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
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 05:06 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 05:18 — 2026-11-08 05:18（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 05:06最近发现新增版本：2026-11-07 17:43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4,056 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 05:04（北京时间）
版本更新 · v2arXiv:2611.00843

Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon

Zhenzhou, Shi, Yizhe, Shi

原文摘要

We report the end-to-end deployment and measurement of MiniMax H3, a 20.38-billion-parameter video diffusion transformer (DiT) - the count measured from the safetensors headers of the Q8 checkpoint as deployed locally (Section 3.2) - running entirely on consumer Apple Silicon hardware: an Apple Mac mini with M5 Pro chip and 64 GiB of unified memory. Using the official bf16-to-Q8 (8-bit, group size 64) quantization path executed locally on the machine, we produced a working text-to-video pipeline with no cloud dependency. We document the full deployment procedure, including two non-trivial blockers and their fixes, and report measured figures for build time, peak memory, and per-clip render latency across four resolution tiers (Draft 384x640 through Native 768x1344). A 15.08-second 576x1024 clip rendered in 4838.49 seconds with a measured MLX peak of 27.467 GiB. We further operated the system as an unattended production pipeline, completing 17 clips in 26.49 hours with zero render failures. A blind human review of the 17 production clips (generation prompts withheld) averaged 3.12, 3.18, and 2.94 out of 5 for structural integrity, temporal consistency, and visible artifacts. All figures in this report are our own measurements except where explicitly labeled as third-party data. This is a systems/empirical report; we make no claim of model innovation.

cs.CV · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03107

Finding and Certifying Weighted Minimum Cuts with Cut Queries

Troy Lee

原文摘要

We study the deterministic and nondeterministic cut query complexity of minimum cut in undirected graphs with arbitrary nonnegative edge weights. For the nondeterministic case, we show that every $n$-vertex graph has an $O(n\log^2(2n))$-query certificate of its exact global minimum-cut value, such that any other nonnegatively weighted graph on the same vertex set that agrees on these queries has the same minimum cut value. A key ingredient is a way to certify a maximum $s$--$t$ flow value with only $O(n)$ cut queries. For the deterministic case we give an algorithm that finds an exact global minimum cut using $O(n^{3/2}\log^3(2n)(\log\log(2n))^2)$ cut queries. Previously no $O(n^{2-\varepsilon})$ deterministic bound was known for arbitrary nonnegatively weighted graphs. The algorithm follows Karger's two-respecting tree approach. The key new ingredient is a deterministic construction of a weak skeleton of the input graph $G$: an explicit weighted graph $H$ in which every minimum cut of $G$ is a $5/4$-approximate minimum cut.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.06317

Settling the Complexity of Hylland--Zeckhauser Equilibria

Zhengyang Liu, Yixin Tao, Yonglei Yan

原文摘要

The Hylland--Zeckhauser (HZ) mechanism is a foundational framework for allocating indivisible goods in one-sided matching markets via lotteries supported by competitive prices and equal artificial budgets. We resolve the exact computational complexity of the HZ scheme by proving that computing an exact HZ equilibrium is FIXP-complete, thereby settling a conjecture of Vazirani and Yannakakis. Notably, this hardness persists even when computing the equilibrium allocation alone. We establish our hardness result via a reduction that encodes quadratic fixed-point equations into a reciprocal variational inequality. On the algorithmic side, we present a deterministic polynomial-time approximation algorithm that achieves an additive error of $0.0755211 + δ$ for any $δ> 0$, significantly improving upon the previous $1/e$ guarantee.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04647

Non-asymptotic Sphere-Packing Bounds for Finite-Blocklength Scalar Gaussian Multiple-Access and Broadcast Channels

Kaixuan Bao, Wei Xu, Xiaohu You

原文摘要

This paper investigates non-asymptotic achievable rate regions of Gaussian multiple-access channels (MACs) and broadcast channels (BCs) in the finite-blocklength regime. By employing a proposed volume-uniform random coding (VURC) codebook that distributes codewords uniformly within an $n$-dimensional power sphere, together with successive interference cancellation (SIC) decoding, we derive a closed-form achievability bound, a scheme-specific lower bound on the average error probability, and a fourth-order asymptotic characterization. The proposed SIC achievability bound admits a simple and analytically interpretable closed-form expression, enabling direct performance evaluation without iterative computation. The structure of the proposed SIC asymptotic bound offers a highly extensible framework, allowing advances in single-user finite-blocklength theory to be systematically incorporated into the multiuser setting. Futhermore, to characterize the performance benefit of joint decoding, we further derive numerical and closed-form achievability bounds for the two-user Gaussian MAC under joint nearest-neighbor (JNN) decoding. Numerical results illustrate the performance differences among the proposed SIC and JNN bounds and existing benchmarks.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.09411

Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data

Dominik Schnaus, Thomas Dagès, Daniel Cremers, Xi Wang, Phillip Isola

原文摘要

Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic Representation Hypothesis suggests that models trained on different modalities may converge spontaneously toward a shared representation geometry. But then, do we even need paired examples for cross-modal alignment? Remarkably, we show that paired examples are unnecessary for coarse cross-modal alignment. Our simple Wasserstein Procrustes method with a coarse geometric initialization (GeoWarP) aligns two disjoint embedding sets by estimating a single orthogonal map without seeing any pairs. Across datasets, modalities, and unimodal models, we show that we can consistently align independently trained representations without pairs, and standard geometric alignment metrics accurately predict when this is possible. Nevertheless, we can naturally benefit from paired examples. In the very few-pair regime, our method substantially outperforms existing ones, while staying competitive with pair-based methods with more added examples. Finally, we demonstrate that the resulting alignments can enable text-to-image generation without paired examples. These results show that independently trained models often share enough geometry to establish cross-modal correspondence with little or no paired data.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04645

Therapy-FIS: A Dataset for Assessing Facilitative Interpersonal Skills in Psychotherapeutic Setting

Qijian Zheng, Wanqing Lin, Yuanfang Wang, Yijun Ge, Jordan Bate, Katie Aafjes-van Doorn, Feng Liu

原文摘要

Facilitative Interpersonal Skills (FIS) is a performance-based assessment method that provides a structured framework for evaluating the interpersonal competencies of mental health professionals. However, existing FIS assessment relies heavily on human observer ratings, making the evaluation process labor-intensive, costly, and difficult to scale. Progress toward automated FIS assessment has also been constrained by the lack of publicly available professional data in psychotherapy settings. To address this limitation, we introduce Therapy-FIS, a dataset for automated FIS assessment in standardized psychotherapy tasks. To our knowledge, Therapy-FIS is the first publicly available dataset in this domain. It contains facial, acoustic, and textual signals derived from standardized therapist responses to standardized mock patient stimulus clips, based on 890 therapist video recordings and 8 patient videos, and is rated with eight FIS subscale ratings and an overall FIS score. Built on Therapy-FIS, we further establish a benchmark with two downstream tasks: Therapist Performance Rating and Joint Therapist--mock-Patient Performance Rating. We also introduce a competitive baseline, DyadicFIS, with gated fusion and routed readout under therapist-only and dyadic settings. DyadicFIS obtains the best macro CCC(Concordance Correlation Coefficient) scores on both tasks (0.2807 and 0.3299). Therapy-FIS offers a reproducible resource for data-driven automated assessment of therapeutic interpersonal skills in mental health.

cs.CV · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.09001

Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths

Qihao Yuan

原文摘要

Multi-step LLM reasoning lacks a machine-recheckable ledger: discarded reasoning paths leave no auditable record. We propose the Deposon scattering layer, which binds each node of an LLM-generated concept-decomposition graph to a two-parameter Deposon state; paths undergo three-channel scattering -- transmission, reflection, irreversible dissipation -- obeying T+R+A=1 for arbitrary parameters, with a maximum per-path energy-audit deviation of 2.2E-16 (machine epsilon). We report all three evidence tiers honestly. On synthetic trap benchmarks the path-filtering gain is closed (pre-registered): unified reaches 100% versus a decoy-capture baseline at 7%/10%. On real benchmarks the layer is indistinguishable from a trivial six-keyword rule filter (GSM8K 0.87 >= 0.85, McNemar p=0.5; StrategyQA 0.899 = 0.899); no difference is detected here, so we sharpen the claim to "the differential value lies solely in machine verifiability." Fusion yields a second negative result: convex combinations with a semantic prior never improve (physics 0.484 -> 0.452), and the apparent lambda=2 gain is an anti-field artifact; any fusion gain must be nonlinear. Modeling the reverse dynamics as a potential game on the graph, we evidence an auditable scalar's monotonicity and near-gradientness and quantify the empirical coordination ratio (ECR). The three formalized dynamical-equivalence propositions (P1a/P1b/T-P1c) are falsified under the pre-registered kill protocol, and the potential-game claim is downgraded to approximate (cyclic-graph median residual 0.669): only consistency-level evidence survives at the dynamical level. Code: github.com/zeroandcat/Deposon.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00682

Testing MAX-CUT in the Adjacency Matrix Model: Tight Non-Adaptive Bounds and a Cubic Adaptive Lower Bound

Songhua He

原文摘要

We study the query complexity of approximating the MAX-CUT value to additive error $\varepsilon n^2$ in the adjacency matrix model. This was one of the first problems studied in graph property testing [GGR'98]. Previously, the best known upper bound for both adaptive and non-adaptive algorithms was $O(1/\varepsilon^6)$ [RV'07; MS'08; GMRS'22]. The only known lower bound was a trivial $Ω(1/\varepsilon^2)$ bound. We close this gap from both sides for non-adaptive algorithms, proving that its query complexity is exactly $Θ(1/\varepsilon^4)$. We also prove an adaptive $Ω(1/\varepsilon^3)$ lower bound. Our upper bound is achieved by a canonical tester that samples $O(1/\varepsilon^2)$ vertices in expectation and outputs the rescaled MAX-CUT value of the induced subgraph. We prove its correctness by applying spectral truncation to the adjacency matrix, using a geometric argument to control the sampling error of the retained low-rank part and a cut-norm restriction estimate [RV'07] for the remainder. As an application, an analogous proof also yields a tight $O(1/\varepsilon^4)$ non-adaptive query upper bound for MAX-2CSP. For our lower bounds, we show indistinguishability between a uniform random graph and a random graph with a planted hidden partition. For the non-adaptive lower bound, we observe that one plus the $χ^2$-divergence between the query transcript distributions is exactly a normalized Ising partition function, which can be bounded using Boolean hypercontractivity. For the adaptive lower bound, we relate each query's distinguishing power to the prediction, based on previous answers, of whether its endpoints lie in the same part of the hidden partition. We bound the combined advantage of these predictions using the completed transcript, which lets us analyze the adaptively chosen pairs of vertices together despite their dependence on earlier answers.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04642

Stabilizing Neural Emulation of Spatiotemporal Physical Dynamics through Denoising Koopman Latent Dynamics

Chenxu Wu, Sixing Chen, Junming Hou, Jiahan Huang, Jianqiao Zeng, Peiming Luo, Liang Yan, Jian Wei You

原文摘要

Koopman operator theory provides a principled framework for reduced-order modeling of nonlinear spatiotemporal dynamics through linear evolution in an observable space. In practice, however, learned finite-dimensional representations are typically approximately invariant, causing unresolved dynamics and accumulated closure errors. Recent approaches, inspired by the Mori-Zwanzig formalism, address these effects through deterministic memory or closure modeling, yet robust extrapolation beyond the training horizon remains challenging. Here, we propose KoopFlow, an efficient prediction-correction framework based on the key insight that finite-dimensional Koopman error accumulation can be reinterpreted as a progressive distributional degradation process. Accordingly, KoopFlow treats Koopman predictions as noisy intermediate estimates, which are then transported toward the target latent distribution through a generative model, thereby mitigating accumulated errors while retaining computational efficiency and temporal flexibility. Moreover, we reveal a non-monotonic relationship between Koopman spectral coherence and predictive accuracy. Experiments across diverse nonlinear dynamical systems demonstrate improved long-horizon prediction accuracy and stability over representative baselines, particularly beyond the training horizon.

cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.36924

Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video

Sarmad Idrees, Jongeun Choi

原文摘要

Learning humanoid skills from videos typically requires a successful human demonstration, which often demands custom data collection. Although failures have traditionally been treated only as negative examples in robot learning, they can still reveal a usable trajectory prefix before the task fails, as well as the intended outcome. To leverage this information from a failed-attempt video, we propose TRACC, a pipeline that imitates the useful portion of the motion trajectory and then completes the task based on the inferred task outcome. The usable motion prefix serves as prior knowledge until the failure occurs, after which the task-completion reward guides the policy to learn the intended task goal without requiring a successful task trajectory. We evaluate our method on six in-the-wild failed human tasks from the Oops! dataset. Our experimental results demonstrate the effectiveness of the proposed approach for learning from failed attempts when no successful demonstration is available. Thus, these findings establish failed human videos as a viable source of supervision for humanoid skill learning.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01609

MagPillar: A Soft Magnetopillar Array Tactile Sensor for Robotic Surface Perception

Haotian Guo, Yu Feng, Hao Wu, Jiazhi Tang, Ningbin Zhang, Jianshu Zhou

原文摘要

Robotic surface exploration benefits from tactile interfaces that accommodate contact and capture variations in surface characteristics. Herein, we report MagPillar, a tactile sensor inspired by spider tactile hairs that combines a magnetic pillar array with three-axis Hall sensing. A full-array mechanical and magnetic-field model characterizes how pillar deformation affects the superposed fields measured across the array, providing a physical basis for interpreting its contact responses. The compliant pillar architecture translates contact with surface textures and geometric features into distinct magnetic response patterns. Then, in robotic surface perception experiments, spectral features and logistic regression distinguish six material surfaces with an offline accuracy of 99.34% under within-session temporally blocked cross-validation. Continuous scans over periodic protrusions produce amplitude and peak-spacing variations consistent with changes in surface geometry. These findings connect compliant contact mechanics with distributed magnetic sensing, paving a new path for material recognition and qualitative surface-profile perception.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04641

Does LinUCB Need Valid Confidence Sets?

Ahmed Ben Yahmed, Marc Abeille, David Janz, Clément Calauzènes

原文摘要

We show that replacing LinUCB's usual confidence width $β$ by any fixed $α>0$ preserves sublinear regret when the action set is $M$-smooth and $m$-strongly convex. Our high-probability regret bound for this generalisation, $α$-LinUCB, establishes that valid confidence sets are not necessary for the success of LinUCB. We identify the mechanism behind this result: action-set curvature drives $α$-LinUCB to explore every direction, even when optimism is not guaranteed. To analyse this mechanism, we introduce a logarithmically capped spectral potential that, unlike the standard log-determinant potential, caps contributions from well-explored directions. This yields lower bounds on the smallest eigenvalue of the design matrix. At the standard confidence width $α=β\asymp\sqrt{d\log T}$, our $T$-round regret bound in $d$ dimensions is $O\bigl(\frac{M}{m}d\sqrt{T\log T}\bigr)$, up to iterated-logarithmic factors, improving the horizon dependence of the classical LinUCB guarantee by a factor of $\sqrt{\log T}$.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29607

No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses

Francesco Corti, Moritz Becker, Olga Saukh

原文摘要

Deep neural networks deployed on smart glasses must adapt to changes in the distribution of incoming data while adhering to strict privacy and device constraints. We present No Frames, Just Frequencies, a bandwidth-efficient source-assisted adaptation framework that characterizes distribution shifts using compact frequency descriptors computed on-device. Rather than transmitting camera frames, the glasses compute and send frequency descriptors to a host device that contains a replica of the model. The host device maps the received frequency descriptor to a distribution shift operator that synthesizes out-of-distribution data and adapts a model replica using a pre-defined adaptation protocol. We evaluate the framework on mixtures of ImageNet-C corruptions using convolution-based (ConvNeXtV2-Femto), self-attention-based (DeiT-Tiny), and hybrid (TinyViT-5M) vision models, on person classification (Visual Wake Words), and on object detection (MS-COCO). Our results reveal that adaptation driven solely by the transmitted descriptors recovers $93-95\%$ of the supervised oracle adaptation gain on all three architectures, $82\%$ on Visual Wake Words and $94$--$98\%$ on MS-COCO. Notably, adaptation quality degrades gracefully as the descriptor resolution decreases from $224 $ to $28$ pixels, consistently across architectures, enabling bandwidth reductions from $213\times$ to $784\times$ across the frequency descriptors.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.08974

CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding

Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya, Haruto Suzuki, Kuniaki Saito, Toshihiko Fukushima, Cristian C. Beltran-Hernandez, Mai Nishimura

原文摘要

Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model scales. The core obstacle is output-distribution mismatch: predicting actions as bare numeric token sequences moves generation away from the VLM's pretrained language distribution, degrading the capabilities we seek to preserve. To address this, we propose CLAP (Causal Language-Action Prediction), which prepends each numeric action sequence with a natural-language action description, causally conditioning precise action-token prediction on a language-action plan without modifying the backbone architecture. With only 4-5 hours of training, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under language, object, and spatial perturbations. Ablations attribute the gains to action-grounded language semantics, and on a real UR5e robot 2B CLAP reaches 60% success against 15% for matched VLA-0. We release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05437

Req-Space: A User Study of Interactive Visualisations for Requirements Review

Risha Parveen, Navneet Arora, Zheying Zhang, Kalle Mäkelä, Pekka Abrahamsson

原文摘要

Requirements review involves identifying inconsistencies and assessing change implications across distributed specifications. Motivated by needs raised in industrial project workshops, we investigate Req-Space, an interactive prototype integrating semantic exploration and traceability visualisation to support human-led review. We conducted a fixed-order, two-phase study with 20 participants, including 11 with at least three years of software or IT experience. Participants reviewed a fictional 40-requirement software specification and a guest-checkout change request, first using source documents and then revisiting the same tasks with Req-Space. During the supported review, 17 participants recorded at least one additional source-supported item or pair. Of 69 assessable additional units, 58 (84.1%) were judged supported by the source materials. Seven decision rationales were judged stronger in Phase 2, including five without a change in the decision category. Participants generally found the visualisations helpful, although workload responses were mixed and some misinterpreted visual relationships. The findings suggest that visual support can facilitate requirements exploration and decision justification, provided relationship meanings and source context remain clear. The fixed study sequence prevents attributing the observed changes specifically to Req-Space.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03851

The Price of Partial Information with Switching Costs: A Complete Characterization for Feedback Graphs

Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Emmanuel Esposito, Federico Fusco, Tomer Koren

原文摘要

We study how switching costs affect minimax regret under partial feedback. Which features of the feedback preserve the $\sqrt T$ rate, and which force the $T^{2/3}$ rate? We address this question in the framework of feedback graphs, which interpolate between full information and bandits: playing an action reveals the losses of its out-neighbors in a known directed graph. Prior work on feedback graphs with switching costs gave algorithms with regret of order $T^{2/3}$, but matching lower bounds only for restricted classes of graphs, leaving the question open. We establish a complete characterization of the minimax regret with switching costs for all feedback graphs: $\widetildeΘ(\sqrt T)$ if the graph is strongly revealing, meaning that every pair of distinct actions has an endpoint that observes the losses of both; $\widetildeΘ(γ^{1/3}T^{2/3})$ for every other observable graph, where $γ$ is the domination number; and linear otherwise. In particular, tournaments, in which every action observes its own loss and each pair of actions is joined by one directed edge, sit at the phase transition: they behave like full information, but deleting the edge of any pair forces the rate $T^{2/3}$. Hence an action that observes all losses is neither necessary nor sufficient for the rate $\sqrt T$. Our algorithm TournamentSteering for the strongly revealing case rests on a new principle: each observed comparison of two actions serves both to estimate losses and to steer play, and the loss reduction from steering pays for the variance of the estimates. For every strongly revealing graph, distributing the comparisons among observing actions keeps this variance, and hence the regret, polylogarithmic in the number of actions, by an argument similar to the greedy construction of logarithmic dominating sets in tournaments.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04638

EvoCache: Accelerating Browser Large Language Model Delivery with Public Cache Anchors

Zhiyu Wang, Rajkumar Buyya

原文摘要

Large Language Models (LLMs) can run directly in a browser, but first use typically requires downloading model files that are hundreds of MiB or even several GiB in size. The same LLM is often repackaged by different publishers; these files share substantial content, yet byte differences prevent whole-file caches from reusing them. We propose EvoCache, a browser-managed LLM delivery system. EvoCache uses public cache anchors that are stored in advance by the browser and independent of browsing history to reconstruct losslessly the publisher version requested by a site. A site specifies only the target, while the browser selects the anchor and performs reconstruction, keeping both hidden from the site. An audit of 1,000 public repositories finds that 61 of the 100 most popular LLMs are offered by multiple publishers and that 98.1% of overlapping versions cannot be reused by whole-file caching. Across 23 cross-publisher model-package pairs, EvoCache achieves a median traffic reduction of 77.3% and outperforms every comparator. Across 240 real end-to-end browser experiments, EvoCache reduces network traffic by 78.9% and page-ready time by 64.2% relative to ordinary full downloads. For cached data left by other sites, EvoCache also protects users' cross-site cache privacy by using the same return time for cache hits and misses.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04637

SAT Encoding for Set of At-Most-K Cardinality Constraints with Ladder Shape

Hieu Truong Xuan, Tuyen Kieu Van, Khanh To Van

原文摘要

This paper presents a novel SAT encoding designed to represent a sequence of At-Most-K cardinality constraints arranged in a ladder-like structure, referred to as the Ladder AMK constraint. These AMK constraints feature a ladder-like arrangement, with shared common variables in the center and two variables differing at the beginning and the end. The proposed encoding first decomposes the sequence of AMK constraints into separated blocks, then encodes each block as a whole rather than encoding each AMK constraint individually. This approach improves the efficiency of constraint solving in SAT solvers by significantly reducing the size of the encoding, precisely the number of variables, and the generated clauses required. To achieve this, the encoding employs Sequential Counter to encode each block and constructs clauses that link adjacent blocks, ensuring equivalence with the input constraints. Compared to the previously proposed encoding that uses BDD for Ladder AMO constraint, our encoding requires fewer variables and clauses. Our study is the first study that develops SAT encoding for Ladder AMK constraints with k>1. Experimental results on single Ladder AMO and Ladder AMK constraints indicate that our encoding significantly enhances both the size of the encoding and the efficiency of solving time compared to existing encodings. Furthermore, by evaluating on the two real-world combinatorial problems, namely Anti-bandwidth Problem and Nurse Rostering Problem, we found that the proposed encoding surpasses alternative encodings, as well as more advanced Constraint Programming and Mixed Integer Programming solvers. In summary, the SAT encoding technique presented in this paper provides a more efficient method for encoding sequence constraint, specifically Ladder AMK constraint, which could enhance the effectiveness of SAT solving for various problems involving this type of constraint.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04635

First Near-Additive All-Pairs Approximate Shortest Paths in Decremental Weighted Graphs

Eden Koveshi, Liam Roditty, Ariel Sapir

原文摘要

We present the first four All-Pairs Approximate Shortest Paths (APASP) algorithms for decremental weighted undirected graphs. We extend the hierarchy induced edge sets of Baswana and Kavitha [FOCS'06 and SICOMP'10] to the decremental setting. At any point in time, for any $u,v$, $W_{i}$ denotes the weight of the $i$-th heaviest edge on any shortest path between them in the current graph. For any $\varepsilon>0$, our first algorithm maintains $(1+\varepsilon,2W_{2})$-APASP in $\tilde{O}(n^{\frac{3}{2}+o(1)}m^{\frac{1}{2}})$ total update time, matching a single static computation of Cohen and Zwick [SODA'97 and JALG'01], up to a subpolynomial factor. It also improves the stretch of the $(2+\varepsilon)$-APASP algorithm of Dory, Forster, Nazari and de Vos [ICALP'24]. Our second algorithm maintains $(1+\varepsilon,2W_{1}+2W_{2})$-APASP in $\tilde{O}(n^{\frac{7}{3}})$ total update time, improving upon Chechik's $(3+\varepsilon)$-APASP algorithm [FOCS'18] for $m=Ω(n^{\frac{11}{6}})$. We also obtain two $(1+\varepsilon,2\cdot(k-1)W_{1})$-APASP algorithms with total update times $\tilde{O}(n^{2-\frac{1}{k}+o(1)}m^{\frac{1}{k}})$ and $\tilde{O}(n^{2+\frac{2}{3k-2}+o(1)})$, adapting the static $+2\sum_{i=1}^{k-1}W_{i}$-APASP algorithms of Cohen and Zwick [SODA'97 and JALG'01] and Roditty and Sapir [FSTTCS'25]. For unweighted graphs, we present $(1+\varepsilon,2)$-APASP in $\tilde{O}(n^{\frac{7}{3}})$ total update time and $(1+\varepsilon,2\cdot(k-1))$-APASP in $\tilde{O}(n^{2+\frac{1}{3k-4}+o(1)})$. Combined with the results of Dory, Forster, Nazari and de Vos [ICALP'24], these match the fastest combinatorial static bounds of Dor, Halperin and Zwick [FOCS'96 and SICOMP'00] up to subpolynomial factors.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04634

VeriSpoof: Beyond Real or Fake with One Audio LLM

Yang Xiao, Ting Dang

原文摘要

A speech deepfake detector estimates whether a recording is synthetic, but a forensic analyst also asks which system produced it, whether recordings share a source, and what evidence supports each conclusion. We present VeriSpoof, an audio language model that unifies five tasks with shared weights: deepfake detection, generator attribution (generator, acoustic model and vocoder), recording-condition analysis, synthesized-span localisation, and source verification. Each decision is supported by grounded rationales whose statements can be independently verified. Answers are scored by sentence likelihood, allowing detection and source verification to be thresholded without separate heads. Rationale statements can be checked against waveform measurements, span labels, or generator metadata. Counterfactual examples train decisions to follow the stated evidence. Across the 14 Speech-DF-Arena test sets, VeriSpoof-Plus achieves 2.14% pooled EER, ranking third of 28 systems and first among open-weight systems. VeriSpoof-Base, trained only on official training splits of eight corpora, achieves 4.43% EER, less than half that of the next open-weight detector. With the same weights, VeriSpoof-Plus verifies whether recordings from generators unseen in training share a source at 6.2% EER. Controlled studies show that the audio representation governs detection, the LLM governs recording comparison, and source supervision is necessary for neural-codec fakes. Statement-checkable rationales catch partial fakes missed by one-step answers (99.6% vs. 78.4% on PartialEdit) and determine decisions under edits unseen in training (99.5%). Training updates only 29.7M of 2.85B parameters, fitting a single 24 GB GPU with gradient checkpointing. We release both models, inference code, a demo, and VeriSpoof-Bench, the evaluation suite covering these questions.

eess.AS · cs.CR · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04633

ReXMo: End-to-End Video Character Replacement with Expression and Motion Preservation

Hualiang Wei, Wenhui Li

原文摘要

Video character replacement aims to replace actors while preserving facial expressions, motions, and scene dynamics. Existing methods typically rely on masked generation with pose guidance, limiting fine-grained expression and motion preservation in complex scenes. We propose ReXMo, an end-to-end framework that supports single-, multi-, and selective character replacement scenarios. ReXMo introduces paired triplet supervision, where synthesized driving videos and original videos share identical performances but different identities, enabling scalable training through synthetic data generation. An In-Context Diffusion Transformer learns identity transformation by jointly conditioning on driving videos, reference identities, and text prompts, while an Expression Enhancement Adapter improves facial expression preservation in multi-person scenes. Extensive experiments demonstrate that ReXMo outperforms existing methods in identity fidelity, motion consistency, expression preservation, and visual quality. Our dataset and code will be publicly released.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04632

Self-Privileged Fine-Tuning

Yangrong Hu, Xueyu Zhou, Yue Wu, Jian Huang

原文摘要

Supervised fine-tuning (SFT) is a key component of language model post-training, enabling effective task adaptation and serving as an important foundation for subsequent reinforcement learning. Recent methods seek to improve SFT by introducing token-level weights into the training objective, where these weights are typically derived from a model's output distribution at each token position. To better understand how such weighting schemes affect SFT, we analyze their optimization objectives and theoretically characterize the target distributions they induce. Our analysis shows that dynamic weighting methods, such as Dynamic Fine-Tuning (DFT), induce a heavily sharpened distribution, whereas static weighting methods fit a target distribution proportional to the product of the data distribution and a frozen prior. These findings suggest that static weighting provides a more stable training target, while its effectiveness critically depends on the quality of the prior distribution. Building on this observation, we propose Self-Privileged Fine-Tuning (SPFT), which uses a frozen copy of the initial model conditioned on privileged information (such as ground truth for mathematical questions) as a prior to provide guidance for token-level weighting during fine-tuning. Through a Bayesian decomposition, we further show that SPFT reweights the standard static prior according to how informative each target token is for predicting the ground-truth outcome, thereby assigning larger weights to more predictive tokens. Experiments on mathematical reasoning and code generation show that SPFT improves over standard SFT and other baselines across the main settings.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.07604

EmbedTalk: Talking Head Synthesis using Gaussian Embeddings

Arpita Saggar, Jonathan C. Darling, Duygu Sarikaya, David C. Hogg

原文摘要

Deformable 3D Gaussian Splatting (3DGS) has emerged as a popular method for real-time talking head synthesis, offering high-quality renderings at low latency. Tri-planes are a common choice for encoding Gaussians prior to deformation since they provide a compact and continuous representation. However, tri-plane encodings are limited by grid resolution and approximation errors introduced by projecting 3D volumetric fields onto 2D subspaces. Recent work has demonstrated the effectiveness of per-Gaussian embeddings for driving temporal deformations in 4D scene reconstruction. We introduce EmbedTalk, which leverages these embeddings to model speech-driven facial deformations for talking head synthesis. Comprehensive experiments show that EmbedTalk improves rendering quality, lip synchronisation, and motion consistency over previous 3DGS-based methods, while remaining competitive with state-of-the-art generative models. Replacing tri-plane features with embeddings also yields significantly more compact models that achieve 60+ FPS on a laptop GPU (RTX 2060 6 GB). Code and further details are available at https://arpita2512.github.io/EmbedTalk/

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.12231

An Efficient Minimax-Optimal Algorithm for Adversarial $m$-Set Bandits

Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni

原文摘要

We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items. The resulting action set contains $K=\binom{d}{m}$ elements and can therefore be exponentially large. We propose a computationally efficient algorithm that exploits this structure without explicitly enumerating the action set. Against adaptive non-anticipating adversaries, it guarantees, with probability at least $1-δ$, regret against the best action in hindsight of $R_T =O(\sqrt{dT\log(K/δ)}). $ This matches the high-probability regret bound of the finite-action EXP3 with Kiefer-Wolfowitz exploration algorithm of Zimmert and Lattimore, whose direct implementation may require exponential space. Our algorithm instead represents each sampling distribution with $d$ parameters and runs in polynomial time without enumerating the action set. This resolves an open problem posed by Maiti et al. We complement this upper bound with a matching high-probability lower bound. For all sufficiently small $δ$ and all sufficiently large horizons, every randomized algorithm admits an adaptive non-anticipating adversary for which, with probability at least $δ$, $R_T=Ω( \sqrt{dT\log(K/δ)}). $ Thus, the rate is minimax optimal up to universal constants in this regime. In particular, setting $m=1$ shows that the $\log K$ factor in the high-probability regret bound for ordinary $K$-armed bandits against adaptive non-anticipating adversaries is unavoidable. This strengthens the lower bound of Gerchinovitz and Lattimore, closing the remaining $\sqrt{\log K}$ gap between high-probability upper and lower regret bounds.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.08698

Supersampling Stable Diffusion and Beyond: Training-Free Neural Network Scaling via Signal Interpolation

Md Abu Obaida Zishan, Jannatun Noor, Annajiat Alim Rasel

原文摘要

This work presents a training-free approach for interpolating neural networks using signal interpolation methods (i.e., linear, bilinear, bicubic). We discovered this phenomenon while attempting to interpolate the convolution layers of Stable-Diffusion-1.5 for beyond-training-resolution (BTR) image generation. As we know, for generating BTR images using DDPMs (Denoising Diffusion Probabilistic Models), there are mainly two approaches, namely, 1) patch-wise diffusion and 2) convolution-kernel dilation. Patch-wise diffusion cannot solve the object-duplication problem efficiently, while the kernel dilation approach may be harder to fine-tune later. Thus, we proposed convolution-kernel interpolation of the Stable Diffusion 1.5 model for $4\times$ BTR image generation. We discover and show mathematically that signal interpolation methods can correctly scale convolution kernels when multiplied by a flat-attenuation factor, while achieving competitive performance against the state of the art. We then applied the same methodology to non-DDPM deep neural network architectures, adapting them for BTR image classification, achieving a worst-case performance drop of $\sim 7\%$ on the ImageNet-1k validation set. Again, we subsample the penultimate fully connected layer of VGG-16 using our method, reducing up to $\sim 9\%$ parameters with $\sim 5\%$ loss in performance. Finally, we also discuss how we can reduce the memory footprint of training neural networks to $4\times$ or greater.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04627

Evaluating LLMs as Judges of Counterspeech Quality Against Online Hate Speech

Johnny Alali, Nicolás Benjamín Ocampo, Davide Ceolin

原文摘要

Prolonged exposure to hate speech on social media can cause lasting psychological distress among users. Counterspeech has emerged as an effective, non-censorial mitigation strategy, but its deployment requires rigorous quality assessment. Manual assessment is unscalable due to the large volume of content on the Web and imposes severe emotional strain on human annotators. Large Language Models (LLMs) offer a scalable alternative, yet concerns remain regarding their reliability. In this paper, we investigate the extent to which LLMs can effectively perform this task. We test 12 open-weight LLMs of different sizes and families under zero-shot, few-shot, and chain-of-thought prompting, to approximate pointwise and pairwise human expert assessment of counterspeech quality across four dimensions: relevance, coherence, aggressiveness, and suitableness. We find that (i) LLMs show low agreement and moderate rank correlations with human experts: our best configuration, Qwen 2.5 72B on coherence, achieves up to a linear-weighted Cohen's $κ_l = 0.19$ and Spearman's $ρ= 0.42$ in pointwise evaluation and an unweighted Cohen's $κ= 0.25$ in pairwise evaluation. (ii) Converting pointwise scores into pairwise labels substantially improves human--LLM agreement for selected configurations. For same-instance coherence, Qwen 2.5 72B under zero-shot prompting achieves $κ= 0.35$ with converted labels, compared with $κ= 0.25$ when judging pairs directly, and Mixtral 8$\times$7B under few-shot prompting improves from $κ= 0.07$ to $κ= 0.34$. (iii) LLMs agree more with one another than with human experts, particularly in pairwise evaluation, where the strongest model pair, OLMo 2 32B and Llama 3.3 70B on coherence, reaches substantial agreement with $κ= 0.76$, whereas their agreement with the experts in the same configuration does not exceed $κ= 0.21$.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04626

MambaHand: Local Identity and Behavioral Sequence Learning with Mamba for Dynamic Hand Gesture Authentication

Zenan Lin, Junduan Huang, Xilai Wang, Wenxiong Kang

原文摘要

Dynamic hand gesture authentication (DHGA) is an emerging biometric technique that contains both physiological and behavioral identity characteristics. However, existing methods primarily rely on convolutional networks or manually designed motion representations, making it difficult to jointly capture fine-grained local identity differences and long-range behavioral dependencies during hand gesture execution. To address these challenges, we propose a two-stream identity representation learning framework, MambaHand Net, to combine CNNs with Mamba for DHGA. The proposed framework consists of a Local Identity Stream (LIS) and a Behavioral Sequential Stream (BSS). The LIS extracts frame-wise local identity cues with a convolutional network, while the BSS preserves spatial tokens from intermediate visual features and constructs first-order and second-order temporal difference sequences to model multi-order behavioral variations. Moreover, the bidirectional Mamba is incorporated into the BSS to model semantic motion across different spatial locations, enabling efficient long-range modeling of hand gesture execution habits. Finally, attention-guided spatial token aggregation and a two-stream fusion strategy are used to integrate local identity cues and multi-order behavioral patterns into a discriminative identity representation. Our method achieves state-of-the-art (SOTA) average performance on the SCUT-DHGA benchmark dataset, demonstrating that combining CNNs with Mamba is an effective new solution for DHGA.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00240

Constant Approximation of Fréchet Distance in Near-Linear Time

Haoqiang Huang, Zihe Wang, Shuo Zhang

原文摘要

We give the first constant-factor approximation for the Fréchet distance in near-linear time. Given two polygonal curves in $\mathbb{R}^d$ with $n$ and $m$ vertices, respectively, where $m\le n$, our deterministic algorithm runs in $O(n^{1+\varepsilon})$ time for every fixed $\varepsilon>0$ and $d$, with an approximation factor depending only on $\varepsilon$ and $d$. The same result holds for the discrete Fréchet distance. Our result extends the line of work initiated by Cheng, Huang, and Zhang (STOC 2025) from strongly subquadratic to near-linear time. Our algorithm recursively balances preprocessing and query time. An index for comparing subcurves of a single curve supports faster queries between different curves. We obtain this speedup by replacing one curve with surrogates assembled from indexed subcurves of the other and shared across starting points of matchings. Faster queries then reduce the cost of building the next index. Compact boundary reachability summaries allow the answers to be reused in later recursive calls. After a number of rounds depending only on $\varepsilon$, both preprocessing and query time are near-linear.

cs.CG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2601.08434

Large Multimodal Models for Embodied Intelligent Driving: Enabling the Next Generation of Autonomous Mobility

Long Zhang, Yuchen Xia, Bingqing Wei, Zhen Liu, Shiwen Mao, Zhu Han, Mohsen Guizani

原文摘要

The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (EI) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article proposes a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning for real-time policy optimization. This article particularly details the foundational principles of EI driving and LMMs, and also introduces the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. The proposed framework, evaluated through a lane-change planning case study, achieves at least a 19% performance improvement over the baselines, as verified by simulations. Finally, key open challenges and future research directions are identified to guide subsequent work.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04625

QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution

Manzong Huang, Chenyang Bu, Yi He, Jiapu Wang, Xindong Wu

原文摘要

Multi-hop retrieval-augmented generation (RAG) supports Web information seeking and fact verification by recovering complementary evidence across related pages within a limited retrieval budget. Scoring evidence independently against the original question can miss supporting units whose relevance emerges through intermediate facts. Iterative retrieval incorporates these facts into subsequent queries, while graph retrieval explicitly models relations among evidence units. Yet fixed-query graph retrievers update entity representations without adapting the query condition to accumulated relational context. We view multi-hop evidence recovery as the coupled evolution of evidence representations and query conditions, with accumulated context informing both what the retriever represents and how it searches for complementary evidence. QueryFlow realizes this perspective by recurrently integrating query-conditioned summaries of graph context into a shared query state, which controls boundary inputs and relation features for subsequent propagation. Across four representative multi-hop question answering (QA) datasets, QueryFlow achieves macro Recall@10 (R@10), Full Recall@10 (FR@10), and LLM-Acc gains of 4.98, 8.40, and 8.0 percentage points over representative baselines, respectively.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗