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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 15:38 — 2026-11-16 15:38(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,921 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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.13814

Swanada: Split-Encoder Capability-Routed Conformer CTC and Sub-30 MB On-Device Speech Recognition Across Twelve Scripts

Hemanth HM

原文摘要

Client-side automatic speech recognition (ASR) across Indic and Classical scripts eliminates cloud transcription costs, network tail latency, and server-side audio retention, yet neural exports face four systems bottlenecks in browsers and mobile runtimes: (1) monolithic per-language Conformer checkpoints require ~177 MiB per script (> 2.1 GiB across 12 scripts), exhausting CacheStorage quotas; (2) static relative positional encoding tables embed 10.2-20.5 MB of FP32 constants while 1x1 Conv1d layers trigger slow or unsupported ConvInteger kernels in WebAssembly SIMD; (3) sliding-window CTC flickers on boundary tokens; and (4) mobile WebAudio pipelines suffer 44.1/48 kHz sample-rate mismatches and silent AudioWorklet stalls under iOS WKWebView. We present Swanada, an open-source 16 kHz streaming ASR system spanning Classical Sanskrit, Indian English, and ten Indian languages (sa, en, hi, kn, mr, bn, ta, te, ml, gu, pa, or) across browser WebAssembly, Node.js, and Python. Swanada pairs capability-routed shared INT8 Conformer encoders (a 17-layer 177.38 MiB Studio tier at $d = 512$ for desktop/servers and a distilled 14-layer 25.35 MiB Mobile tier at $d = 256$ for phones) with twelve hot-swappable 515.0 KiB native-script linear CTC heads ($257 \times 512$), cutting 12-language storage by $11.6\times$ (183.4 MiB) and $67.8\times$ (31.39 MiB; 25.85 MiB first load). Runtime protobuf tail surgery exposes the shared representation in $< 2$ ms, while dynamic positional synthesis, MatMul pointwise convolutions, and post-quantization QInt8 head calibration preserve sub-30 MB accuracy. Across $N = 480$ held-out and $N = 1,280$ open public test clips (FLEURS, LibriSpeech, GLOBE, AMI, wild Sanskrit), Swanada achieves 5.43% held-out and 8.87% 12-language open CER on Studio (18.56% and 19.23% on Mobile) at $0.0097\times$-$0.0264\times$ RTF, with 30.6 ms median TTFT and 0.00% committed-prefix churn.

cs.SD · cs.AI

新论文 · v1arXiv:2611.13813

Optimal radio labelings for the Cartesian product of a path and the Heawood graph

Payal Vasoya, Miral Doshi, Devsi Bantva

原文摘要

For a simple graph $G$, let $d(u,v)$ denote the distance between two vertices $u$ and $v$ in $G$, and let $diam(G)$ denote the diameter of $G$. A radio labeling of $G$ is a mapping $f : V(G) \rightarrow \mathbb{N} \cup \{0\}$ such that $|f(u)-f(v)|\geq diam(G) + 1 - d(u,v)$ holds for every pair of distinct vertices $u, v \in G$. The span of $f$ is the difference between the largest and smallest integers assigned by $f$, and the radio number $rn(G)$ is the minimum span taking over all radio labelings of $G$. Let $P_n$ denote the path on $n$ vertices and let $H$ denote the Heawood graph (see Figure-1). In this paper we determine the radio number for the Cartesian product of a path and the Heawood graph, and characterize all optimal radio labelings of $P_n \Box H$. Moreover, we show that the radio number of $P_n \Box H$ exceed the lower bound given for $rn(G)$ in [6], where $G$ is any graph, and that this gap is arbitrarily large.

math.CO · cs.DM

新论文 · v1arXiv:2611.13811

Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech

Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas

原文摘要

Antalia-2 Mini is a single-voice Turkish text-to-speech model with 7,620,931 parameters. It reads characters and produces 48 kHz audio at 41 times real time on an Apple M5 laptop CPU (2 threads). Its training audio came only from VoxCPM2 (the teacher), about 300 times larger, cloning one synthetic clip; automatic checks kept about 1,790 h. Fine-tuning the vocoder on the acoustic model's own mel spectrograms cut the word error rate (WER) of Whisper's transcripts from a mean of 3.89% to 1.75% at adjacent pre-release checkpoints. The teacher corrupts the start of a clip when the first word begins with ö, the student learned this, and a spoken prefix we cut from the output hides it. On the 495-sentence Freya-TR-Eval benchmark, where we tuned settings, version 1.0.1 has WER 1.09% and character error rate 0.22% on our public harness. A paired bootstrap cannot distinguish these from EMA Lightning, an 8.6M Turkish model, which scores higher on full-band UTMOS, an English-trained quality proxy. No human listening test exists. Weights, inference code and the benchmark harness are public under Apache-2.0; training code and data are not.

cs.CL · cs.SD

新论文 · v1arXiv:2611.13810

Camera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm

Simon Cowling

原文摘要

Real-robot benchmarks of learned visuomotor policies often record room illuminance as the lighting condition. We show that, on a typical low-cost rig, room light and image light can be almost unrelated. Four imitation-learning policies (ACT, SmolVLA, Diffusion Policy and pi0.5) were trained on the same 50 demonstrations of a pick-and-place task on an SO-101 arm. Each was run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera. Both cameras were set to automatic exposure and white balance, which most likely absorbed the difference; exposure was not locked in this experiment. An accidental repeat of one 10-rollout block reproduced its success count (7/10) but matched the first block at only 6 of 10 placements, consistent with chance. We conclude that lux alone does not describe what a policy sees. Camera settings, and image statistics compared with the training recordings, are the quantities to report and control. Data and code are public.

cs.RO

新论文 · v1arXiv:2611.13808

FastWild-GS: Minutes-Scale In-the-Wild Gaussian Splatting via Compact Per-Image Appearance Adaptation

Donghun Ryu, Seokhyun Kim, Minhyeok Lee

原文摘要

Internet photos of a scene differ in exposure, illumination and transient objects such as passers-by, so one set of Gaussian colours cannot explain all photos (the in-the-wild setting). Recent in-the-wild Gaussian Splatting methods mostly report hours of per-scene optimization. We present FastWild-GS, which describes each photo by a 128-dimensional Photo Appearance Token and a per-channel transform, a scale and an offset applied to the rendered image (six parameters); a small MLP predicts the colour of each Gaussian from this token and a per-Gaussian feature, replacing the spherical-harmonics colour. The same transform is applied to the renders that score Gaussians for densification and pruning, so appearance differences between photos are not counted as reconstruction error. On PhotoTourism, FastWild-GS trains in 8.8 minutes per scene with the lowest LPIPS among the compared methods, 23x faster than AsymGS, the next best in LPIPS. On NeRF-OSR, it has the best average PSNR, SSIM and LPIPS among the compared methods in 9.7 minutes per scene.

cs.CV

新论文 · v1arXiv:2611.13807

Relaxing Cross-Modal Correspondence for Multimodal Remote Sensing Pretraining

Xianping Ma, Yu Zhang, Mingzhe Jiang, Wanxin Xie, Qing Zhu, Nan Xu, Xiaokang Zhang, Yuanxin Ye

原文摘要

Multimodal remote sensing pretraining commonly relies on exact instance-level correspondence across modalities, implicitly treating strictly paired observations as a prerequisite for learning transferable representations. In this work, we revisit this assumption by relaxing cross-modal correspondence from the instance level to the semantic level. We introduce Semantic Pairing (SemPair), a pairing-relaxed pretraining strategy that replaces exact instance pairs with class-consistent cross-instance pairs. To characterize the effect of correspondence relaxation, we formulate a latent-factor model that separates cross-modal dependence into shared semantic structure and instance-specific correlation, showing that SemPair preserves the former while marginalizing instance-specific cross-modal correlations in expectation. We further introduce Mixed Pairing (MixPair) as a controlled interpolation between semantic and exact pairing to study correspondence granularity along a continuous spectrum. Extensive experiments consistently show that SemPair achieves transfer performance comparable to exact pairing (ExaPair), while MixPair reveals a non-monotonic relationship between downstream transfer and the instance-pairing ratio. These results demonstrate that exact instance correspondence is not a prerequisite for effective multimodal remote sensing pretraining and establish cross-modal correspondence granularity as an important design dimension for transferable multimodal representation learning. More broadly, this finding suggests a practical route toward scaling multimodal pretraining with reduced dependence on costly instance-aligned data.

cs.CV · cs.AI

新论文 · v1arXiv:2611.13802

Scaling Shapley Energy Attribution to Large LLM Batches

Qi Luo, Ziwen Wang, Kunlin Li, Changxi Liu, Yun Chen

原文摘要

LLM services have become essential infrastructure for applications such as chat assistants and coding agents. Service providers need to attribute resource consumption to individual requests for purposes such as billing. Among these resources, energy is a key metric for assessing the cost of serving each request. However, serving engines batch requests together, and GPUs report only aggregate energy consumption. Providers typically estimate each request's share in proportion to its token consumption, but this approach can produce substantially unfair estimates. The Shapley value provides a principled solution to fair energy allocation, but computing it directly requires $2^N-1$ GPU runs for $N$ requests, which is infeasible for large batches. To address this problem, we propose StepSplit. Across GPU generations, we observe that the energy consumed by each inference step, a forward pass over a batch, consists of a shared energy, largely due to reading model weights, and a request-specific energy. We derive a closed-form Shapley value: each request is charged its own energy plus an equal part of the shared energy of every step in which it participates. A microbenchmark of 2.5-17.8 minutes calibrates both parts of the step energy once per model and GPU configuration. Under static batching, StepSplit uses this closed form in a single pass over the scheduler log. Under continuous batching, removing a request can change how the remaining requests are batched, so StepSplit adds a correction to the closed form, computed by replaying the scheduler on a CPU. We evaluate StepSplit against Shapley values measured using 529,513 GPU runs. Under static batching with batch sizes of 8-256, StepSplit achieves an $L_1$ error of 0.4-4.3%, compared with 13.4-61.3% for token-proportional allocation. Under continuous batching with 8-128 requests, the corresponding errors are 0.5-6.4% and 20.6-71.7%.

cs.DC · cs.AR · cs.PF

新论文 · v1arXiv:2611.13801

Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data

Hang Li, Jiaxin Qi, Yan Cui, Yuhua Zheng, Jianqiang Huang

原文摘要

Motivation: Gene regulatory networks (GRNs) capture the underlying interactions through which transcription factors (TFs) regulate genes. Based on gene expression data, existing GRN inference approaches generally fall into two categories: graph-based methods, which model the GRN as a whole graph, and pairwise-based methods, which decompose the GRN into individual TF-target gene pairs for modeling. However, each approach exhibits limitations that are precisely the strengths of its counterpart. Graph-based methods tend to overfit due to their reliance on a single training graph, whereas pairwise-based methods benefit from abundant TF-target training pairs. In contrast, pairwise-based methods overlook the global topological structure, which is essential for comprehensively capturing regulatory mechanisms. Results: To address these limitations, we propose scGPL, an end-to-end unified framework that jointly models global regulatory topology and local interactions. scGPL extracts macro-level features from the global regulatory graph and introduces a dynamic, importance-guided subgraph sampling mechanism to capture fine-grained local dependencies. By fusing global representations with subgraph-enhanced local features, our framework bridges the gap between the two paradigms, incorporating essential whole-graph topological dependencies while retaining the data abundance advantage of pairwise methods. Extensive experiments on seven benchmark datasets demonstrate that scGPL consistently achieves state-of-the-art performance, with up to 13.7% improvement over the strongest baseline, validating the effectiveness of our integrative design. Availability and implementation: The source code is maintained on GitHub (https://github.com/talent-hang/scGPL), and the datasets and versioned releases are archived at https://doi.org/10.5281/zenodo.21608485 for reproducibility.

q-bio.GN · cs.AI

版本更新 · v2arXiv:2602.20921

On Compatible Generalization Bounds of Deep Residual Networks From a Dynamical System Perspective

Jinshu Huang, Mingfei Sun, Chunlin Wu

原文摘要

Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes. Deep residual networks (ResNets) fall into one of the most important classes of DNNs. In this paper, we study the compatible generalization behavior of deep residual networks with a broad class of activation functions in the deep-layer limit, from a dynamical system perspective. We first show a refined contraction inequality for Rademacher complexity of function classes composed by that type of activation functions. We then conduct an equivalence analysis of component hypothesis sets in Rademacher complexity and forward convergence analysis of network state variables, which enable us to establish compatible uniform generalization bounds that simultaneously achieve the optimal \(O(1/\sqrt{S})\) sample rate for both discrete- and continuous-time ResNets. The bounds also share a common layer-number independent leading term and non-positive refinement terms that capture the decomposition structure of the activation function, revealing a consistent generalization behavior in the deep-layer limit. Compared to previous works considering both discrete- and continuous-time ResNets simultaneously, our theoretical results not only have better sample rate, but also are established under weaker assumptions on the learnable parameters. We also support our theoretical findings with numerical experiments.

cs.LG

版本更新 · v2arXiv:2611.07948

Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency

Shuyi Miao, Zheng Li, Xu Xie, Linrui Xu, Fei Shen, Xiaoyu Du, Tat-Seng Chua

原文摘要

As large language models (LLMs) are increasingly deployed in real-world applications, evaluating the correctness of their responses is crucial for reliable use. However, such evaluation is challenging because reference answers are rarely available in practice. Existing reference-free methods mainly rely on output signals, which may assign high scores to incorrect responses and thus do not necessarily reflect correctness. This motivates exploring the model's internal computation for complementary correctness signals. Recent studies exploit internal states, but they mainly analyze hidden-state trajectories across layers, which record only the combined updates of attention and feed-forward networks (FFNs) and overlook how these components interact. We therefore propose Circe, a training-free self-evaluation method that assesses a response using both internal and external signals, without reference answers or repeated sampling. For internal signals, we first introduce component interaction consistency (CIC), which measures the directional alignment between attention updates in earlier layers and attention-induced FFN output changes in later layers. We further incorporate representation geometry (RG) to characterize normalized displacement and angular changes along layerwise hidden-state trajectories. For the external signal, we convert the mean negative log-likelihood of generated tokens into a bounded likelihood confidence (LC) score. Finally, we fuse CIC, RG, and LC into a unified correctness score. Experiments on five LLMs and six benchmarks across four domains show that our method distinguishes correct from incorrect responses more effectively than existing baselines, and generalizes to multilingual, multimodal, and open-world settings.

cs.AI

新论文 · v1arXiv:2611.13797

Auditing LLM Pseudo-Label Distillation for Review Informativeness at E-Commerce Scale

M. Emin Dogan, Cansu Er, Aysenur Kulunk, M. Furkan Eseoglu, H. Bahadir Sahin

原文摘要

We study hard-label distillation from Gemini 3.1 Flash-Lite to compact encoders on 5.34 million Turkish marketplace reviews. A strict new-SKU temporal test measures teacher fidelity; a separate, teacher-label-blind audit by one company annotator measures editorial agreement. An H3 category prefix slightly improves teacher fidelity on the full new-SKU test. On the 16,000-review chronological audit subset, it instead reduces agreement with both Gemini and the annotator, with a clearer paired difference for CORN than for cross entropy. Thus the context effect depends on the evaluation population, and teacher fidelity alone does not establish editorial alignment. Under the measured offline configurations, a single-L4 student pipeline processes reviews 50.2 times faster than the teacher pipeline.

cs.IR

新论文 · v1arXiv:2611.13794

AnchorMTS: Multi-View Signal Representation and Forecast-Anchored Fusion for Long-Term Time-Series Forecasting

Gao Wu, Tingting Xu, Changning Wu, Tengfei Long, Yong Liu, Jiabin Jin, Kexin Zhang

原文摘要

Long-term time-series forecasters typically optimize a single numerical representation, even though the same history exposes complementary geometry, recurrence, and semantic structure. We propose AnchorMTS, which derives self-aligned visual and textual views from each observed window and uses them only to refine a complete numerical forecast. A trainable evidence path produces a candidate forecast, while a parameter-free output projection enforces an exact per-variable bound on its displacement from the numerical anchor. Across six benchmarks and four horizons, AnchorMTS achieves the best macro MSE/MAE (0.336/0.367) among seven supervised baselines and wins 18 of 24 MSE settings against the cellwise baseline envelope; removing the auxiliary path raises macro MSE to 0.340. The projection leaves 95.8% of candidate refinements unchanged while yielding zero bound violations, showing that complementary multi-view evidence can improve forecasting while its final influence remains explicitly controlled.

cs.LG

版本更新 · v2arXiv:2611.09964

How Many Demonstrations Does a VLA Need? On the Sample Efficiency of VLA Finetuning

Rahul Chand, Miguel Villa Floran

原文摘要

Pretrained vision language action (VLA) models show strong zero-shot performance but they are rarely deployed directly and are often first post-trained on demonstrations from the target setting. Yet VLAs are typically compared by zero-shot or full-data fine-tuned success which reveals little about the data and compute required for downstream adaptation. We study adaptation efficiency for six VLAs ($π_0$, $π_{0.5}$, and GR00T N1-N1.7) on four LIBERO suites, varying both demonstrations and training steps. This reveals differences hidden by full-data fine-tuning: models which are within two points on the full LIBERO-Spatial dataset differ by up to 3$\times$ in success with 50 demonstrations. $π_{0.5}$ needs 2-5$\times$ fewer demonstrations than $π_0$ and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite. Within GR00T, N1.5 adapts more efficiently than N1.6 and N1.7 on three of four suites, despite their stronger zero-shot performance. We also study one pretraining factor behind these differences by freezing the VLM during finetuning: this severely degrades the $π$ models whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models.

cs.CV · cs.RO

新论文 · v1arXiv:2611.13790

RiSE-Drive: Risk-Sensitive Long-Horizon Candidate Evaluation for End-to-End Autonomous Driving

Yu Zhao, Hongyi Duan, Ming Yin, Hongyuan Zhang, Fan Yang, Hongzhi Wang, Xiubo Liang

原文摘要

End-to-end autonomous driving systems increasingly rely on generating multiple trajectory candidates and selecting one for execution. In this setting, a central challenge is no longer only candidate generation, but how to evaluate candidates according to their long-horizon consequences under uncertainty. Existing methods still mainly use deterministic point scores, heuristic subscores, or single-outcome evaluations, which makes it difficult to capture delayed failures, tail risk, and ranking instability under plausible future perturbations. We present RiSE-Drive, a framework for risk-sensitive long-horizon candidate evaluation in end-to-end autonomous driving. RiSE-Drive first performs candidate-conditioned latent future rollout, then estimates long-horizon outcome distributions instead of single scalar scores, and finally ranks candidates using a tail-risk-aware and perturbation-robust decision criterion. This reformulates candidate scoring from deterministic oracle-style evaluation into distributional outcome assessment with explicit risk control. As a result, the evaluator is encouraged to prefer candidates that are not only strong under nominal conditions, but also reliable under long-horizon rollout and safety-critical deviations. Experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks, as well as the closed-loop HUGSIM benchmark, show that RiSE-Drive achieves state-of-the-art performance and significantly improves the robustness of candidate selection.

cs.RO

新论文 · v1arXiv:2611.13787

Local Modifications of Nearest-Neighbor and Min-Plus Representations

Liliia Redina

原文摘要

We study how changing a Boolean-valued function at $d$ inputs affects the size and precision of its exact representations. Starting from a representation of size $m$, we prove four bounds, two for nearest-neighbor (NN) representations and two for integer min-plus representations. (i) For NN representations on a finite subset of $\mathbb{R}^n$ with $n\ge2$, at most $m+2d$ anchors suffice. The coefficient $2$ is optimal: on a three-point domain, changing one value can increase the minimum number of anchors from one to three. (ii) For NN representations on the Boolean cube with rational anchors, let $R$ be the maximum original coordinate bit length, and let $Δ$ be the maximum bit length of the least common denominator of any one original anchor's coordinates. We construct a representation with at most $m+3d$ anchors on a common dyadic grid and coordinate bit length $O(R+Δ+\log(n+1))$. (iii) For integer min-plus representations on the Boolean cube, we give a construction that keeps the original $m$ forms and their labels and adds at most $d$ new forms. Its maximum weight is at most $W+2n$, where $W$ is the largest absolute original coefficient, including constant terms. (iv) For integer min-plus representations on a finite rational domain $X\subset\mathbb{Q}^n$, at most $m+2d$ forms suffice. Their maximum weight is polynomially bounded in $m,d,W,n,|X|$, the coordinate bound, and the common denominator of $X$. The coefficient $2$ is again optimal: on a three-point domain, changing one value can increase the minimum number of forms from one to three. These bounds imply stability under polynomially many changes on the cube for polynomial-size representations, including those with polynomially bounded NN coordinate bit length or min-plus weight.

cs.CC · cs.DM

新论文 · v1arXiv:2611.13785

The Target Is a Predicate: Predicate-State Grounding for Semantic-Level Video Reasoning Segmentation

Yuhuan Hong, Yiming Ren, Zhiqiang Lin, Feize Wu, Xingyun Liu, Yitong Xie, Lei Zhou, Lisheng Wu 等 10 位作者

原文摘要

In this paper, we introduce Predicate-State Video Reasoning Segmentation (PS-VRS), where a query defines a dynamic predicate $P(o,t)$ over objects and time rather than a fixed object identity. Existing methods typically treat the target as permanently active once identified, leading to over-emission of masks during vacant intervals and failure to handle target switching. To address this, we construct PS-Bench, a large-scale benchmark with 2,077 videos and 16,250 queries annotated with explicit active/vacant predicate states, temporal intervals, and pixel masks. We further propose Predicate-State Grounding (PSG), a State-Bind-Emit pipeline that: (1) predicts [ACTIVE]/[VACANT] state tokens; (2) aligns them to video frames via dense cross-modal similarity; and (3) emits masks via SAM2 only for active states. Experiments show that PSG outperforms existing baselines by +9.32 J&F on PS-Bench and significantly reduces false-positive mask emissions. Our results demonstrate the effectiveness of explicit predicate-state modeling for video reasoning segmentation with dynamic visual witnesses.

cs.CV

新论文 · v1arXiv:2611.13784

Marrying Capacity and Precision for Efficient 2D Gaussian Image Representation

Lin Dong, Qi Ming, Liuqian Wang, Wentao Chao, Yufei Gao, Chengming Liu, Lei Shi

原文摘要

2D Gaussian representations provide an explicit and efficient way to represent images, but their rate-distortion performance under limited budgets depends critically on how Gaussian capacity and parameter precision are allocated. Existing methods typically optimize these two resources separately, overlooking content-dependent capacity demands and heterogeneous quantization sensitivity. We present CP-GS, a capacity-precision coupled Gaussian splatting framework for budget-aware 2D Gaussian image representation that jointly optimizes capacity allocation and attribute precision under a shared rate constraint. CP-GS first constructs a content-adaptive Gaussian representation by dynamically reallocating a fixed Gaussian budget from redundant regions to areas with higher representation demand. It then introduces hierarchical distortion-aware representation quantization, using efficient rendering-based calibration to allocate precision across Gaussian attributes and further refine it within heterogeneous attribute groups. Finally, it jointly optimizes Gaussian capacity and attribute precision by constructing candidate representations with different Gaussian counts and precision configurations and selecting operating points according to decoded distortion and actual serialized size. Experiments on DIV2K and Kodak show that CP-GS achieves improved rate-distortion performance over representative 2D Gaussian and implicit neural representations across a range of budgets, while maintaining a fixed overall representation budget and low optimization cost. These results demonstrate the benefit of jointly optimizing spatial capacity and parameter precision for compact Gaussian image representation.

cs.CV

新论文 · v1arXiv:2611.13782

Integrating Action Prefix Prediction and Alignment Across Modalities for Multimodal Reinforcement Learning

Sijie Xu, Francisco Cruz

原文摘要

Learning representations from multimodal observations is difficult in reinforcement learning with limited interaction data. Multimodal Joint Predictive Representation combines multimodal latent prediction with contrastive learning across modalities, but its recursive rollout depends on earlier predictions and its pairwise alignment focuses on correspondence between modalities. We propose Improved Predictive Representation, which combines prediction from action prefixes with alignment at the observed anchor based on Contrastive Multimodal learning. At each horizon, it predicts future representations directly from the observed anchor and the corresponding sequence of actions. We evaluate two crop configurations: IPR-S with a minimum retained crop area of 10%, and IPR-H with 50%. Across five DeepMind Control Suite tasks, IPR-H achieves an average return across tasks that is 10.0% higher than the baseline with visual and depth images and 3.4% higher with visual images and position vectors. The relative performance of the two configurations varies across tasks. In Webots, both IPR configurations achieve higher mean final returns than the baseline without LiDAR, but not when LiDAR is available.

cs.AI

版本更新 · v2arXiv:2611.10035

Ninada: Sub-Clause Split-Graph VITS Streaming and Capability-Routed 24 kHz Speech Synthesis Across Twelve Scripts

Hemanth HM

原文摘要

End-to-end VITS text-to-speech models synthesize natural speech in a single forward pass, yet standard ONNX exports execute monolithically over an entire clause, delaying Time-To-First-Audio (TTFA) to several seconds and spiking activation memory. Client-side deployment across Indic scripts faces four further bottlenecks: 138.8 MB float32 checkpoints per language strain browser caches, mobile WebGPU stalls for 6-14 s compiling convolution shaders while still running slower than real time ($1.44\times$ RTF), small WebAssembly pthread pools stall at barriers on big-LITTLE mobile CPUs, and mobile Web Audio pipelines drop frames or mute output under AudioWorklet contention and iOS WKWebView rules. We present Ninada, an open-source 24 kHz TTS system covering English, Classical Sanskrit, and ten Indian languages (sa, en, hi, kn, mr, bn, ta, te, ml, gu, pa, or) across a capability-routed 48-checkpoint fleet: 24 studio HiFi-GAN v1 specialists (27.9 MB W8A32+FP16 ONNX) for desktop/WebGPU and 24 distilled c8c8_384 iSTFTNet specialists (21.7 MB ONNX, $2.64\times$ fewer vocoder MACs via an exact NOLA dual-window ConvTranspose1d inverse STFT with zero complex ops) for mobile WASM, plus a 0.0 MB zero-dependency Klatt fallback. At runtime, Ninada splits a single ONNX file in memory in $< 15$ ms into prior, flow, and windowed vocoder sub-sessions streaming 12-frame halos with raised-cosine crossfades. On $N = 480$ held-out 24 kHz studio utterances, Ninada achieves 3.22 dB 0-8 kHz MCD (3.09 dB mobile iSTFTNet; 1.33 dB 24-voice distillation MCD, vs. 5.17 dB for the 1,526.8 MB 16 kHz Meta MMS fleet) and 6.07 dB 8-12 kHz error, delivering 89-155 ms audible startup on desktop WebGPU and 538-649 ms zero-underrun streaming at 0.75-0.76x RTF on a physical Google Pixel 10 Pro XL.

cs.SE · cs.SD

新论文 · v1arXiv:2611.13779

Softness is something you also need! Why compliance helps control: information metrics of a passive walker with compliant ankle

Fabio Bonsignorio, Elisabetta Barletta, Sorin Dragomir, Francesco Esposito, Enrica Zereik

原文摘要

A great gap in adaptivity, flexibility, and dexterity still exists between intelligent robots, whether they are made of rigid or (partially) compliant components, and their naturally evolved animal and vegetal counterparts. One reason could be of `paradigm' nature. On the one hand, most robots (both rigid and soft) are still designed by following a `Cartesian' approach, with top-down control and a clear mind-body separation. Designing artificial agents on the basis of the principles that we observe in biology is not an easy task. The principles of organization of animals and plants rely on morphological computation and emergence of fit behaviors from loosely coupled networks of embodied agents. Modeling and control require radically new approaches. In this paper we briefly recall and explain some seminal mathematical results linking information metrics and dynamics of the agents, already published years ago; we integrate them with some recent methods developed by us and by the community, we highlight some brief remarks about their relevance and we hint to our current and near future work towards finding concrete and efficient ways for the modeling and control of completely or partially compliant artificial agents and for a better understanding of physical intelligence in nature. We present a technical note summarizing phase-space volume calculations for inverted-pendulum and passive-dynamic walking models, following our proposed framework. Starting from the McGeer compass gait, we introduce knee-ankle compliance, foot-rocker effects, and a Ruina-style compass gait with distributed leg inertia. Standard heel-strike maps are derived and used in the estimation of viable phase-space volumes $W(γ)$, based on a state-dependent Monte-Carlo and Reproducing Kernel Hilbert Spaces methods. We show how the methods based on RKHS allow deeper and more subtle analysis.

cs.RO · cs.AI

新论文 · v1arXiv:2611.13778

Polynomial Quantum Recurrent Channels for Matrix Inverse Actions: Deferred-Reset Dynamics and Chebyshev Filtering

Vahid Tavakkoli, Kabeh Mohsenzadegan, Kyandoghere Kyamakya

原文摘要

We develop completely positive, trace-preserving polynomial recurrent channels for quantum solution-state preparation and derive fixed-point and time-varying tracking bounds. Across 2,880 synthetic configurations, resident Chebyshev recurrence improves accuracy-passing snapshot counts in 608 cases, ties in 2,271, and loses in one. A separate 360-scenario cost study shows that fresh recurrence is cheaper in all 184 jointly feasible scenarios (median resident-to-fresh cost ratio: 3.12), while resident recurrence uniquely satisfies accuracy requirements in 74 cases. At a logical noise rate of $10^-4$, neither recurrent method qualifies. Based on exact reduced-density simulations and assumed cost models, our results demonstrate conditional tracking advantages but no general end-to-end speedup or total-cost benefit.

quant-ph · cs.ET

新论文 · v1arXiv:2611.13776

DisasterAgent: An Evidence-Driven Agent for Verifiable Disaster Report Generation From Remote Sensing Imagery

Zhijian Li, Jiawei Song, Chao Ren, Yidan Zhang, Peijin Wang, Xian Sun, Kun Fu

原文摘要

Remote sensing disaster assessment is moving from simple damage classification toward comprehensive report-level analysis. In this setting, responders need not only damage descriptions but also verifiable evidence to guide response and recovery. Recent vision-language models (VLMs) and tool-augmented agents offer strong multimodal reasoning and perception, but they struggle to provide the evidence required for high-stakes verification. To address these limitations, we propose DisasterAgent, an evidence-driven agent that uses a Perception-Augmentation-Generation workflow to generate verifiable disaster reports from bitemporal optical imagery. DisasterAgent first invokes a specialized vision expert toolkit in the perception phase to build a Spatiotemporal Perception Graph (STPG), serving as a structured memory to store and organize disaster-induced changes across space and time. Evidence-based Augmentation (EA) then extracts evidence from the STPG, attaching inline citations that form a closed evidence loop from each statement to the supporting visual evidence. Extensive experiments on the DisasterM3 and RSCC benchmarks demonstrate that DisasterAgent consistently outperforms general-domain VLMs, remote sensing-specialized models, and existing remote sensing agents. Notably, compared with the original model, it improves the average score for disaster report generation on DisasterM3 by 13.5\% and ST5-SCS on RSCC by 15.34\%, providing a more accurate and verifiable solution for disaster emergency response. The code will be available at https://github.com/ZhijianLi2003/DisasterAgent.

cs.CV · cs.AI

版本更新 · v3arXiv:2611.06817

Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models

Juncheng Ma, Jiaxin Li, Jiankai Tu, Bo Liang, Guodong Lv, Yufan Deng, Junzhe Tang, Liangzhu Yang 等 35 位作者

原文摘要

Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and training recipes. We introduce Open-HumanWAM, the first fully open recipe for scaling egocentric pretraining to 50,000 hours, anchored by Open-HumanWAM-50K---a curated egocentric video corpus densely annotated with hand motion and natural language. Leveraging this corpus, we systematically investigate pure human pretraining via closed-loop simulation evaluations and uncover an empirical log-linear scaling law linking pretraining data hours to downstream robot success rates. Grounded in these findings, we develop HumanWAM-Vanilla, a world--action model pretrained exclusively on 50k hours of egocentric human video. Upon robot post-training, HumanWAM-Vanilla reaches 92.08% success on RoboTwin 2.0 Clean2Clean and 68.88% on Clean2Random, alongside a 14.17% mean success rate and a 19.00 mean progress score on RoboDojo. To push the capability frontier further, we explore joint human--robot pretraining with HumanWAM-Goal, a visual-goal-conditioned world--action model. Hybrid data scaling unlocks broad zero-shot generalization across both simulation and physical benchmarks, propelling post-trained RoboTwin 2.0 performance to new state-of-the-art levels: 92.70% on Clean2Clean and a substantial leap to 84.60% on Clean2Random. On physical robots, HumanWAM-Goal further exhibits emergent embodied in-context learning, dynamically adapting its manipulation behavior to unseen visual goals without parameter updates. To support reproducible scaling research in embodied AI, we open-source the Open-HumanWAM-50K corpus, data curation and pretraining pipelines, alongside the pretrained and post-trained HumanWAM checkpoints, inference code, and simulation evaluation suites.

cs.CV · cs.RO

新论文 · v1arXiv:2611.13774

AI-Adaptive Virtual Reality for STEM: Engagement, Retention, and Learning Outcomes

Srinivasa K G, Akshit Rana, Aman Singh, Kshitij Kumar Singh Chauhan

原文摘要

Virtual Reality (VR) presents a com pelling opportunity to transform STEM pedagogy; however, empirical evidence evaluating AI-driven adaptivity, objective engagement metrics, and long-term knowledge retention remains sparse. This paper proposes and evaluates an AI-adaptive VR based solar system learning module deployed on Meta Quest 2, wherein a machine learning model dynamically adjusts in structional difficulty based on real-time learner interaction logs including dwell time, gaze patterns, and response latency. A controlled between-subjects experiment was conducted involving 120 secondary school students (mean age 14.3 years) across three schools in India, randomly assigned to three conditions: AI adaptive VR, standard VR, and traditional classroom instruction. Engagement was measured objectively through eye-tracking fixation density and heart rate variability (HRV), alongside pre-test, immediate post-test, and delayed post-tests at one week and one month intervals. Statistical analyses encompassing paired t-tests, one-way ANOVA, and Structural Equation Modeling (SEM) reveal that the AI-adaptive VR cohort demonstrated significantly higher knowledge improvement scores (mean gain = 38.4 vs. 31.2 vs. 10.7), superior one-month retention (p < 0.001), and measurably elevated engagement across all biometric indicators. SEM confirmed immersion as a significant mediator between adaptive instruction and knowledge acquisition (\b{eta} = 0.63, p < 0.001). Post-session self-directed learning exploration was recorded at 80% among AI-adaptive VR participants versus 40% in the traditional group. These findings establish an evidence based framework for deploying AI-adaptive immersive learning environments in resource-varied STEM educational contexts.

cs.ET

版本更新 · v2arXiv:2611.11996

OASIS: Optimization-Aware Subgoal Inference with Safety Constraints for Autonomous Mobile Robot Navigation

Arian Hajizadeh, Javad Pourrafi Arabani, Negar Shenavar, Sana Bashiri, Seyed Majid Esmailzadeh

原文摘要

Navigation in dynamic environments requires mobile robots to make progress toward their goals while respecting motion limits and avoiding surrounding obstacles. Learned subgoal policies can guide model predictive control beyond its local prediction horizon, but a geometrically suitable subgoal does not necessarily lead to a successfully solved control problem. This paper proposes OASIS, a hierarchical navigation framework that incorporates recent optimization outcomes into reinforcement learning-based subgoal generation. A high-level policy trained using Soft Actor--Critic generates local subgoals, while a nonlinear model predictive controller tracks them subject to motion limits, geometric collision-avoidance constraints, and embedded high-order control barrier function constraints. The outcomes of controller optimizations over each subgoal interval are summarized and provided to the policy at its next decision, without requiring additional optimization calls. The framework is evaluated in five navigation scenarios with static and moving obstacles, including dense interactions and sensing uncertainty. Comparisons with hierarchical and direct-goal control variants show that OASIS achieves the highest aggregate navigation success. Matched comparisons across three training seeds further show a consistent success advantage over the otherwise identical hierarchy without optimization-status input. The selected-policy comparison also shows fewer primary optimization failures with similar mean controller time.

cs.RO

版本更新 · v2arXiv:2610.29164

XingChen-UniFE: A Unified Generative Speech Front-End via Complementary Acoustic-Semantic Modeling

Kelan Kuang, Qihan Hu, Jian Kang, Jie Li, Yongxiang Li, Yi Liu

原文摘要

This paper presents XingChen-UniFE, a unified large audio language model (LALM) for general speech restoration (GSR) and target speaker extraction (TSE). The proposed model employs complementary semantic and acoustic representations through a dual-stream encoder, where a self-supervised learning model provides hierarchical semantic features and a learnable acoustic branch captures fine-grained structures from complex spectra. A bidirectional cross-attention module further facilitates information exchange between the two representations. The fused representation conditions the LALM for discrete speech token generation with task and speaker information. Experiments demonstrate strong performance on both GSR and TSE and robust generalization to unseen degradation conditions.

eess.AS · cs.SD

新论文 · v1arXiv:2611.13769

From Depth to Safe Depth: Uncertainty-Aware Monocular Perception for Mobile Robot Navigation

Saeid Firouzi Daghigh, Saeed Ayat

原文摘要

Monocular depth foundation models make it tempting to replace depth sensors on mobile robots with a single RGB camera. We show that, used off the shelf, this is unsafe: in a simulated indoor navigation benchmark, a standard Nav2 stack driven by Depth Anything V2 (metric) collides in 63\% of 120 episodes, because the model systematically over-estimates the distance to nearby obstacles. We propose a lightweight plug-in module that turns predicted depth into \emph{safe depth}. A 0.58\,M-parameter head on top of the \emph{frozen} depth model predicts, per pixel, a log-depth correction $μ$ and an uncertainty $σ$, trained with a $β$-weighted Gaussian negative log-likelihood. The navigation stack consumes the one-sided bound $\hat d_{\text{safe}}=d\,e^{μ-kσ}$, where $k$ is set by conformal calibration on a held-out world, and uncertainty also decides which pixels may be treated as floor. The correction halves the depth error (AbsRel $0.262\rightarrow0.134$) and reduces near-range over-estimation from 59.8\% to 12.0\%. In navigation, safe depth raises the success rate from 37\% to 70\% and lowers collisions from 63\% to 3\%, close to the 2\% of ground-truth depth. A constant safety margin calibrated to the same pixel coverage reaches only 30\% success because it freezes the robot; uncertainty-aware safety wins 52 of 56 discordant paired episodes against it. Gains hold on glass, texture-less walls and dark regions.

cs.RO · cs.CV

新论文 · v1arXiv:2611.13768

Unified Far-field and Near-field Codebook Design for XL-array Systems

Chao Zhou, Changsheng You, Liujia Yao

原文摘要

While extremely large-scale antenna arrays (XL-arrays) hold immense promise for next-generation wireless networks, the paradigm shift encompassing new near-field communications renders conventional discrete Fourier transform (DFT)-based Type-I codebooks inefficient. Meanwhile, existing near-field alternatives usually impose prohibitively high storage and/or feedback burdens. To tackle these challenges, we propose in this letter a unified codebook applicable to both far-field and near-field XL-array systems. Our key idea is to express the near-field channel steering vector in an equivalent form, which is a Hadamard product of an angular vector and a curvature-related vector. This new representation allows direct reuse of the legacy Type-I codebook for angle quantization, while only a lightweight auxiliary codebook is newly added for additional curvature quantization. Subsequently, we optimize the auxiliary curvature codebook by maximizing the average beamforming gain given the information of user distribution. By leveraging the local monotonicity of the beamforming gain with respect to curvature mismatch, the optimization problem is further reduced to a quantization-error minimization problem, for which suboptimal curvature codewords are obtained. Numerical results demonstrate that the proposed unified codebook achieves near-optimal beamforming performance that approaches its upper bound based on perfect channel state information (CSI), while significantly reducing the required feedback overhead as compared to various benchmark schemes.

cs.IT

新论文 · v1arXiv:2611.13766

FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control

Santosh Mohan Rajkumar, Debdipta Goswami, Stephanie Stockar

原文摘要

We present FAME-QP, a GPU-accelerated solver for dense quadratic programs arising in linear model predictive control. FAME-QP combines constraint-dependent operator representations with fused single- and two-kernel iterations replayed through CUDA graphs, automatically selecting the execution configuration through device calibration and problem-specific timing. It probes a cached operator bank to select the initial penalty and updates operators lazily when problem matrices change. Numerical benchmarks and simulated humanoid and quadrotor control experiments demonstrate reduced latency relative to competing GPU solvers while maintaining solution accuracy and control performance.

cs.RO · cs.GR · eess.SY

版本更新 · v2arXiv:2610.24395

MSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information

Xinyu Chen, Liangjian Wen, Jiang Duan, Dongkai Wang, Yong Dai, Jiayu Bai, Jianzhuang Liu, Zhen Tian 等 10 位作者

原文摘要

In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-oriented methods such as the Multimodal Competition Regularizer (MCR) perform well by alleviating this imbalance during training. These dynamic balancing methods, however, mainly adjust modality contributions and do not consider how imbalance affects the formation of synergistic information during fusion. Synergy is a major source of multimodal advantage, because it is predictive gain that cannot be recovered from unimodal evidence alone. We propose the Multimodal Synergistic Competition Regularizer (MSCR), a fusion method that jointly promotes balanced modality utilization and the discovery of synergistic information. MSCR has two complementary objectives. An anti-dominance objective suppresses excessive unimodal influence and leaves room for synergistic information, and a synergy objective encourages the fused predictor to outperform a non-synergistic unimodal reference. An adaptive gate further concentrates the regularization on samples that need stronger collaborative modeling. Experiments on five benchmarks show that MSCR consistently improves performance over MCR and strengthens synergistic capability. It raises conditional recovery, the accuracy of the fused prediction on samples that the unimodal predictors misclassify, as well as the share of the model's output that InterSHAP attributes to cross-modal interactions. Its gain in conditional recovery persists when the fusion module is Transformer-based. Code is available at https://github.com/chenxinyu991-collab/MSCR.

cs.AI · cs.CV · cs.LG