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

+979新增论文
+781其中 AI 相关
+119已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 22:54 — 2026-11-20 22:54(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 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。

28,961 已收录论文24,030 AI 相关8,912 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 7,900 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2611.15073

When Does Causality Help in Multivariate Time-Series Anomaly Detection?

Long Zhang, Wei Huang, Aishui Rao, Jian Hu, Binxiang Wu, Jie Li, Chen Gong, Linxi Feng

原文摘要

Causality-aware scoring is common in multivariate time-series anomaly detection, yet the literature rarely states when it helps. Holding one causality-guided autoencoder (DeCauAE) fixed, we vary graph quality, anomaly type and protocol against ground truth. Graph quality fixes the payoff: on a twenty-variable DAG the gain over a graph-free autoencoder decays as the graph is corrupted. Anomaly type fixes the target: the structural factor lifts window F1 from 0.800 to 0.976 where anomalies break conditional structure, and its advantage vanishes below a break severity s 0.3. Protocol fixes the ranking: point-adjusted F1 lets a random score match the full model, while range-aware VUS separates the autoencoder family from the classical baselines. On real benchmarks the causal module pays only where density makes a system eligible and cross-subsample reproducibility selects entities inside it; enabling it everywhere costs 0.012 VUS-ROC. The structural factor also transfers to classical detectors .

cs.LG

版本更新 · v2arXiv:2610.06509

Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior

Eliot Walt, Miltiadis Kofinas, Nikolaj Mücke, Efstratios Gavves, Dim Coumou

原文摘要

Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computational costs of classic physics-based models. However, most existing foundation models are deterministic, limiting the generation of large ensembles for accurate uncertainty quantification, extreme weather risk assessment, and long-range weather forecasting. Furthermore, these models incur a large, often prohibitive, computational overhead to train from scratch. To address these shortcomings, we turn a pretrained deterministic prior model, namely the Aurora foundation model, into a generative ensemble-prediction model. To that end, we introduce a novel generative method, Denoising Stochastic Interpolants, combined with a replay buffer for Stochastic Differential Equation (SDE) rollout, enabling probabilistic training of SDE trajectories. Our stochastic foundation model, Xaurora, is finetuned from the small Aurora version, yet it approaches the state-of-the-art on global ensemble metrics and is competitive with the large version of Aurora. Our method is parameter and sample efficient, and generates skilful 15-day forecasts in 7 minutes. Our results demonstrate that deterministic foundation models can be efficiently extended into even stronger stochastic models.

cs.LG · physics.ao-ph

版本更新 · v2arXiv:2611.14183

An Augmented Lagrangian Approach to Lifted Bellman Linear Programming

Jongchan Park, Hyukjun Yang, Narim Jeong, Donghwan Lee

原文摘要

Temporal-difference critics regress onto a bootstrapped target and usually need a target network. Lifted Bellman Linear Programming (LBLP) instead expresses the in-sample optimal values of offline RL as the solution to a linear program over the dataset. Its neural solver ALBUM relaxes the constraints into hinge penalties with fixed coefficients, and its guarantees are conditions on coefficients chosen in advance. We solve the same program with the method of multipliers: the coefficients become multipliers learned by dual ascent, with one penalty parameter $ρ$. In the convex case the fixed points are the KKT pairs of LBLP, and at every stationary point the applied constraint weights balance the objective exactly. The critic can serve a Gaussian actor, a flow actor, and best-of-N sampling, and for the Gaussian actor we propose an advantage-normalized DDPG+BC objective. With a single $Q$ and $V$ and no target network, our AL-LBLP with best-of-N reaches 60.1\% average success on the 50 state-based OGBench tasks. On long-horizon tasks, it reaches 81.5% on humanoidmaze-giant and 79.8% on antmaze-giant. It does not collapse up to batch size 8192.

cs.AI

版本更新 · v2arXiv:2510.02848

Rhythm-TTS: High-Fidelity Shortcut Latent Modeling and Probabilistic Rhythm Generation for Zero-Shot Text-to-Speech

Hieu-Nghia Huynh-Nguyen, Ngoc-Son Nguyen, Long-Khanh Pham Huynh Nguyen Dang, Huy Tien Nguyen, Van Nguyen

原文摘要

Zero-shot text-to-speech (TTS) systems are commonly built on either discrete codec tokens or continuous acoustic representations. Discrete-token models benefit from stable sequence modeling and explicit speech factorization, but they ultimately synthesize speech through codebook lookup and codeword composition, which can accumulate errors and impose a quality ceiling on naturalness and speaker similarity. Continuous-representation models can generate fine-grained speech latents directly, but often require heavier in-context modeling and less explicit alignment. This paper presents \textbf{Rhythm-TTS}, a shortcut zero-shot TTS framework that combines the factorizability of discrete codec tokens with the fidelity of continuous latent generation. Instead of using predicted codec tokens as the final acoustic representation, Rhythm-TTS uses them as a semantic-acoustic prior and directly generates holistic continuous speech latents with flow matching, bypassing the discrete-to-latent reconstruction path at inference time. We further address an underexplored dimension of speech naturalness: rhythm diversity across multiple synthesis runs. Motivated by the hypothesis that rhythm variation is largely governed by phoneme duration changes and the occurrence of silent pauses, we introduce probabilistic Duration and Silence Generators to sample dynamic pacing patterns before acoustic generation. Experiments on zero-shot TTS benchmarks evaluate intelligibility, naturalness, speaker similarity, efficiency, and run-to-run rhythm diversity, showing that the proposed shortcut latent modeling and probabilistic rhythm generation improve the fidelity and temporal naturalness of non-autoregressive zero-shot TTS. Code and audio samples are available at our demo page https://rhythm-tts.github.io.

cs.SD · cs.AI

新论文 · v1arXiv:2611.26057

SlotFlow-GB: A Neural Framework for Trans-Dimensional Inference of Overlapping Galactic Binaries

Niklas Houba, Giovanni Giarda, Davide Piras

原文摘要

The Laser Interferometer Space Antenna (LISA) will observe the millihertz gravitational-wave sky, including millions of long-lived Galactic binaries (GBs), tens of thousands of which are expected to be individually resolvable throughout the mission's lifetime. Extracting these sources requires jointly determining their number and physical parameters from strongly overlapping signals, posing a computationally demanding trans-dimensional inference problem. We introduce SlotFlow-GB, a neural framework that constructs a learned approximation to the trans-dimensional posterior, producing a probability distribution over source multiplicity and parameter densities for individual binaries in a single evaluation, without requiring their number to be specified in advance. We demonstrate this framework using year-long LISA simulations containing up to ten binaries within a 2 $μ$Hz frequency interval, focusing on a high-SNR regime in which source overlap, rather than individual-source detectability, is the primary challenge. The inferred source count differs from the true count by at most one in 94% of cases, while the model identifies individual binaries even when their signals overlap strongly in frequency. A complete evaluation, including parameter sampling, takes just 41 ms per band on one NVIDIA GH200 GPU, or 530 ms on eight laptop CPU threads. We further demonstrate that these distributions can be used to initialize subsequent likelihood-based inference, connecting fast amortized predictions with joint parameter estimation.

astro-ph.IM · cs.LG · gr-qc · physics.data-an · physics.ins-det

新论文 · v1arXiv:2611.26044

Variational Trajectory Flow Matching with a Non-Linear Interpolant

Gurjeet Sangra Singh, Frantzeska Lavda, Alexandros Kalousis

原文摘要

Simulation-free methods such as Trajectory Flow Matching learn dynamics by regressing the time derivative of a local interpolant placed between consecutive observations. The interpolant defines the regression target, and under sparse, irregular sampling, it underrepresents the dynamics and bounds what can be learned. We show that no fixed interpolant dominates: the best of linear, quadratic, spline and quintic changes with the system and with the sampling density. We propose to learn the interpolant instead. An amortized implicit neural representation (INR) is fitted to the training trajectories and frozen as a teacher supplying the target velocity to a learnable velocity field. We further frame the velocity field within a variational framework, yielding a probabilistic forecaster that, at inference, requires only the velocity field and no SDE solver. We evaluate our method on a range of dynamical systems: it consistently achieves high accuracy and more stable long-horizon rollouts under sparser observations, at matched velocity-field capacity.

cs.LO

新论文 · v1arXiv:2611.26040

Streaming-AAA: Streaming AAA Game Video Generation at High Resolution, High Frame Rate, and Low Latency

Zhihao Hu, Jianqi Ma, Jun Zhang, Jiayang Bai, Haifeng Shi, Yanxiang Zhuang, Zhongqian Sun, Weidong Zhang 等 9 位作者

原文摘要

Controllable streaming video generation offers a promising route toward interactive game simulation, yet existing methods remain far from practical gameplay. They often fail to jointly achieve high visual fidelity, high frame rates, and low interaction latency, resulting in poor responsiveness and degraded user experience. We present Streaming-AAA, a new paradigm for controllable infinite generation of AAA-quality game videos. Our system generates 1080p gameplay videos at 43 FPS with 198 ms end-to-end latency interaction on merely NVIDIA A800 GPUs, while supporting long-horizon play without severe temporal degradation or collapse. Streaming-AAA is built upon three key designs. First, we redesign the VAE architecture for efficient high-resolution decoding, enabling real-time synthesis at 1080p. Second, we pretrain the diffusion model using diffusion forcing and significantly extend the temporal training horizon, allowing the model to capture long-term dependencies and maintain persistent memory. Third, we perform post-training distillation and memory compression to improve inference efficiency while retaining visual quality and temporal consistency. Experiments show that Streaming-AAA substantially improves visual fidelity, frame rate, latency, and long-term stability over prior controllable video generation approaches, enabling a significantly more playable experience for interactive AAA game video generation.

cs.CV

版本更新 · v2arXiv:2611.23386

Chorus: Shared N-gram Embeddings with Layer-wise Adaptation

Stephen Chung, Wenyu Du

原文摘要

Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and added to the model's input or to its intermediate layers. Recent designs commonly use a separate n-gram embedding table for each layer, which makes the tables costly in memory and prevents layers from sharing what they learn. However, a single shared table gives every layer the same embedding, leaves no room for layer-wise preferences, and performs poorly in practice. We propose Chorus, in which one set of n-gram embedding tables serves the whole network and every layer reads it in its own way. Each layer maps the refined embedding through its own projection layer, after rescaling its components by factors computed from its current hidden state. Chorus matches the quality of existing n-gram methods with 87% smaller tables: with 1.2B table parameters it predicts text better than FactorEngram and DeepSeek's Engram do with 9.6B. It outperforms Engram, TN-gram and FactorEngram in every setting where we compared them, across table sizes from 20M to 9.6B parameters. We also show that the recently proposed memory-efficient optimizer Ember works well with Chorus, saving 99.2% of table-optimizer memory compared with AdamW without degrading training performance. These results enable further scaling of n-gram embedding tables along the table-size axis by reducing memory use and allowing shared knowledge to be reused across layers.

cs.CL

版本更新 · v3arXiv:2609.20050

The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents

Zhexi Feng, Ruiyi Zhang, Yongbo Yang, Pengtao Xie

原文摘要

Retrieval assembles repository context by ranking passages for relevance to the current query. A coding agent halfway through an issue has already read much of what such a ranker returns. Relevance is scored per passage, but sufficiency belongs to the set: independently scored passages can fill the budget with support for one requirement while another goes unmet. We formulate state-conditioned minimal sufficient evidence recovery: given a captured agent state, recover a compact evidence combination supplying what its next decision still lacks. SERBench measures this on 500 held-out states from 45 repositories, recording what the agent has seen, crediting only sets that satisfy every annotated evidence requirement of the current decision, and separating set recovery from candidate discovery. MSS-Complement treats acquisition as set construction, not ranking. Three semantic calls propose a jointly sufficient set, search for what it lacks, and return 4-8 intact source units within 6,144 tokens. One configuration, fixed on calibration data, recovers a complete set for 73.0% of those states at five items and 80.6% at eight, against 61.4% and 72.4% for Qwen3 embedding with reranking. A matched control ranking by similarity alone recovers fewer complete sets, placing the margin over it in the set-level policy, not the computation. The lead persists from frozen repository source with no gold-derived pool. On AMA-Bench it answers from a 76.2% smaller answer prompt, with accuracy 2.08 points above that benchmark's own memory agent. Removing one required group from a complete set costs repair-localization precision under two executors. Retrieval for agents is better posed as recovering what a decision lacks than re-ranking what an issue resembles.

cs.IR · cs.AI · cs.CL

版本更新 · v4arXiv:2610.32192

Identifying codes of Archimedean grids

Rudini Sampaio

原文摘要

An identifying code of a graph is a dominating set $C$ such that the sets $N[v]\cap C$ are pairwise distinct. The minimum density of an identifying code has been studied extensively for several infinite grids. It is known to be $1/4$ for the triangular grid and $7/20$ for the square grid, whereas for the hexagonal grid the problem is still open, between $5/12$ and $53/126$. These three grids are the regular members of the family of the eleven Archimedean grids. In this paper, we start a systematic study of identifying codes in this family. We determine the minimum density for five of the nine Archimedean grids for which it was not known: it is $2/3$ for the truncated hexagonal grid, $3/7$ for the truncated square grid, and $1/3$ for the trihexagonal (kagome) grid, the elongated triangular grid and the snub hexagonal grid. All lower bounds are proved by the discharging method. For the three remaining non-regular Archimedean grids, we also obtain some bounds: the minimum density lies between $3/7$ and $13/30$ for the truncated trihexagonal grid, between $1/3$ and $11/30$ for the rhombitrihexagonal grid, and between $2/7$ and $9/28$ for the snub square grid. As a by-product, we prove that every identifying code of a cubic graph with the slow growth property in which every vertex lies on exactly one triangle (resp. $4$-cycle) has density at least $2/3$ (resp. $3/7$).

math.CO · cs.DM

新论文 · v1arXiv:2611.26024

ForeSeek: Foresight-Driven Reasoning for Long-Form Video Understanding

Yuchen Sun, Siyuan Cheng, Shi-Zhe Chen, Yixin Qin, Jinwen Luo, Zheng Wei

原文摘要

Long-form video understanding, as a fundamental yet crucial vision task, is being revolutionized by multimodal large language model (MLLM)-based video agents. However, the retrieval-driven nature inherent to these agents creates a significant bottleneck, forcing them to reactively fetch clips based on local saliency without a global temporal plan. To address this, we present ForeSeek, a foresight-driven video agent that transforms long-video reasoning from reactive retrieval into predictive exploration. Rather than blindly probing the timeline, ForeSeek forms visually grounded expectations over unseen temporal regions, verifies them through targeted observations, and continuously refines its search based on emerging evidence, where failed expectations serve as informative signals for principled backtracking. Furthermore, we develop a two-stage training framework that equips MLLMs with foresight-guided reasoning and efficient decision making. Extensive experiments on five long-video benchmarks demonstrate that ForeSeek consistently improves the efficiency--accuracy trade-off of long-video reasoning, achieving competitive or superior accuracy while observing $2.5$--$4.4\times$ fewer frames than the strongest search-based agent. Code is available at https://github.com/harry0021/ForeSeek

cs.AI

新论文 · v1arXiv:2611.26020

FrontierReplay: Split-Free Exact Prefix Caching for Hybrid Language Models

Zekun Wang, Yizhuo Wang

原文摘要

Hybrid language models combine self-attention with recurrent layers whose in-place state updates restrict prefix reuse to exact saved positions. Saving states on a coarse grid wastes reusable prefixes, whereas existing fine-grained exact caches must cut the prefill forward pass at each mid-prompt checkpoint, adding scheduler steps that outweigh the reuse gains under load. We observe that across multi-turn chat, agent loops, document question answering, and tree search, prefix reuse almost always ends at structural boundaries predictable in advance, such as turn ends and known branch points. We present FrontierReplay, a prefix caching system that materializes exact checkpoints at these boundaries without cutting the prefill. While the forward pass runs uncut, FrontierReplay logs a short window of recurrent-layer inputs and invokes a cross-layer, state-only replay kernel to build the target state 6-37x cheaper per token than full recomputation without host synchronization. A frontier-aware retention policy prioritizes active anchors and proven branches while lending dead checkpoint slots to the attention KV cache. Across diverse hybrid architectures, model scales, and workloads, FrontierReplay delivers clear gains over existing exact caches, lowering median time to first token (TTFT) by 16-89% (up to 8.9x), raising 80% service-level objective (SLO) capacity by up to 1.73x, and improving goodput by up to 4.26x (3.67x at larger scales). Compared with approximate replay methods, FrontierReplay delivers up to 1.54x higher goodput while preserving exact task accuracy, avoiding the up to 17% accuracy drop suffered by approximation on long contexts.

cs.LG

新论文 · v1arXiv:2611.26004

Extracting Value from Grey Literature: processes and technologies for aggregating and analyzing the hidden big data treasure of organizations

G. Motta, R. Puccinelli, L. Reggiani, Massimiliano Saccone

原文摘要

Grey literature can be a valuable source of information about organizations activities and, to a certain extent, about their identity. Some of the major problems that hinder their full exploitation are the heterogeneity of formats, the lack of structure, the unpredictability of their content, the size of the document bases, which can quickly become huge. The collection and mining of grey literature can be applied to individual organizations or classes of organizations, thus enabling the analysis of the trends in particular fields. To this end, some techniques can be inherited from the best practices for the management of structured documents belonging to well identified categories, but something more is needed in our case. Obvious steps are: identifying sources, collecting items, cleansing and de-duplicating contents, assigning unique and persistent identifiers, adding metadata and augmenting the information using other sources. These phases are common to all digital libraries but further steps are required, in our opinion, in the case of grey literature in order to build document bases of value.

cs.DL

版本更新 · v2arXiv:2609.02402

A Physics-Consistent Benchmark for Contact-Rich Human-Robot Interaction in Assistive Care

Chengxiao He, Shenghai Yuan, Liuqun Fan, Shenzhe Zhu

原文摘要

Conventional task-level evaluation asks whether a robot policy completes a specified action, but can miss failures that emerge only during physical human contact. This limitation is critical in contact-rich assistive tasks, where meaningful evaluation requires a physically responsive human, interaction-quality assessment beyond task success, and a leak-free observer-scorer protocol. We introduce a physics-consistent benchmark for contact-rich human-robot interaction, instantiated in robot-assisted bathing. The benchmark combines a deformable, passively responding human, physics-aware scores alongside task-level success, and a frozen vision-only / scorer-only evaluation protocol. To establish physical validity, region-wise simulated responses are calibrated against force-indentation measurements from Franka impedance pushes on a medical-care manikin. Under a frozen T1-T7 protocol with 140 runs per method, an LLM-augmented state machine (State Machine) achieves 72.9% task success but drops to 56.4% after correct-region and force-safety screening; VoxPoser produces lighter and more stable contact but completes only 27.9% of trials; and zero-shot pi0.5 achieves 0.7% task success with no correct-region or safety-gated successes. These results show that task completion alone does not imply physically valid contact and motivate physics-aware screening before deployment of contact-rich assistive robot policies.

cs.RO

新论文 · v1arXiv:2611.25986

Seeing Beyond the Obvious: Complementary Semantic Guidance for Salient Single-Positive Multi-Label Learning

Tong Jin, Meng-Long Wang, Xingyu Zhao, Sheng-Jun Huang

原文摘要

Salient Single-Positive Multi-Label Learning (SalSPML) assigns each image its most salient positive label, leaving other classes unlabeled. Existing methods construct class-level Salient Prototypes from observed positives to guide the recognition of unobserved classes. However, since salient annotations favor visually prominent instances, these prototypes may not fully capture the visual diversity of hidden positives, resulting in insufficient positive supervision. To address this limitation, we propose CoST, a Coverage-guided Complementary Soft-Target Refinement framework that supplements Salient Prototypes with complementary class-semantic information. Specifically, CoST identifies semantically relevant candidates from unknown classes by leveraging task-learned category information and image-text semantic correspondence. The selected candidates are then aggregated into class-wise Coverage Prototypes to complement the semantic representations provided by Salient Prototypes. Furthermore, we introduce a ranking-based selective refinement strategy that identifies classes receiving stronger semantic support from Coverage Prototypes and selectively enhances their soft targets while preserving the base soft targets for the rest. Experiments on multiple benchmarks demonstrate the effectiveness of CoST, with strong performance gains over existing baselines.

cs.LG

新论文 · v1arXiv:2611.25981

Safe Subgame Resolving in Multiplayer Games

Boning Li, Longbo Huang

原文摘要

Poker and other games with hidden information are too large to solve in one pass. Strong systems compute a complete blueprint strategy offline and refine it in real time inside the reached subgame. In 2p0s games, a safety theorem guarantees that subgame resolving never increases how much an adversary can gain by exploiting the resolved strategy relative to the blueprint strategy. With three or more players acting independently, no such guarantee exists yet, and heuristic resolving can increase the profile's best-response gap. We prove the first conditional safety theorem for uncorrelated multiplayer subgame resolving, a post-hoc certificate for any delivered update. The best-response gap of the resolved profile exceeds that of the blueprint by at most four terms. Two concern the resolver: the subgame value the blueprint promised without realizing ($A_i^{S}$) and the resolver's subgame solve error ($\varepsilon_i$). The other two are the opponents' best-response gains inside the subgame over their promised values ($\sum_q M_{q}$) and a structural tax ($Θ$), which measures how much the players' total utility can change. The tax is zero in constant-sum games, including every rake-free poker variant. Constructions attain each term with equality. On three-player Leduc poker and on Kuhn poker with up to six players, resolving without a certificate raises the gap beyond a small tolerance in 12% to 100% of the updates. The certificate flags every such update and accepts 41% (Kuhn) and 86% (Leduc) of the standard resolving updates. A resolver that keeps the blueprint whenever the certificate exceeds the tolerance delivers no harmful update. The certificate needs only one best-response pass per opponent inside the subgame, so real-time multiplayer solvers that refine a blueprint can attach it as a safety check. Code is available at https://github.com/lbn187/MultiPlayerSolver

cs.GT · cs.AI

新论文 · v1arXiv:2611.25980

Learning What Actions Change: Action Effect Matching for Dynamics-Faithful World Models

John Won, Yonghoon Dong, Jinwoo Shin

原文摘要

World models aim to predict environment dynamics under actions, enabling the prediction of action consequences without executing them in the real world. Yet despite producing increasingly realistic videos, current world models often fail to capture how small action changes affect future observations. This limits their use in tasks such as robotic policy evaluation and model-based planning, where nearly identical actions can lead to qualitatively different outcomes. To address this, we propose AFFECT, an auxiliary training objective for learning the distribution of visual changes induced by action perturbations. Specifically, we inject temporally correlated noise into the actions of a policy trained on task-agnostic human teleoperation. We then train the world model so that its generated videos respond to this noise as the recorded videos do, without requiring repeated executions from the same initial state. Across OGBench simulation and real-world DROID and ALOHA-2 setups, AFFECT makes world-model rollouts more faithful to real outcomes. On DROID, the Pearson correlation between policy success rates in the world model and on the real robot rises from 0.47 to 0.79, alongside up to 23% lower FVD. These gains carry over to planning, where selecting actions with AFFECT-trained world models improves task success by up to 8.3%.

cs.RO · cs.CV

版本更新 · v2arXiv:2608.24336

On the Maximum Number of Vertices that Belong to Every Metric Basis

Anni Hakanen, Ville Junnila, Tero Laihonen, Havu Miikonen, Ismael G. Yero

原文摘要

Resolving sets of graphs have been widely studied since their introduction in the 1970's by Slater and, independently, by Harary and Melter. The minimum cardinality of a resolving set of a graph $G$ is called the metric dimension of $G$ and is denoted by $\dim(G)$. In this paper, we concentrate on the existence of vertices in a graph $G$ that belong to all metric bases of $G$, i.e. resolving sets of cardinality $\dim(G)$. Such vertices are called basis forced vertices, and we denote the number of them by $\mathrm{bf}(G)$. We show that $\mathrm{bf}(G)\le 2/3(n-\dim(G)-1)$ for any connected nontrivial graph $G$ of order $n$. In addition, we show that this bound can be attained. Furthermore, it also implies that $\mathrm{bf}(G)\le 2/5(n-1)$ holds for any nontrivial connected graph $G$. This result answers a question posed by Bagheri \emph{et al.} in 2016. Moreover, we provide a complete realization of the parameters $n$, $\dim(G)$ and $\mathrm{bf}(G) \ge 1$ within the previous bounds. We consider some extremal cases related to basis forced vertices in a graph, in particular, we give a full characterization of the graphs with $\mathrm{bf}(G) = 2$ and $\dim(G) = n-4$.

math.CO · cs.DM

版本更新 · v3arXiv:2609.30059

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

原文摘要

Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted optimizers explore these opportunities through kernel generation and refinement; yet translating isolated kernel improvements into model-level gains remains a challenge. We present KernelOPT, a profiling-guided multi-agent system for GPU kernel optimization. It inspects generated Triton kernels and external library calls in compiler artifacts to guide synthesis and refinement, then assembles and evaluates the resulting model. Four stages of validation combine execution checks, multi-seed numerical comparison, model-level checking with a float64 fallback and end-to-end performance gating ($γ{=}1.03$). The system supports PyTorch nn.Modules, standalone Triton kernels, and Helion kernels. It is evaluated on all 250 KernelBench problems on NVIDIA H200 which includes 100 single-operator problems (Level1), 100 composite operators (Level2), and 50 model architectures (Level3). KernelOPT achieves geometric mean speedups over torch.compile of 1.40$\times$, 1.15$\times$ and 1.07$\times$ respectively across L1, L2 and L3. Among problems exceeding 1.03$\times$ speedup, the geomeans are 2.54$\times$ (36 L1), 1.84$\times$ (23 L2), and 1.37$\times$ (11 L3). These gains include arithmetic-precision changes and task-specific algebraic simplifications under the evaluated numerical tolerances. The evaluation also reveals discrepancies between isolated kernel improvements and end-to-end performance, motivating model-level measurement alongside kernel-level optimization. Code is available at https://github.com/TorchedHat/KernelOPT.

cs.DC · cs.AI · cs.LG

版本更新 · v2arXiv:2605.27980

Periodic and Harmonic Periodic RoPE for Length Extrapolation in LLMs

Simin Huo, Ning Li

原文摘要

The ability to process long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. Rotary position embedding (RoPE) gives every token a new rotation angle, so a model eventually meets angles it never saw in training, i.e., position exhaustion. We propose Periodic RoPE (P-RoPE), a positional encoding mechanism that operates in conjunction with sliding window attention. It repeats the first sliding-window-size \(W\) angles of the RoPE table, so the model needs only \(W\) distinct angles. P-RoPE works but introduces a wrap error at the window boundary. We further propose Harmonic Periodic RoPE (HP-RoPE), which removes the error by choosing frequencies that complete whole turns in \(W\) tokens. We compare models that share the same architecture, data, and schedule and differ only in the window-layer position encoding: standard RoPE, P-RoPE, and HP-RoPE. The results show that P-RoPE and HP-RoPE keep perplexity nearly flat from the training length \(768\) to \(16\)k, while RoPE, NTK, and YaRN rise. In a format-free Passkey test at \(16\)k, they remain at \(99\)--\(100\%\), against \(11\)--\(37\%\) for those RoPE interpolations. The code is available at \href{https://github.com/Cominder/miniwin}{https://github.com/Cominder/miniwin}.

cs.CL · cs.AI

版本更新 · v3arXiv:2604.15214

Optimal algorithmic complexity of inference in quantum kernel methods

Elies Gil-Fuster, Seongwook Shin, Sofiene Jerbi, Jens Eisert, Maximilian J. Kramer

原文摘要

Quantum kernel methods are among the leading candidates for achieving quantum advantage in supervised learning. A key bottleneck is the cost of inference: evaluating a trained model on new data requires estimating a weighted sum $\sum_{i=1}^N α_i k(x,x_i)$ of $N$ kernel values to additive precision $\varepsilon$, where $α$ is the vector of trained coefficients. The standard approach estimates each term independently via sampling, yielding a query complexity of $O(N\lVertα\rVert_2^2/\varepsilon^2)$. In this work, we identify two independent axes for improvement: (1) How individual kernel values are estimated (sampling versus quantum amplitude estimation), and (2) how the sum is approximated (term-by-term versus via a single observable), and systematically analyze all combinations thereof. The query-optimal combination, encoding the full inference sum as the expectation value of a single observable and applying quantum amplitude estimation, achieves a query complexity of $O(\lVertα\rVert_1/\varepsilon)$, removing the dependence on $N$ from the query count and yielding a quadratic improvement in both $\lVertα\rVert_1$ and $\varepsilon$. We prove a matching lower bound of $Ω(\lVertα\rVert_1/\varepsilon)$, establishing query-optimality of our approach up to logarithmic factors. Beyond query complexity, we also analyze how these improvements translate into gate costs and show that the query-optimal strategy is not always optimal in practice from the perspective of gate complexity. Our results provide both a query-optimal algorithm and a practically optimal choice of strategy depending on hardware capabilities, along with a complete landscape of intermediate methods to guide practitioners. All algorithms require only amplitude estimation as a subroutine and are thus natural candidates for early-fault-tolerant implementations.

quant-ph · cs.LG

新论文 · v1arXiv:2611.25970

The Depth of a Prediction: Where Language Models Resolve a Word Predicts Human Reading Time

Donato Riccio, Fabrizio Maturo

原文摘要

Surprisal from a language model's final layer predicts how long people read a word, yet the model computes its prediction across many layers. We read each word's prediction at every layer with the tuned lens and summarize this layerwise surprisal trajectory by its resolution depth, the depth around which its change is centered. On eight English eye-tracking and self-paced reading corpora (81,957 words) and ten GPT-2, OPT and Pythia models, words that a model resolves later, and the words after them, are read more slowly than equally surprising words. Resolution depth improves held-out prediction beyond final-layer surprisal, entropy and the best single layer by 0.26 millinats per word (pooled p = 0.001), about a third of entropy's gain, and each model family gains, GPT-2 and Pythia through one corpus each. The net gain varies between corpora (random-effects mean 0.07, p = 0.37); against layer-shuffled depth, which adds as many coefficients, it is positive in seven of eight corpora (random-effects mean 0.23, p = 0.016), and untrained networks show no gain under the logit lens. Pooled over corpora, the effect holds with corrected word probabilities and beyond first-to-last-layer divergences, and a whole-trajectory functional regression adds no significant information beyond resolution depth.

cs.CL · cs.LG

新论文 · v1arXiv:2611.25958

Learning optimal gaits and styles for terrain-adaptive quadruped locomotion

Guillaume Bellegarda, Auke Ijspeert

原文摘要

Animals use many different gaits to locomote at different speeds across varying terrains. A longstanding question in biology and robotics is: which gait is best? This question is most often addressed from an energy-efficiency perspective on flat terrain, leaving open how the answer depends on terrain and on the criterion optimized. Here we show that gait optimality is determined jointly by terrain, performance metric, and velocity. We use deep reinforcement learning and networks of abstract oscillators, modeling spinal central pattern generators, to learn 11 quadrupedal gaits across diverse challenging terrains, together with the locomotion style (base height, foot ground clearance, foot offsets) that each requires. A second policy then selects among them to optimize a user-specified criterion such as cost of transport, base stability, or joint smoothness. Across these performance metrics and within this repertoire, every gait is optimal under at least one terrain-metric-velocity combination. The framework adapts zero-shot to gait couplings and styles never seen during training, to terrains far beyond the training distribution, and to larger quadrupeds five times the training mass. With a single additional pitch-tracking reward term, the same gait couplings also support bipedal-mode locomotion. Our method provides a general and systematic way to produce expressive locomotion and to select the gait best suited to a given terrain and criterion. Project page: https://guillaume10.github.io/terrain-gaits.

cs.RO

新论文 · v1arXiv:2611.25938

DTS: Delta-Based Tile Scoring for Efficient Long-Context Sparse Attention

Emre Uğur, Jiawen Qi, Qinyu Chen

原文摘要

Large language models (LLMs) increasingly need to process long documents and codebases, making long-context attention a major prefill bottleneck. Block sparse attention reduces computation by skipping unimportant blocks of the attention matrix, but scoring blocks accurately can itself be expensive. We propose Delta-Based Tile Scoring (DTS), a training-free, content-adaptive tile scoring method for sparse block attention. DTS selects query and key anchors according to local vector changes, using fewer representatives in redundant regions while retaining more detail in heterogeneous regions. To accelerate anchor selection, parallel delta packing partitions the query and key sequences into tile-aligned chunks and performs bounded local scans over these chunks concurrently. The selected tiles are then computed using the original query, key, and value vectors. On LLaMA-3.1-8B-Instruct, DTS keeps average RULER and LongBench scores within 0.10 percentage points of full attention, with RULER evaluated up to 128K tokens. At 128K tokens, DTS reduces measured scoring-pipeline latency by 38% compared with XAttention. On four NVIDIA H100 GPUs, it achieves a 3.3$\times$ prefill speedup over a PyTorch full-attention baseline using FlashAttention-2 at 512K tokens.

cs.LG

版本更新 · v3arXiv:2505.20003

TabPFN: One Model to Rule Them All?

Qiong Zhang, Yan Shuo Tan, Qinglong Tian, Pengfei Li

原文摘要

Hollmann et al. (Nature 637 (2025) 319-326) recently introduced TabPFN, a transformer-based deep learning model for regression and classification on tabular data, which they claim "outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time." Furthermore, they have called TabPFN a "foundation model" for tabular data, as it can support "data generation, density estimation, learning reusable embeddings and fine-tuning". In this paper, we provide a tailored explanation of how TabPFN works for a statistics audience, by emphasizing its interpretation as approximate Bayesian inference. We then explore the significance of TabPFN to the field of statistics: We show that an out-of-the-box application of TabPFN can sometimes outperform specialized state-of-the-art methods for semi-supervised parameter estimation, prediction under covariate shift, and heterogeneous treatment effect estimation. As a partial explanation for the predictive effectiveness of TabPFN, we show that it can simultaneously adapt to both nonparametric structure and parametric structure, for instance, sometimes outperforming LASSO even when assumptions are correctly specified. All experiments can be reproduced using the code provided at https://github.com/qinglong-tian/tabpfn_study (https://github.com/qinglong-tian/tabpfn_study).

cs.LG · stat.ME · stat.ML

新论文 · v1arXiv:2611.25930

Why Flat Drafts Stay Flat: Region-Mean Latents Govern Texture in Flow-Based Image Generation

Zihan Gu, Jiangcan Jia, Hua Zhang, Lulu Zhao

原文摘要

Flat color-block drafts specify layout and regional color while leaving interior detail unspecified, yet pretrained flow-based generators can preserve their flat appearance even under photorealistic prompts. We trace this behavior to a cross-scale mechanism linking fine pixel variation to regional means in variational autoencoder (VAE) latent space. Flattening photo regions systematically shifts their latent means, with offsets concentrated along a shared channel direction within each backbone. Controlled field exchanges in FLUX.1-dev and Qwen-Image establish the effect of this displacement on texture generation: adding the photo-derived regional mean field to a flat latent restores texture, whereas adding its complementary field alone largely preserves flatness. A second-order encoding expansion explains how encoder curvature can convert zero-mean perturbations into mean shifts. An analytically solvable conditional Gaussian flow shows how regional noise averaging enables near-unit endpoint sensitivity at high signal-to-noise ratios. This mechanism motivates training-free rendering through pixel dither before encoding, mean-field scaling, and early boundary holding. Paired low-rank adaptation (LoRA) with draft conditioning improves content recovery and produces photo-like regional means under the standard velocity objective. Explicit regional mean guidance remains effective after adaptation, continuously controlling texture and improving color fidelity. These findings connect encoding shifts to persistent generation behavior and support interventions evaluated for texture, spatial fidelity, and semantic recovery.

cs.CV

版本更新 · v2arXiv:2609.37745

Optimizer-dependent training dynamics converge to the same one-third optimal data scaling

Hyunseok Lee, Mihir Basil, Yizhou Liu, Jeff Gore

原文摘要

Neural scaling, in which loss falls as a power law with training, is central to large language models, and one recent proposal is that a $1/3$ exponent emerges from learning peaked distributions. That account describes SGD, but models in practice are trained with adaptive optimizers. Here we separate two exponents the $1/3$ account does not distinguish: how fast the loss falls with training steps along a single run, and how fast the optimally tuned loss falls with dataset size $D$. We show that the first, a dynamic exponent, is optimizer-specific while the second, an optimal data exponent, converges to $1/3$ across optimizers. In an online teacher-student model we decompose the loss into norm growth (radial) and alignment toward the teacher direction (tangential), each decaying as a power law with dynamic exponents $α_{r}$ and $α_{t}$. Under SGD, both are close to $1/3$, so the data exponent is also $1/3$ across different learning rates. Under Adam the two separate: $α_{r} \simeq 0.48$ but $α_{t} \simeq 0.08$. Since the total loss is minimized when these two parts are balanced, the optimal learning rate is optimizer-dependent: $D$-independent for SGD but falls with $D$ for Adam. Yet tuned to that optimum, the loss returns to $D^{-1/3}$ for both. A stochastic-dynamics analysis explains why: the optimizers can trade decay speed between the two channels, but they all fall on a single dynamic exponent relation, $2α_{r}+ α_{t} = 1$, which fixes the optimal data exponent at $1/3$. Across seven optimizers, including Muon, the measured exponents are consistent with this relation, and the optimal-loss envelopes agree with $D^{-1/3}$ across them. The optimizer sets how fast a model learns per step; tuned optimally, it changes the prefactor but not the rate at which loss falls per sample.

cs.LG

版本更新 · v2arXiv:2611.04663

Best-of-Depth: Learning Exploratory Dynamics in Looped Transformers

Shota Takashiro, Takeshi Kojima, Masanori Koyama, Kohei Hayashi, Yusuke Iwasawa

原文摘要

Looped Transformers extend inference-time computation through repeated latent-state updates, but final-depth training does not directly encourage useful intermediate alternatives. We introduce Best-of-Depth (BoD), which trains a recurrent trajectory as a candidate set by minimizing prediction loss across depths. Different valid targets can be matched at different depths without architectural changes or depth-specific labels. An exact-match analysis connects this objective to solution coverage. On N-Queens completion and graph coloring, BoD improves coverage over final-depth and intermediate-supervision objectives. N-Queens coverage reaches 91.03%, versus 45.75% for final-depth training. Further experiments show discovery beyond the training depth and recovery of solutions withheld from teacher pools on familiar inputs. Fine-tuning a pretrained looped language model with BoD yields higher pooled code-generation success than final-depth training when programs are generated separately at evaluated fixed depths. These results support training recurrent computation for solution discovery along its trajectory.

cs.LG · cs.AI

新论文 · v1arXiv:2611.25903

From Cases to Criteria: Reusing Evaluation Knowledge for Task-Specific Rubric Generation

Qiyan Deng, Long-Kai Huang, Kangfei Zhao

原文摘要

Query-specific rubrics make LLM evaluation more fine-grained and transparent, and generating high-quality rubrics requires both identifying the target query's evaluation scope and specifying concrete checks. Historical rubrics provide reusable evaluation experiences, yet existing approaches reuse either complete query-rubric cases or aggregated criteria and dimensions without explicitly connecting recurring evaluation requirements to their criterion-level evidence and source-query context. This can preserve irrelevant task details or lose the broader evaluation structure. In this paper, we introduce RubricDuo, which organizes historical query-rubric pairs into a Rubric Knowledge Graph linking evaluation dimensions, shared concepts, local concepts, criteria, and queries, where reusable evaluation requirements across queries are abstracted by shared concepts. Given a target query, RubricDuo first combines concepts relevant to the target query with retrieved historical cases to draft a rubric with broad coverage. It then revisits each draft criterion, retrieves concept-linked historical criteria and their source queries, and adapts applicable evidence to refine the criterion. Experiments on RubricBench and HealthBench demonstrate that RubricDuo achieves the overall best performance among the evaluated automatic methods in both alignment with human-authored rubrics and downstream LLM judging.

cs.AI

新论文 · v1arXiv:2611.25898

Verifiable Logic in Medical LLMs: A Critical Review of Agentic Clinical Reasoning Optimization and Neuro-Symbolic Grounding

Youssef ElNahas, Adel Ammar, Soumaya Chaffar, Wadii Boulila

原文摘要

Clinical large language models are usually judged by whether the final answer is right. Yet a model can reach a fluent, plausible output through invalid reasoning that static benchmarks do not detect, and confident hallucination, causally invalid inference, and spurious demographic shortcuts can pass conventional evaluation. This critical review covers four paradigms in turn: how clinical hallucination arises and why static metrics miss it; the agentic hallucination cascade, in which multi-agent and tool-augmented systems propagate and amplify early reasoning errors; process reward modeling as step-level supervision; and neuro-symbolic grounding, in which formal logic engines, ontology reasoners, and knowledge graphs place verifiable constraints on neural output. Within their encoded domains, systems with symbolic veto layers offer guarantees that hold relative to their encoded knowledge, and they report large gains on the safety measures they use. These results come from single studies, mostly in simulated or small-sample settings, and are not directly comparable with neural baselines. Process reward models remain bounded by the statistics of their training data. We propose a conceptual framework that maps each agentic failure mode to a symbolic intervention point, and we argue that clinical AI safety depends substantially on system architecture. Because current regulation emphasizes performance and does not require verification of reasoning steps, we argue that responsible certification should also audit reasoning trajectories alongside accuracy on static benchmarks.

cs.CL · cs.AI · cs.CY · cs.LG