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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 12:14 — 2026-11-22 12:14(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v3arXiv:2510.19374

Survival of the fittest Cox model: Pivotal variable selection for time-to-event data

Maxime van Cutsem, Sylvain Sardy

原文摘要

We revisit Cox's proportional hazards model to improve variable selection in survival analysis. A square-root transformation of the partial likelihood renders the selection of the regularization parameter asymptotically pivotal: the baseline hazard and the censoring rate cancel exactly, and the way censoring is spread over time only enters through a bounded correction of order $1/\log n$. Using martingale residuals, we compute this penalty level by Monte Carlo without reordering the design matrix. The resulting criterion borrows from information criteria such as BIC and from penalized regression methods such as the lasso, taking the best of both. On simulated and real data, our method substantially improves upon state-of-the-art approaches used daily.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2611.25955

Web search in Latin America: language models use less local and diverse news than search engines

Francisco W. Kerche, Franziska Sofia Hafner, Felix M. Simon, Luc Rocher

原文摘要

AI platforms are becoming a major gateway to news and current events. This shift risks amplifying existing geographical biases that favour narratives from wealthier countries over those from the Global South. This is particularly relevant in Latin America, which accounts for the largest share of AI usage in the Global South. We examine how information about Latin America changes when users shift from conventional search engines to LLM-based search. We construct a dataset of 1,901 current events across nine Latin American countries, craft realistic queries, and submit them to three search engines and four language models. We vary query language and user location to represent local, diaspora, tourist, and foreign user scenarios. Across 49,207 requests and 8,834 unique domains, language models return a less diverse set of news sources than search engines. Across user types, the share of domestic news returned by language models is inconsistent. For local users, while search engines already return only 41.3\% local news, language models return a further 3.6 to 11.6 percentage points less. Taken together, our findings suggest that LLM-based search can reproduce and, in some settings, amplify geographical hierarchies in the reach and visibility of news sources. We release an open dataset to support multilingual and geographically diverse evaluation of LLM-based search, and highlight implications for more equitable information systems design.

cs.CL · cs.AI · cs.CY

新论文 · v1arXiv:2611.25953

Below Three: A 2.8027-Approximation for Moldable Precedence Scheduling

Klaus Jansen, Felix Ohnesorge

原文摘要

We study makespan minimisation for nonpreemptive moldable jobs with arbitrary precedence constraints on identical processors. Each job runs on a chosen number of processors that remains fixed throughout its execution. Allocating more processors to a job can shorten its execution, but may increase total work and delay other jobs. We assume nonincreasing processing times, nondecreasing work, and a convex duration--work relation after dominated allocations are removed. This model includes jobs with concave speedup, for which Jansen and Zhang obtained a $3.291919\ldots$-approximation. Independently and concurrently with our work, Chen obtained a $3.016208\ldots$-approximation for the full convex model and a $2.973912\ldots$-approximation for concave speedup. We give a deterministic polynomial-time $2.8027$-approximation for the full convex model and every number of processors. Our result breaks the factor-three barrier for this model and also improves the approximation guarantee for concave speedup.

cs.DS

版本更新 · v2arXiv:2604.04136

Rethinking Exposure Correction for Spatially Non-uniform Degradation

Ao Li, Jiawei Sun, Le Dong, Zhenyu Wang, Weisheng Dong, Xin Li

原文摘要

Real-world exposure correction is fundamentally challenged by spatially non-uniform degradations, where diverse exposure errors frequently coexist within a single image. However, existing exposure correction methods are still largely developed under a predominantly uniform assumption. Architecturally, they typically rely on globally aggregated modulation signals that capture only the overall exposure trend. From the optimization perspective, conventional reconstruction losses are usually derived under a shared global scale, thus overlooking the spatially varying correction demands across regions. To address these limitations, we propose a new exposure correction paradigm explicitly designed for spatial non-uniformity. Specifically, we introduce a Spatial Signal Encoder to predict spatially adaptive modulation weights, which are used to guide multiple look-up tables for image transformation, together with an HSL-based compensation module for improved color fidelity. Beyond the architectural design, we propose an uncertainty-inspired non-uniform loss that dynamically allocates the optimization focus based on local restoration uncertainties, better matching the heterogeneous nature of real-world exposure errors. Extensive experiments demonstrate that our method achieves superior qualitative and quantitative performance compared with state-of-the-art methods. Code is available at https://github.com/FALALAS/rethinkingEC.

cs.CV

版本更新 · v2arXiv:2609.32478

Agnostic Smoothed Online Regression with Adversarial Responses

Xuanyu Chen, Yue Yu

原文摘要

We study smoothed online prediction with bounded adversarial responses. This widely studied framework bridges i.i.d. sampling and adversarial covariate selection through a smoothness parameter $\textsf{C}_{\textsf{cov}}$, which bounds conditional covariate densities relative to a fixed, unknown base measure. We propose Hedge-Cover, an information-theoretic algorithm that achieves sublinear regret $\widetilde{O}(\sqrt{\text{Pdim}(\mathcal{F}) \textsf{C}_{\textsf{cov}} T})$ for function classes with bounded pseudo-dimension. The algorithm aggregates a carefully constructed family of experts using Hedge, with a prior that links regret to the number of disagreements between a consistent selector and a target function. We bound this number by exploiting covariate smoothness. This answers an open problem posed in \cite{blanchard2025agnostic} on the minimax optimal adaptive regret of the smoothed online regression problem. We establish a matching lower bound for the class of linear predictors. The main intricacy of the lower bound lies in explicitly constructing a challenging sequential covariate distribution supported on mutually orthogonal hyperplanes. This construction may be of independent technical interest. Finally, we revisit the well-specified setting and quantify the effect of response noise. For conditionally $ν^2$-subGaussian responses, we extend the existing lower bound under realizable responses by showing that the minimax expected regret is $Ω((1\vee ν)\sqrt{(\textsf{C}_{\textsf{cov}}-1)dT})$ for a function class of VC dimension $d$. A corresponding upper bound for ERM matches this dependence on $ν$.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2611.25947

Matching Architecture to Workload: Comparing RISC-V Parallel Accelerators for Energy-Efficient Embedded Computing

Luca Colombo, Luigi Ghionda, Amirhossein Kiamarzi, Yvan Tortorella, Riccardo Giunti, Niccolò Giuliani, Samuele Colmi, Angelo Garofalo 等 10 位作者

原文摘要

Embedded computing demands high performance and energy efficiency across workloads with widely different computational characteristics. Choosing the most suitable execution model therefore requires a quantitative understanding of how each model maps to different workload classes. In this paper, we compare three execution models for energy-efficient embedded computing: scalar multicore, stream ing multicore, and vector processing. We use three open-source RISC-V accelerators as representative implementations: the PULP Cluster, the Snitch Cluster, and Spatz, respectively. Their open-source hardware and software stacks enable a controlled comparison based on implementations in the same 12 nm technology and a common benchmark suite. Our results reveal that no single execution model performs best across all workload classes. Spatz delivers the greatest benefits for regular and highly vectorizable compute-intensive applications, achieving up to 4.29x higher performance and 5.17x greater energy efficiency than the other architectures. However, its effectiveness strongly depends on the availability of data-level parallelism and regular computation and memory-access patterns, making it the most sensitive to workload characteristics. The Snitch Cluster performs particularly well on applications with limited parallelism and streamable memory-access patterns, providing up to 5.53x higher performance and 1.45x greater energy efficiency. Conversely, the PULP Cluster is most effective on irregular and control-dominated applications, achieving improvements of up to 5.66x in performance and 2.80x in energy efficiency. Compared with Spatz, however, the greater flexibility offered by PULP and Snitch comes at a non-negligible cost in terms of both area and power.

cs.DC · cs.AR

版本更新 · v5arXiv:2212.06123

Security of Deep Reinforcement Learning for Autonomous Driving: A Survey

Ambra Demontis, Srishti Gupta, Maura Pintor, Luca Demetrio, Kathrin Grosse, Hsiao-Ying Lin, Chengfang Fang, Battista Biggio 等 9 位作者

原文摘要

Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is susceptible to attacks designed either to compromise policy learning or to induce erroneous decisions by trained agents. Although the literature on RL security has grown rapidly and several surveys exist, existing categorizations often fall short in guiding the selection of appropriate defenses for specific systems. In this work, we present a comprehensive survey of 86 recent studies on RL security, addressing these limitations by systematically categorizing attacks and defenses according to defined threat models and single- versus multi-agent settings. Furthermore, we examine the relevance and applicability of state-of-the-art attacks and defense mechanisms within the context of autonomous driving, providing insights to inform the design of robust RL systems.

cs.LG · cs.RO

版本更新 · v4arXiv:2607.22583

Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization

Muhammad Junaid Ali, Smail Niar, El-Ghazali Talbi

原文摘要

Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities. However, deploying them in embedded and edge computing environments remains challenging because of strict latency, memory, and energy constraints. Their large parameter counts and computational demands hinder efficient execution on resource-constrained platforms. Although model pruning has emerged as a viable solution for reducing scale while preserving performance, jointly optimizing layers, attention heads, and Multi-Layer Perceptron (MLP) dimensions remains highly complex. Exhaustively exploring this combined design space is computationally expensive and often leads to local optima or unstable configurations. To address these limitations, we propose a hardware-aware, multi-objective structured pruning framework. The proposed two-stage method explicitly targets latency and model size for efficient deployment on edge devices. In the coarse-grained stage, multi-objective depth pruning removes entire attention and MLP blocks to reduce computational load and memory usage. In the subsequent fine-grained stage, Parallel Bayesian Optimization (PBO) searches for the optimal layer-wise pruning ratios for pruning under latency constraints, while importance-based strategies rank the specific components to be pruned within each layer's allocated budget. Experimental results show that our approach reduces model complexity with minimal impact on commonsense reasoning tasks and zero-shot performance. Our method achieves a favorable trade-off among accuracy, latency, and model size, making it suitable for edge deployment. Across multiple LLMs at 37.5% and 50% pruning ratios, the proposed approach achieves better performance on commonsense reasoning tasks than existing methods while significantly reducing inference cost.

cs.AI · cs.CL

新论文 · v1arXiv:2611.25946

Point Dynamics as Proxy for Robotic World Models

Dong An, Tianyu Liu, Haoran Ding, Wen Yang, Anqing Duan, Zhengzhong Liu, Eric P. Xing, Guangyi Liu

原文摘要

Robotic world models predict future video frames from the current observation and a sequence of robot actions. While recent models follow the given actions closely, manipulated objects often collapse or move inconsistently with the action. We attribute this to the conditioning: an action, or a rendering of the robot, specifies where the robot goes but not how the scene responds, leaving a single video model to infer the interaction dynamics implicitly while also rendering appearance. We therefore separate dynamics prediction from visual rendering, with 3D point dynamics as the proxy between them. Specifically, we lift the first frame into 3D points, simulate how they respond to the robot's motion with a learned point dynamics model, and render the simulated points back into pixel-aligned videos that any video model can read. In controlled experiments on the DROID dataset with two video renderers of different architectures, this point dynamics proxy reduces object motion error by 8.6% and 6.2% without degrading image quality, and by 8.1% on a real bimanual robot. Moreover, the video follows the simulation: more accurate dynamics yield more accurate object motion, and editing the points steers the video. This suggests that advances in dynamics modeling can translate into more faithful robotic world models.

cs.CV

新论文 · v1arXiv:2611.25945

BlockJack: Cross-Tenant Redirection Fault Attacks on Paged KV Cache Address Translation in LLM Serving

Qifan Wang, Jeremy Boy, Jonas Sander, Yansong Gao, Hongsheng Hu, Ye Dong, Thomas Eisenbarth, David Oswald

原文摘要

Large language model (LLM) serving frameworks accelerate inference by retaining previously computed states in a key-value (KV) cache. Paged serving frameworks such as vLLM organize this cache through block tables analogous to OS page tables, which map each request's logical KV blocks to physical KV blocks, forming a software-managed address translation layer. Although fault attacks such as Rowhammer have exploited OS page tables to redirect memory accesses, prior fault attacks on LLMs have largely targeted the data plane, i.e., model weights or KV-cache contents, leaving KV-cache mapping unexplored. We present BlockJack (i.e., Block Hijack), the first KV cache address-translation fault attack in LLM inference. By corrupting block-table entries, BlockJack redirects a request's KV cache reads to blocks assigned to another tenant's request without modifying model parameters, prompts, or cached KV states. It achieves both confidentiality violation (victim information appears in attacker responses) and integrity violation (attacker-supplied context steers victim answers). We study paged KV cache mappings in vLLM and formally characterize when redirect targets are predictable. Across seven models spanning the Qwen, Llama, Gemma, and Phi families, a faulted mapping exposes victim context. For the integrity attack, we examine how topic proximity, intra-topic divergence, and model behavior shape redirected responses. On a 248-scene medical benchmark, the integrity attack causes up to 41.1% of responses to recommend less urgent care, while still appearing consistent with the victim's question. We demonstrate physical feasibility of BlockJack with Rowhammer and subsequently evaluate assignment validation as a defense. Following responsible disclosure, vLLM and Sonar confirmed the vulnerability and proposed patches that we reviewed and validated.

cs.CR

新论文 · v1arXiv:2611.25942

Gradient Boosting with Kolmogorov-Arnold Units for Interpretable Regression beyond Pairwise Interactions

Minjong Cheon, Hanseon Joo, Eunji Lee

原文摘要

Interpretable models for tabular regression, such as the explainable boosting machine (EBM), restrict a prediction to main effects and pairwise interactions so that every part of it can be plotted. When the target depends on three or more inputs jointly, this restriction costs accuracy, and a black-box model with post hoc explanations becomes the usual fallback. Here we present MJBoost, a gradient boosting method whose weak learner is a single Kolmogorov-Arnold unit $g(\sum_p φ_p(x_p))$ with penalized spline inner and outer functions. Each unit is fitted in closed form by alternating penalized least squares, starting from principal Hessian directions of the residual, and categorical and missing inputs enter the units directly. Because a unit depends on each input only through one inner function, the fitted model has an exact functional ANOVA decomposition into main effects, pair effects and a higher-order remainder, which one-dimensional convolutions compute. On synthetic targets of interaction order three to six, the test error of MJBoost is up to 13 times lower than that of EBM, and its decomposition recovers the true variance share of every order to within 0.04. On the 35 regression tasks of the OpenML-CTR23 benchmark, it has a lower test RMSE than EBM on 21 tasks and a higher one on 2 (geometric-mean RMSE -29.1%). On these tasks the main and pair effects of the fitted model explain a median 0.992 of its variance, so the model reads as plots where the data allow, and the decomposition measures the higher-order part where they do not. With Newton steps the same algorithm classifies: on 32 binary tasks of OpenML-CC18 its test log-loss is on par with that of EBM, and on 11 multiclass tasks its mean log-loss is lower than that of EBM on 8 and than that of tuned LightGBM on 7.

cs.LG

新论文 · v1arXiv:2611.25940

Self-Orthogonal MDS Principal-Ideal Codes

Yangcheng Li, Pingzhi Yuan

原文摘要

We investigate Euclidean self-orthogonality and the generalized Reed--Solomon (GRS) property for coefficient-vector codes generated by a monic polynomial $g$ and its shifts $xg,\ldots,x^{k-1}g$, of length $n=r+k$ and dimension $k$, where $°g=r$ and $3\le k\le r$. We give a complete classification, over any algebraically closed field, of the generators for which these codes are both self-orthogonal and GRS. Such generators have either distinct roots in a geometric progression satisfying explicit order and scalar conditions, or a single repeated root in certain positive characteristics. In particular, only finitely many generators occur for fixed $r$, $k$, and characteristic. We determine their maximal self-orthogonal lengths, show that the corresponding maximal-length codes are cyclic or negacyclic, and obtain exact generator counts over finite fields, together with the least fields of definition. In contrast, when $3\le k<r$, we prove that every algebraically closed field supports infinitely many pairwise monomially inequivalent self-orthogonal non-GRS maximum distance separable (MDS) codes in this family. Consequently, arbitrarily many such codes can be realized over a common finite extension of any prescribed finite field, while remaining inequivalent and non-GRS over its algebraic closure.

cs.IT

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

新论文 · v1arXiv:2611.25936

Hellinger Decision Trees for Density Ratio Estimation: Finite-Sample Guarantees

Ren-Rui Liu, Zheng-Chu Guo

原文摘要

Density ratios play a central role in two-sample comparison, distribution-shift adaptation, and generative-model evaluation. However, estimating a density ratio through separate estimation of the underlying densities can be unnecessarily challenging. In this paper, we develop a direct approach to the log density ratio estimation by minimizing a balanced Hellinger risk over additive ensembles of axis-aligned decision trees, trained using Newton boosting. We establish finite-sample guarantees for the estimator produced by the algorithm and derive an explicit convergence rate. Under suitable tail and Hölder smoothness conditions, together with an additional assumption on the progress made at each boosting iteration, our rate matches, up to logarithmic factors, the classical minimax-optimal $ \mathscr{L}^{2} $ rate for function estimation. A key technical contribution is an optimization analysis that exploits the special exponential structure of the Hellinger risk. In particular, we show that the decrease in the second-order Taylor approximation (which is computable) of the empirical risk controls the actual decrease in that risk, yielding a direct optimization guarantee for the boosting algorithm. This allows us to establish statistical convergence guarantees for the algorithm's output without relying on an idealized empirical-risk minimizer. Experiments on synthetic data corroborate the predicted convergence behavior, while experiments on public datasets demonstrate the practical effectiveness of the proposed estimator.

stat.ML · cs.LG

版本更新 · v5arXiv:2507.18061

TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios

Zehan Li, Hongjie Chen, Qing Wang, Yuxin Zhang, Jing Zhou, Hang Lv, Mengjie Du, Yaodong Song 等 12 位作者

原文摘要

Spoken Language Models (SLMs) are expected to support natural spoken interaction beyond task completion. Existing benchmarks assess a range of semantic tasks and conversational capabilities. However, high task scores do not necessarily imply reliable and appropriate spoken interaction. To address this gap, we introduce TELEVAL, a large-scale benchmark focused on Chinese spoken interaction. It evaluates responses to spoken inputs without additional task-specific prompts or predefined answer options. TELEVAL covers two complementary aspects: (1) Reliable Content Fulfillment, which measures semantic accuracy under diverse acoustic and linguistic conditions, and (2) Interactional Appropriateness, which assesses conversational naturalness and appropriate adaptation to auditory cues. Experiments reveal limitations in both aspects. Strong results on factual question-answering datasets do not consistently extend to locally relevant knowledge or challenging speech conditions, such as Chinese cultural questions and dialectal speech. Models also struggle to adapt their responses to auditory cues, even in cases where they explicitly recognize them. We further document a recurring failure pattern, termed the "Caption Trap", in which some responses describe a perceived auditory cue instead of addressing the user's conversational needs. Overall, the evaluated SLMs struggle to deliver consistently accurate and conversationally appropriate responses. TELEVAL provides a diagnostic framework for evaluating both content reliability and conversational adaptation.

cs.CL · cs.AI · cs.SD · eess.AS

新论文 · v1arXiv:2611.25934

AGSR: Aperture-Guided Super-Resolution for Gaussian Splatting

Ayman Alkhateeb, Hadi Amirpour, Christian Timmerer

原文摘要

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but Gaussian rasterization attenuates fine-scale scene structure through the projected covariance of each primitive. We show that contracting these projected covariances at inference time can mitigate the effective bandwidth limitation induced by finite Gaussian footprints, motivating a multi-aperture rendering framework for super-resolution. Based on this insight, we propose AGSR (Aperture-Guided Super-Resolution), a lightweight inference-time framework that progressively fuses multi-aperture renderings using uncertainty-guided feature aggregation and geometric conditioning from transmittance and depth cues. AGSR operates as a plug-in enhancement for pre-trained 3DGS models. Experiments on the Mip-NeRF 360 benchmark show that AGSR outperforms lightweight image-space super-resolution baselines, with gains increasing as the underlying Gaussian representation deteriorates. The results provide evidence that covariance contraction exposes bandwidth-sensitive structural cues attenuated by native Gaussian rasterization. AGSR achieves these improvements while maintaining real-time performance with up to 139k parameters.

cs.CV · cs.GR

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

新论文 · v1arXiv:2611.25927

Fast-JEPA: Advancing the Success-Latency Frontier for Latent World Models

Yao Zhang, Bin Yu, Shijie Lian, Haishan Liu, Changti Wu, Yu Wu, Kai Chen

原文摘要

Latent world models predict the outcomes of action sequences, but comparing candidate plans through recursive rollout remains expensive at test time. We introduce Fast-JEPA, a latent world model planning framework that advances the success-latency Pareto frontier of predictive search. Fast-JEPA reorganizes predictive computation to support effective action-sequence search at low planning cost. It constructs a goal-directed plan to guide search and directly predicts the outcomes of complete candidates for efficient comparison, avoiding recursive state rollout during refinement. Across PushT, Reacher, Cube, and TwoRoom, Fast-JEPA achieves 96.50% average success rate with 2.41x faster planning than INTACT. Search-budget sweeps show that its competitive success and low latency extend across candidate counts and refinement depths. We further introduce DynaGoal, a benchmark for evaluating world-model planning under dynamic out-of-distribution conditions, execution deadlines, and controlled response delays. Fast-JEPA achieves average success rates of 73.83% on DynaGoal-Shift and 87.67% on DynaGoal-Deadline, demonstrating the practical value of low-latency predictive planning under changing control conditions and execution-time constraints. Our code is available at https://github.com/Sofilyzia/Fast-JEPA.

cs.RO · cs.AI

新论文 · v1arXiv:2611.25926

ROAM-GRPO: Enforcing Reasoning Diversity in GRPO via Routed Off-mode Approach Mining

Jeff Duan, Matt Thomson

原文摘要

Supervised fine-tuning (SFT) paired with Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant recipe for post-training LLMs on complex reasoning tasks, but has been shown to collapse the policy into a low-diversity mode. Repeated LLM outputs are nearly identical, and pass@k accuracy converges or degrades as a result. We propose ROAM-GRPO (Routed Off-mode Approach Mining for GRPO), an augmentation to the GRPO algorithm which incentivizes exploration of distinct reasoning strategies and aims to increase output creativity during evaluation. ROAM-GRPO detects well-solved problems during training and transfers them to an "off-mode" track. The model is prompted to produce distinct solution strategies to such problems, which are verified for logical validity and distinctness by an LLM judge and subsequently self-distilled into the policy. Training Qwen3.5-2b on a 1,000-problem subset of the MATH lvl5 dataset, ROAM-GRPO implementation increases peak pass@16 by 4.7% and correct embedding cosine distance by approximately 1.5-2x on a difficult evaluation set.

cs.AI

新论文 · v1arXiv:2611.25925

SpatialMem: Building Quantitative Spatial Reasoning Agents with Hierarchical Memory

Zinan Zheng, Nuo Chen, Jia Li

原文摘要

Vision Language Models (VLMs) have shown remarkable capabilities in qualitative spatial reasoning, but remain limited in quantitative spatial reasoning. Current work leverages the VLM agent to invoke external vision tools to perform computation. However, these methods usually bind each functional requirement to a single predefined vision specialist, implicitly resulting in fixed and rigid tool pipelines. In practice, addressing diverse spatial scenarios and tasks demands a broader diversity in pipeline orchestration and vision specialist selection to achieve robust spatial reasoning. However, such diversity leads to a combinatorial execution space, making it challenging for the agent to orchestrate the optimal pipelines and specialists for different scenarios. In this work, we propose SpatialMem, a memory framework that enables a VLM agent to accumulate tool-use experience and leverage that memory to orchestrate vision specialists to solve the spatial reasoning problem. SpatialMem builds a two-level memory structure, with task memory capturing tool orchestration and scene memory capturing tool selection. It further introduces a dual-state trajectory optimization process to preserve successful tool experiences and refine suboptimal ones. Moreover, existing spatial reasoning benchmarks suffer from quality issues and limited coverage of scene types and tasks. To address these gap, we propose MetricBench, a benchmark covering both indoor and outdoor scenes and three quantitative spatial reasoning tasks. Our method achieves state-of-the-art results on MetricBench, Q-Spatial, and SpatilRGPT-Bench, outperforming best VLM baselines by 32% on MetricBench. Additionally, the memory design yields a 9.1% absolute gain over a memory-free agent on MetricBench.

cs.CV

新论文 · v1arXiv:2611.25924

Ground Truth Bias in AI-Assisted Medical Annotation: A Crossover Study Using an Independent Radiologist Reference Standard

Márton Baltay, Tamás Ilcsik, Márton Borbély

原文摘要

Behavioural evaluations of artificial-intelligence-assisted annotation score every human decision against a reference standard, so their conclusions inherit that standard's validity. We tested how far conclusions about assistance, reliance and individual differences depend on it. Fifty-one non-expert high-school students annotated 50 knee radiographs for osteoarthritis, with and without a deliberately imperfect classifier, in a crossover design; personality and non-verbal reasoning were also measured. Decisions were scored against the public repository labels and against an independent reference standard from a radiologist panel, which graded 23 of the 50 images as indeterminate. Against the repository labels, assistance raised accuracy from 60.4% to 65.3% (odds ratio 1.23, p=0.002). Against the independent standard, the gain on the 27 determinate images was smaller and not significant in the primary model (78.4% to 80.8%; odds ratio 1.16, p=0.178). The apparent benefit had been concentrated on the indeterminate images and was not significant when those images were assigned to either class. The direction of residual over-reliance depended on how indeterminate cases were handled, and the personality trait most strongly associated with accuracy changed identity and sign between standards. Reliance measures are only as valid as the reference standard that defines when the assistant is right.

cs.HC

版本更新 · v2arXiv:2610.36760

GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

Jiale Wang, Chen Zhao, Haoyang Zhang, Yanhao Wu, Fei He, Yanhu Shan, Rui Wu, Wei Ke 等 9 位作者

原文摘要

Feed-forward Gaussian Splatting enables efficient novel view synthesis, but pixel-aligned prediction makes the primitive count grow with image resolution and view count, leading to substantial redundancy and increased computational cost. Non-pixel-aligned methods address this limitation by predicting a fixed number of Gaussians. Without explicit ray and depth constraints, these methods yield misplaced Gaussian centers, causing rendering artifacts under large viewpoint changes. To address this issue, we introduce GeoGSplat, a geometry-grounded feed-forward model that explicitly incorporates geometric priors into the non-pixel-aligned framework. A dual-branch encoder constructs Anchors and Triplane to capture coarse 3D structure and fine-grained scene features, respectively. Subsequently, a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives, enabling 3D reconstruction and novel view synthesis. GeoGSplat surpasses both state-of-the-art pixel-aligned and non-pixel-aligned Gaussian Splatting methods on DTU and NRGBD in terms of novel view synthesis and reconstruction. The advantage of our geometry-grounded paradigm further increases as target viewpoints move farther from the input cameras, demonstrating stronger generalization to large viewpoint changes. Project Page: https://comedy0913.github.io/projects/geogsplat

cs.CV

版本更新 · v4arXiv:2310.06121

From Innermost to Full Almost-Sure Termination of Probabilistic Term Rewriting

Jan-Christoph Kassing, Florian Frohn, Jürgen Giesl

原文摘要

There are many evaluation strategies for term rewrite systems, but proving termination automatically is usually easiest for innermost rewriting. Several syntactic criteria exist when innermost termination implies full termination. We adapt these criteria to the probabilistic setting, e.g., we show when it suffices to analyze almost-sure termination (AST) w.r.t. innermost rewriting to prove full AST of probabilistic term rewrite systems (PTRSs). These criteria also apply to other notions of termination like positive AST. We implemented and evaluated our new contributions in the tool AProVE.

cs.LO

新论文 · v1arXiv:2611.25918

From Code Review Comments to Reuse in Production: An Industrial Study of Extracted Rules

Mutsuha Asada, Yuhei Nakasaka, Keito Tabuchi, Shinpei Hayashi

原文摘要

Much organization-specific code review knowledge remains embedded in comments on individual changes, and recent systems reuse it by turning those comments into rules a language model applies to later changes. Teams must then decide which rules to keep, and the evidence at hand is how often the system's later comments name each rule. Tracing the rules of one such system, Kleene, through 65 days of production use, we found that such a count does not show what a rule contributed. A rule attribution indicates neither whether the source content was preserved nor whether the comment requested a change. Of 56 clauses in 12 rules that later comments named as their reason, 2 were explicit in a source review thread, 38 added conditions to a corresponding passage, and 16 had no passage we could locate; 45 of 79 further comments naming those rules requested no change, 27 of them while stating that the rule applied. On 20 constructed code changes, a reviewer model given only the unedited source thread met the detection criteria on 8 of the 10 that require a report, against 10 of 10 with the extracted rule, a difference whose confidence interval includes zero. Stage counts locate where rules drop out but not why: of 464 rules deployed while the rule-based reviewer subagent ran in their repository, 259 (55.8%) were named, 195 (42.0%) produced a comment that was not withheld, and 94 (20.3%) one with a recorded code change; the largest reduction occurred before any rule was named. Nor did the deployment-time properties we tested settle the choice in advance: retaining the top-ranked half preserved 53.8% of the rules that later produced a non-withheld comment, against 49.2% at random, a difference whose confidence interval includes zero. Judging extracted rules therefore calls for recording each stage separately and comparing each rule against the threads it was extracted from.

cs.SE

新论文 · v1arXiv:2611.25917

LIFT: Latent Flow Matching for Probabilistic Cell Fate Dynamics with Single Cell Snapshots

Bowen Yang, Junda Ying, Yuxuan Wang, Peijie Zhou, Lei Zhang

原文摘要

Lineage tracing links cell states through clonal ancestry, but does not generally identify unique source-descendant pairings. Learning from such data therefore requires a model of conditional outcomes, rather than only the terminal population distribution. We introduce LIFT, a latent flow framework for probabilistic cell-state generation from lineage-informed couplings. Variational inference encodes alternative outcomes in a latent space, while a conditional prior enables sampling from the initial state alone. A Mean Flow decoder predicts future cell state directly, requiring one decoder evaluation per sampling, which makes it convenient to predict cell fate through large scale Monte-Carlo sampling. This construction combines a representation of one-to-many relationships with efficient sampling and an analysis of conditional prediction error. Experiments on synthetic and real datasets demonstrate LIFT's ability to recover both population distribution and cell fate probabilities.

cs.LG

版本更新 · v2arXiv:2605.00581

Gradient Regularized Newton Boosting Trees with Global Convergence

Nikita Zozoulenko, Daniel Falkowski, Thomas Cass, Lukas Gonon

原文摘要

Gradient Boosting Decision Trees (GBDTs) dominate tabular machine learning, with modern implementations like XGBoost, LightGBM, and CatBoost being based on Newton boosting: a second-order descent step in the space of decision trees. Despite its empirical success, the global convergence of Newton boosting is poorly understood compared to first-order boosting. In this paper, we introduce Restricted Newton Descent, a framework for convex optimization with Newton's method on Hilbert spaces with inexact iterates, based on the concepts of cosine angle and weak gradient edge. Within this framework, we recover Newton boosting with GBDTs and classical finite-dimensional theory as special cases. We first prove that vanilla Newton boosting achieves a linear rate of convergence for smooth, strongly convex losses that satisfy a Hessian-dominance condition. To handle general convex losses with Lipschitz Hessians, we extend a recent gradient regularized Newton scheme to the restricted weak learner setting, establishing the first global $\mathcal{O}(\frac{1}{k^2})$ convergence rate for second-order GBDTs. This scheme minimally modifies the classical algorithm by introducing an adaptive $\ell_2$-regularization term proportional to the square root of the gradient norm at each iteration. In numerical experiments, we show that this scheme converges while vanilla Newton boosting may diverge.

stat.ML · cs.LG · math.OC

版本更新 · v3arXiv:2611.06120

ReactWorld: Structuring Interaction Responses for Embodied Video Generation

Hanwei Liu, Huijia Zhang, Hanzhang Wang, Guangyu Liu, Hanbei Zhan, Linjie Hu, Bin Xiao, Xuan Zhou 等 9 位作者

原文摘要

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired by chain-of-thought reasoning, we introduce ReactWorld, an embodied video generation model guided by structured interaction anticipation. In the generation backbone's feature space, an interaction response field predictor anticipates how the interaction will unfold, explicitly describing participant roles, future motion response intensity, and local motion changes. A response feedback adapter forms increments to object features from the difference between the object branch's outputs with predicted and zeroed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories. On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.

cs.CV · cs.RO

新论文 · v1arXiv:2611.25909

The Linguistic Structure of Dependency-Conditioned Embeddings

Bach Phan-Tat, Tung Kieu, Kris Heylen, Dirk Geeraerts, Stefano De Pascale, Dirk Speelman

原文摘要

Dependency-based distributional models capture syntactically informed lexical similarities, but the geometric organisation of dependency-conditioned lexical representations remains underexplored. We investigate the global and local geometry of lemma-dependency relation embeddings using four representations trained on WikiText-103: two count-based PPMI configurations and two Skip-Gram with Negative Sampling (SGNS) configurations. At the global level, we analyse dependency-relation centroids, control for lexical identity through within-lemma centring, and examine their alignment with part-of-speech (POS) distributions. At the local level, we evaluate cross-relation geometric consistency, cross-method agreement, lexical similarity, and polysemous usages. Results show that global geometry is structured strongly by context POS across all representations. Locally, broader lexical similarity structures are partially preserved across dependency relations, while immediate neighbourhoods vary substantially, highlighting different usages. PPMI-based representations exhibit greater cross-relation consistency than SGNS-based representations, with cross-method agreement varying by relation. These findings reveal systematic linguistic organisation at multiple geometric scales and its sensitivity to representation choices.

cs.CL