors do not mean better attribution: once the cache is moved, the receiver names the partner's priority as the partner's less often, not more, and its report of an inserted memory cannot tell the partner's cache from a copy of its own. In short, shared caches deliver content but not ownership.

cs.CL · cs.AI

版本更新 · v3arXiv:2607.27384

Same Illness, Different Voice: Clinical Language Models Lose Accuracy When Patients Speak for Themselves

Prabhjot Singh, Pritam Deka, Vijay Chennareddy

原文摘要

Clinical language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own. We pair 1,000 MedQA cases with three audited retellings (clinical, socioeconomic, cultural) and test 12 open models. Every model is less accurate when the patient speaks in a marked voice, by 9.6 points on average (95% CI 8.2 to 11.0), with no detectable shrinkage at larger scale. Matched controls trace the penalty. Generation temperature does not explain it, a plain first-person paraphrase that states every fact accounts for 2.4 points, and attaching the original vignette to the marked narrative recovers 7.0. We read this mainly as a failure to use facts expressed in patients' own words, not as a reaction to social cues, although our voices bundle both. Chain-of-thought and explicit debiasing instructions together close about a fifth of the gap. Having the same model first restate the account as a clinical vignette halves it and raises marked-voice accuracy by 3.9 points, whereas a structured-schema pipeline closes the same gap but is 7.1 points less accurate than the rewrite. Rewriting also invents plausible details, which we quantify. Code, data and analysis scripts: https://github.com/prabhjotschugh/narrativeshield-sdoh-medqa

cs.CL · cs.AI

新论文 · v1arXiv:2611.04383

Disposable Implementations: What Is Software Engineering For?

Christoph Treude

原文摘要

Existing implementations are usually maintained for most of their life and replaced only as an exception. Coding agents may change that. If agents can produce new implementations from requirements, tests, architectural constraints, and operational records that survive replacement, changing a system may no longer require modifying its existing codebase. We call this process regeneration. An implementation is disposable when regeneration becomes a routine alternative to maintenance. Regenerating and verifying a clean implementation from current requirements and tests may be cheaper than having agents navigate (and potentially compound) existing technical debt, and could eliminate much of that debt. Yet existing code may contain knowledge absent from the preserved artifacts, including safeguards introduced after failures and assumptions that were never documented. A regenerated implementation may pass the available tests and still lose behavior that matters in production. This leaves open how to establish continuity across replacements and whether regeneration reduces maintenance effort or shifts it to the artifacts and processes that support it. We examine these questions through an exploratory review of practitioner literature. Published examples show that agents can replace existing implementations, but do not establish that repeated regeneration is safe or economical. If implementations become disposable, what should software engineering preserve?

cs.SE

新论文 · v1arXiv:2611.04381

On the Hardness of Approximate Quantum Circuit Membership and Optimization

Adam Husted Kjelstrøm, Jaco van de Pol, Andreas Pavlogiannis

原文摘要

Quantum circuit optimization is an indispensable component of the quantum software stack, used to reduce noise, maximize performance, alleviate costs of quantum error correction, or target specific hardware. A related problem is approximate membership: for a fixed set of unitaries $S$, decide whether a given circuit $C$ is within distance $\varepsilon$ of a unitary in $S$ under some metric $m$. Membership is a special case of optimization, where $S$ is a set of unitaries implementable at no cost (e.g., with noise-minimal circuits, or without magic states). Janzing, Wocjan, and Beth (Int. J. Quantum Inf., 2005) showed that, for the operator metric, the case $S=\{I\}$ (approximate identity) is QMA-complete when $C$ is promised to be either close to the identity or far from it. We generalize this setting in three directions: (i) promise-free inputs, (ii) besides $S=\{I\}$, sets $S$ containing only Clifford unitaries, or only generalized permutation matrices (i.e., no superposition), and (iii) the trace-based, spectral, and operator metrics. We show that, in all cases, approximate membership is PP-hard for wide ranges of $\varepsilon$, provided $C$'s gate-set can implement Clifford+T, as the gate-sets of standard hardware do. If $S=\{I\}$, or if $S$ contains only generalized permutation matrices, $I\in S$, and $m$ is a trace-based distance, PP-hardness holds for all non-trivial $\varepsilon$. If $S=\{I\}$ and $m$ is a trace-based distance, PP-hardness holds even for circuits over classical-reversible gate-sets. Our results indicate that approximate membership is harder over promise-free inputs than the QMA-complete promise version, and that this hardness persists across quantum resources (any gates, non-Clifford, superposition) and distance metrics. They directly imply PP-hardness of circuit optimization when minimizing total, non-Clifford, or superposition gate depth or count.

quant-ph · cs.CC

新论文 · v1arXiv:2611.04380

Twice as Fast, Until It Isn't: Quantized Serving of Mid-Size Open LLMs

Smit Kadvani, Kriti Faujdar, Spurthi Tallam

原文摘要

A team serving a 9B-20B open-weight language model on vLLM or SGLang must choose a quantization recipe, and needs two numbers: the speedup over BF16 and the accuracy given up. We assemble every public measurement of these numbers that we could verify and find that the record supplies them only in pieces. Only two checkpoints, both INT4 builds of Gemma 3 12B, have both a vLLM timing and an accuracy score, and that score covers a single MMLU subject, one that the AWQ build was calibrated on. The batch-1 timings predate current engine releases, AMD and Intel Gaudi have no timing in this band at all, and FP4 has none against BF16. The timings that do exist follow one rule. Decoding a small batch is limited by memory bandwidth, so 4-bit weights roughly double speed (2.12x for Qwen2.5-14B on an A100), but the gain vanishes once a large batch makes the GPU compute-bound (1.02x for Gemma 3 12B at batch size 256), where FP8 is the recipe that can still help. Many published accuracy deltas, including every HumanEval delta, lie within benchmark sampling noise. We close with a seven-item reporting checklist for future measurements.

cs.AI

版本更新 · v2arXiv:2609.05862

Budgeted Task-Aware Acquisition of Dynamic Networks

Zihe Zhou

原文摘要

Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs observation and computational costs, making complete updates impractical under limited resources. This paper focuses on budgeted task-aware acquisition on dynamic networks, where a model needs to decide which stale graph information to refresh for a downstream task. We propose Scout, a lightweight framework that learns the task value of querying each node from the maintained graph and observation history. Our evaluation covers one synthetic and 4 real-world dynamic networks, 2 downstream tasks, 9 acquisition baselines, and several query budgets. Scout achieves the highest mean downstream performance in 15 of the 21 benchmark-budget settings and ranks within the top two in 19 of them. Its average rank is 1.4, compared with 3.2 for the strongest baseline. On the same dynamic network, task-matched acquisition improves link-prediction AUC by 0.005-0.007 and node-classification accuracy by 0.007-0.017 over task-mismatched acquisition. These results show that useful graph observations depend on the downstream task and that limited observation budgets can be allocated effectively by learning directly from downstream utility.

cs.LG

版本更新 · v2arXiv:2607.25489

Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation

Wanshu Fan, Zheng Tong, Yang Liu, Jing Qin, Zhongbin Han, Haifan Gong, Congyu Liao, Xiaofeng Liu 等 9 位作者

原文摘要

Large language models and multimodal foundation models are enabling medical artificial intelligence (AI) systems to move beyond isolated prediction and undertake multistep clinical tasks that require planning, tool use, memory, iterative correction, and coordination among specialized agents. However, the scope of agentic AI in medicine remains unsettled, and current evaluation practices are not yet aligned with the requirements of clinical use. We conducted a scoping review with systematic evidence mapping across five electronic sources, screened 1,649 exportable records, and provisionally included 557 unique studies that met predefined criteria for goal-directed task execution, tool use, interaction with external resources, feedback-based refinement, or multi-agent collaboration. The included studies describe single agents that use external tools, workflows supported by retrieval and external knowledge, multimodal agents, and multi-agent systems applied to medical question answering, image interpretation, electronic health record analysis, drug safety, and clinical trial prediction. The evidence base remains dominated by public benchmarks, simulated settings, retrospective datasets, and small-scale expert evaluation. Process reliability, evidence traceability, uncertainty, safety, workflow impact, and external validity are evaluated less consistently. Clinical translation will depend on clearer definitions, reproducible evaluation, auditable oversight, interoperable system design, and prospective validation in real-world clinical workflows.

cs.CV

版本更新 · v2arXiv:2610.07131

The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective

Xingrun Li, Sho Kuno, Yusuke Mukuta, Xin Yang, Tatsuya Harada

原文摘要

We study the implicit bias of Riemannian gradient flow for hyperbolic multiclass classification with fixed class prototypes in hyperbolic space $\mathbb H^n$. Our framework accommodates general permutation invariant relative margin (PERM) losses, a class that includes cross entropy and other standard multiclass losses. Our analysis is based on a decomposition: at large radius, the distance to each prototype splits into a radial term and a direction dependent term described by the Busemann function. This yields two main results. First, we prove a radial dichotomy: the sign of a drift coefficient $μ$ determines whether the radius is pushed toward the ideal boundary or back toward the interior; if the positive drift persists, then $r(t)=\tfrac12\log t+O(1)$, while persistent negative drift returns the trajectory to the large radius threshold in finite time. Second, we show that large-radius directions can approach critical points of the Busemann risk on $\partial\mathbb H^n$, even during radial return. These results provide a rigorous large-radius perspective on two phenomena we refer to as boundary saturation and near-boundary clustering in hyperbolic representation learning.

cs.LG

版本更新 · v2arXiv:2608.01320

Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorithms

Ziyi Cai, Shuangping Li, Yiheng Shen, Kangning Wang, Peng Zhang

原文摘要

Language generation in the limit is a theoretical framework for studying how a generator can learn to produce new valid strings from a stream of positive examples. In this model, an adversary chooses an unknown language from a countable family and enumerates its elements in an arbitrary order, while the generator must eventually output only elements of the language that have not yet appeared in the enumeration. Reliable generation is thus formalized through two eventual guarantees: validity and novelty relative to the observed data. To further quantify the breadth of the generator's outputs, Kleinberg and Wei (FOCS 2025, STOC 2026) introduced lower density as a measure of output coverage. Given an order representing the importance or relevance of possible outputs, lower density is the asymptotic lower bound, as $n$ grows, on the fraction of the first $n$ elements of the target language that the generator outputs before they appear in the data. Kleinberg and Wei showed that $1/2$ is the optimal lower-density guarantee for deterministic algorithms. We develop a simple and unified framework for obtaining optimal lower-density guarantees. We first give a deterministic algorithm that recovers the optimal guarantee of $1/2$ with a significantly simpler analysis than prior work. We then demonstrate the flexibility of our framework through two extensions. First, against an oblivious adversary, randomization raises the optimal guarantee to $1-1/e$. Second, for any finite collection of orders, the optimal deterministic and randomized guarantees can be achieved simultaneously with respect to every order, so accommodating multiple notions of importance or relevance entails no loss in the optimal guarantee.

cs.DS · cs.AI · cs.CL · cs.DM · cs.LG

新论文 · v1arXiv:2611.04379

Understanding Backdoor Attacks in Scene Graph Generation via Global Context Pathway

Xiaoguang Chang, Tuo Chen, Chengze Jiang, Teng Wang, Changyin Sun

原文摘要

Scene Graph Generation (SGG) produces structured scene representations, yet its training-time backdoor risk remains unexplored. Unlike classification, SGG exposes a pair-level attack surface that enables selective corruption of relations involving a designated object category. However, because SGG largely relies on localized evidence, globally placed triggers may face difficulty in manipulating such predictions. Recent SGG architectures increasingly incorporate global context to improve scene modeling, which may in turn facilitate such attacks. In this paper, we systematically study this backdoor risk and investigate the role of the global context pathway in backdoor behavior. Concretely, we first instantiate this attack with an effective method, and propose a three-axis evaluation protocol to characterize backdoor behavior. Experiments on Visual Genome with representative open-vocabulary and closed-set SGG models demonstrate the effectiveness of the attack. Mechanistic analyses reveal that the explicit global context pathway serves as a major carrier of the backdoor effect across the evaluated SGG models. In particular, replacing the poisoned global context representation with its clean counterpart during inference sharply suppresses the attack, yielding 100% and 97% reductions in attack success for the OvSGTR family and RelationFormer, respectively. Moreover, training-time interventions in the OvSGTR family show that suppressing trigger signals in this pathway either reduces attack success or substantially degrades utility. Together, these findings suggest that explicit global context designs may pose a backdoor risk in SGG architectures.

cs.CV · cs.AI

新论文 · v1arXiv:2611.04377

Monodromy Computation Model

Xiaoyang Liu

原文摘要

A closed path can return to its starting point while analytic continuation reaches another branch. We construct a finite computational calculus in which retained logarithmic branches supply memory, analytic observations select operations, and descent through a covering exposes deeper memory. Three branch coordinates suffice, and every finite observation uses the same cubic power covering. Each program defines a globally real analytic return map whose integer-lattice execution is realized by actual path lifting. Our first theorem simulates every finite-alphabet, finite-control Post--Turing machine, preserving complete configurations, halting, and divergence. Our second theorem identifies the partial numeric functions of the calculus, under fixed primitive-recursive input and output maps, with exactly the partial recursive functions. Deleting descent leaves a Forward language with a syntax-derived finite observation quotient and a primitive-recursive halting predicate. This yields a strict separation within the calculus and identifies access to deeper memory as its decisive additional operation. The constructions and semantic correspondences are formalized in Lean 4 with Mathlib.

cs.CC · cs.LO