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

+0新增论文
+0其中 AI 相关
+0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：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 07:52 — 2026-11-16 07:52（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：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 23,348 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:2611.15280

Autonomous Trail Racing with a Bicycle Robot

Fabian Jenelten, Deepana Ishtaweera, Pablo Garcia, Liana Margolese, Igor Bogoslavskyi, Luca Buonocore, Jan Migliazza, Aleksandrs Ecins 等 13 位作者

原文摘要

Navigating off-road trails on a mountain bike requires diverse locomotion skills, including aerial maneuvers, cornering, and slip recovery, paired with sophisticated perception for scene understanding. Translating these capabilities to autonomous, two-wheeled robots remains a formidable challenge. We show that autonomous, high-speed trail navigation can be achieved through a single idea: encoding the trail as a semantic layer of the terrain. In simulation, this layer embeds the navigation task into the training environment; during deployment, it is reconstructed onboard from camera and LiDAR data. First, we introduce a unified learning framework that treats local navigation and locomotion as a joint optimization problem, bypassing the twist or pose command interface of classical control hierarchies. With fixed reward weights, the same framework produces both trail racing and agile parkour, shaped only through terrain semantics and episode length. Second, our perception pipeline combines a frozen vision foundation model with a lightweight dual-head decoder that predicts per-pixel terrain semantics and confidence scores, which are fused with LiDAR range measurements into an egocentric semantic elevation map at 30 Hz onboard an NVIDIA AGX Orin. We validate our framework on the Ultra Mobility Vehicle (UMV), a bicycle robot that autonomously raced across all sections of a kilometer-long, unstructured mountain bike trail at speeds exceeding 5 m/s and averaging 3.26 m/s. In simulation, our policy fails up to an order of magnitude less often than hierarchical baselines while driving faster.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.20454

Capturing Intransitive Dominance in Tennis Forecasting: A Graph Neural Network Approach

Lawrence Clegg, John Cartlidge

原文摘要

Intransitive player dominance, where player A beats B, B beats C, but C beats A, is common in competitive tennis. Yet, there are few known attempts to incorporate it within forecasting methods. We address this problem with a graph neural network approach that explicitly models these intransitive relationships through temporal directed graphs, with players as nodes and their historical match outcomes as directed edges. Our model (65.7% accuracy, 0.214 Brier score) forecasts competitively with established rating systems such as Weighted Elo. Although it does not improve on the baseline in unconditional accuracy, a forecast-encompassing test shows that it carries complementary information. A combined forecast significantly outperforms Weighted Elo, and there is some indication that the gain is larger on the intransitive matchups our model targets. A graph-based representation of player interactions thus captures a forecasting signal that transitive rating systems discard, even between players who share no common opponents.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15278

PCLSegNet: Anatomy-Aware Deep Learning Framework for MRI-based Pancreatic Cyst Segmentation and Size Assessment

Hanyi Zhang, Tongyu Wang, Manuel Debic, Markus Wennmann, Johannes Haubold, Tamara Schikowski, Wilfried Reichardt, Fabian Bamberg 等 24 位作者

原文摘要

Early detection and follow-up of pancreatic cystic lesions (PCLs) are crucial, as some of their subtypes, such as mucinous cystic neoplasms (MCNs) and intraductal papillary mucinous neoplasms, carry a significant risk of malignant transformation. Although most AI studies investigating PCLs rely on computed tomography (CT) scans, magnetic resonance imaging (MRI) offers superior soft tissue contrast, making it highly suitable for PCLs assessment. In this work, we propose an anatomy-aware two-stage deep learning framework for automated PCLs segmentation on abdominal MRI scans. First, a publicly available pancreas segmentation model is used to localize the pancreas. Then, we introduce the anatomyaware PCLSegNet, which incorporates anatomical priors as guidance for pancreas and PCLs segmentation. To address the class imbalance problem, we develop a Class-Specific ErrorWeighted (CSEW) loss function. Postprocessing is applied through anatomical constraints.Our proposed method outperforms multi-organ segmentation models such as TotalSegmentator, achieving substantially higher Dice scores for pancreas segmentation. Moreover, it also achieves a superior normalized surface Dice (NSD) and recall for PCLs segmentationcompared to other state-of-the-art models like nnU-Net, while also notably reducing the false negative rate, facilitating the automatic early detection and the noninvasive imaging-based assessment of PCLs.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15277

DroneDiffusion: Uncertainty-Guided Diffusion Path Planner for UAV Navigation

Ivan Valuev, Iana Zhura, Valerii Serpiva, Miguel Altamirano Cabrera, Dzmitry Tsetserukou

原文摘要

We present DroneDiffusion, a perception-aware diffusion planner for local 3-D UAV trajectory generation that explicitly models and avoids failure zones caused by lens flare, overexposure, and reflective surfaces. A vision-language perceptual safety estimator produces a pixel-aligned reliability map that highlights regions of degraded sensing. A denoising diffusion probabilistic model (DDPM) is conditioned on this map together with the onboard RGB image, goal point, and initial velocity to generate egocentric 3-D trajectories. To enforce obstacle avoidance at inference time without retraining, we apply training-free CHOMP guidance over a 3-D Euclidean signed distance field. The model is trained entirely in simulation and deployed zero-shot on a real drone. Reliability conditioning raises the mean perceptual reliability along generated trajectories to 0.71, compared with 0.63 for a geometric baseline, while guidance halves the collision rate of the learned prior from 14.7% to 7.8%. Perceptual safety conditioning and geometric guidance are therefore complementary: treating sensor reliability as a first-class signal reduces incursions into unreliable regions while maintaining competitive navigation performance.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15276

Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback

Yitong Lin, Jianda Chen, Yihao Hu, Pan Wang, Hang Wang, Zhihao Wen, Xiaoxue Ren, Wei Wu

原文摘要

Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent updates. We introduce Verify by Doing (VbD), a method that co-evolves Actor and Evaluator harnesses within a single task while keeping model weights fixed. The Evaluator actively inspects artifacts and environment state with tools; its findings ground an internal signal for output selection and guide updates to both execution and verification procedures. Proposed Evaluators undergo comparative review on common candidates, while Actor updates require support from their own fresh outputs. Across AutomationBench, $τ^3$ Banking, and selected GDPval tasks, VbD achieves the highest overall scores among the compared methods operating without external feedback, with gains of 3.3, 4.1, and 2.3 percentage points over the strongest baselines on the main backbone. Ablations support the contributions of active verification and Evaluator evolution, and selection from fixed candidate pools shows that improved verification can recover successful outputs without generating new ones.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.16175

PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

Qiwei Yan, Zhiqiang Yuan, Zexi Jia, Nanxing Hu, Kailin Lyu, Jie Zhou, Jinchao Zhang

原文摘要

Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation--owner profiles, social graphs, face-name maps, and evidence provenance--is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.14498

Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model: Linking an Adversarial and a Perceptual Illusion

Alexandre Garcia-Duran, Alejandro Rodriguez-Garcia, Manuel Molano-Mazón, Alexandre Hyafil, Srikanth Ramaswamy, Janne K. Lappalainen

原文摘要

Biological visual systems compute reliably under tight metabolic and wiring constraints, whereas artificial vision systems consume far more energy and can be sensitive to adversarial perturbations. Whether networks with brain-like wiring are more robust at lower computational cost is unclear. We address this by benchmarking a task-optimized, continuous-time recurrent neural network of the fly visual system constrained by its synaptic connectome (FlyNet) against artificial neural networks. We compare it against CNNs, RAFT, and continuous-time recurrent neural networks without detailed connectome constraints (sCTRNN, CTRNN) on a collision-detection task within a differentiable 3D rendering pipeline. FlyNet is adversarially vulnerable but, relative to its compute, more robust to common video corruptions than RAFT, while using up to five orders of magnitude fewer FLOPs. The CTRNNs remain more robust than FlyNet across almost all tested perturbations, suggesting that connectome constraints benefit efficiency, through their low edge count, over robustness. Recurrence improves robustness to white-box attacks in RAFT and temporal context improves robustness to common corruptions. FlyNet's position and velocity representations degrade under adversarial textures but recover under counterfactual textures that restore correct classification while staying equally far from training, ruling out unfamiliar textures as the cause of failure. The reverse-phi illusion similarly disrupts these representations and inverts the same low-level motion statistic as the adversarial textures. Optimizing this input statistic alone, without access to the network, suffices to induce classification failure, attributing both perturbations to the same circuit vulnerability. Connectome-constrained models can thus surface adversarial failure mechanisms as testable hypotheses about biological perceptual vulnerabilities.

cs.CV · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.10130

TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues

Junhui She, Fei Wang, Kun Li, Yiqi Nie, Yuxin Liu, Zhangling Duan, Xun Yang

原文摘要

Gaze target estimation aims to infer the position of a person's gaze within a scene. Within mainstream design logic, multi-branch methods require extra supervision and annotations, while streamlined designs prioritize low-level visual saliency over true gaze intent. The former leads to a high annotation burden and hinders domain transfer, whereas the latter causes misalignment between predicted attention and actual gaze targets. To address this issue, we propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms. The model extracts visual features from a frozen encoder and utilizes an LVLM to obtain gaze-aligned textual cues. We design a transformer-based fusion module with hierarchical text supervision to preserve task semantics. Lightweight decoding heads enable the joint prediction of gaze heatmaps and in-/out-of-frame status. We evaluate our method on four mainstream datasets, and the results show competitive performance across key metrics with robust cross-dataset generalisation without extra fine-tuning. Overall, we provide a streamlined alternative to traditional designs and highlight the potential of LVLMs as accessible auxiliary guidance for gaze estimation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.13339

OPA-Pack: Object-Property-Aware Robotic Bin Packing

Jia-Hui Pan, Yeok Tatt Cheah, Zhengzhe Liu, Ka-Hei Hui, Xiaojie Gao, Pheng-Ann Heng, Yun-Hui Liu, Chi-Wing Fu

原文摘要

Robotic bin packing is a fundamental manipulation problem with broad applications in e-commerce and warehouse automation. However, existing methods primarily focus on object geometry to optimize packing compactness without explicitly modeling object properties such as fragility, edibility, and chemical compatibility that humans typically consider during packing. This paper presents OPA-Pack (Object-Property-Aware Packing), a framework that incorporates object-property information into robotic bin-packing planning. The framework includes an object property recognition scheme based on retrieval-augmented generation and chain-of-thought reasoning to establish a dataset with object property annotations for 1,032 everyday objects. The framework further incorporates OPA-Net, which encodes candidate-object properties via a property embedding layer and represents the container state using fragility and avoidance heightmaps. We design a reward function and adopt a deep Q-learning scheme to train OPA-Net. Experimental results show that OPA-Pack improves avoidance accuracy from 52.3% to 95.0%, reduces load on fragile objects by 29.4%, and achieves a packing compactness of 0.413, compared with 0.420 for the baseline. In addition, we evaluate OPA-Pack on a physical platform using 70 packing sequences sampled from 100 scanned real-world objects. Results show that OPA-Pack outperforms the baseline and other packing heuristics in reducing the number of closely packed incompatible object pairs and the number of compressed fragile objects while preserving packing compactness.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15271

MoE Pretraining:Parallelism Layout Changes the Model, Not Quality

Esther Xin

原文摘要

Large Mixture-of-Experts (MoE) models are trained across many machines, and the way the work is split, the parallelism layout, often changes between runs: a job resumes on a different GPU count, a cluster is resized, or an ablation runs on a new setup. In exact arithmetic the layout should not matter, but in real arithmetic it changes the order in which numbers are added, and some MoE rules such as load balancing and expert capacity are often computed per machine. We ask whether the layout changes the trained MoE model. We pretrain the same small MoE language models (25M to 117M parameters, 20M FineWeb-Edu tokens) with the same seed, data and hyperparameters under 9 data-parallel and expert-parallel layouts, in fp32 on CPUs and fp16 on a GPU, and compare each run with the effect of a new random seed. Across 80 runs we find: (1) The layout does not change model quality, but it does change the model: final predictions differ about 80% as much as with a new seed, and over 90% of routing decisions differ. Any layout, a one-bit change to one weight, or a different CPU thread count has the same effect. (2) The cause is the router: decisions that flip are almost exactly those where two experts were nearly tied (AUC 0.97 to 1.00 in the first 16 steps). (3) More, smaller experts create more near-ties (2.7% with 8 experts, 23% with 64) and less reproducible routing (68% vs. 100% of decisions differ), but outputs do not drift further. (4) A dense model of the same active size is far more stable (0.12x the seed level in fp32, 0.58x in fp16), while the MoE reaches about 0.8x at both precisions and twice as fast. (5) When pretraining resumes on a new layout, timing matters: switching at 84% of pretraining barely changes the final model, while switching at 10%, just after warm-up, changes it substantially. We release code, run logs and data.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15270

Communication-Efficient Federated Multi-View Clustering via View-Aware Quantization

Khadija Ardif, Meryeme Ayache, Nidal Nasser, Ouiame Marnissi

原文摘要

Federated multi-view clustering (FedMVC) has recently attracted increasing attention for its ability to exploit complementary clustering structures across multiple clients while preserving data privacy. However, existing FedMVC methods often suffer from high communication overhead due to the repeated transmission of high-dimensional representations, which limits their scalability in practical federated systems. Moreover, different views may contribute unequally to the clustering performance, calling for adaptive communication strategies. In this paper, we propose a view-aware quantization algorithm for communication-efficient FedMVC. By dynamically assigning quantization bits based on iteratively updated view importance scores, the proposed algorithm effectively balances clustering performance and communication efficiency under a global bit budget constraint. To validate its generality, we integrate our approach into four state-of-the-art FedMVC methods. Extensive experiments on multiple benchmark datasets demonstrate that view-aware quantization achieves up to 6.59x communication reduction while maintaining and in some cases surpassing baseline clustering performance, confirming the effectiveness and scalability of the proposed approach.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13012

khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter

Warit Sirichotedumrong, Adisai Na-Thalang, Chanakan Wittayasakpan, Kritsadha Phatcharoen, Kunat Pipatanakul

原文摘要

Thai is written without spaces between words, making segmentation a foundational step in most Thai NLP pipelines. Existing tools primarily reproduce the word-level conventions of corpora such as BEST; however, because the notion of a "word" in Thai lacks a unified linguistic consensus, these conventions struggle with productive compounding, leading to arbitrary boundaries and ambiguity in downstream representations. Instead, we propose operating at the morphological level, focusing on khammoon, the smallest atomic unit that carries meaning. Segmenting at the morphemic level provides an explicit, consistent morphological representation that eliminates compounding ambiguity. Crucially, this representation benefits downstream learning: models trained on morphemes perform on par with or exceed word-level baselines across part-of-speech tagging, named-entity recognition, and sentiment classification, demonstrating that linguistic consistency improves representation quality without downstream performance penalty. To operationalize this representation, we translate linguistic principles into a formal decision guideline with near-perfect human agreement ($κ\approx 0.99$), scale annotation with an LLM, and correct systematic errors with human labels. Finally, we train khammoon, a lightweight 1M-parameter convolutional BiLSTM segmenter designed for efficient CPU inference, achieving a boundary F1 of 0.992 on out-of-domain text. The guideline, datasets, model, and library are all publicly released.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06407

WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling

Guanrou Yang, Tian Tan, Qian Chen, Zhikang Niu, Yakun Song, Ziyang Ma, Yushen Chen, Zeyu Xie 等 15 位作者

原文摘要

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challenges. Typically, semantics-oriented features are learned from self-supervised learning (SSL), and acoustic-oriented features from reconstruction. Such fragmented representations hinder the realization of truly unified speech systems. We present WavCube, a compact continuous latent derived from an SSL speech encoder that simultaneously supports speech understanding, reconstruction, and generation. WavCube employs a two-stage training scheme. Stage 1 trains a semantic bottleneck to filter off-manifold redundancy that makes raw SSL features intractable for diffusion. Stage 2 injects fine-grained acoustic details via end-to-end reconstruction, while a semantic anchoring loss ensures the representation remains grounded within its original semantic manifold. Comprehensive experiments show that WavCube closely approaches WavLM performance on SUPERB despite an 8x dimensional compression, attains reconstruction quality on par with existing acoustic representations, delivers state-of-the-art zero-shot TTS performance with markedly faster training convergence, and excels in speech enhancement, separation, and voice conversion tasks on the SUPERB-SG benchmark. Systematic ablations reveal that WavCube's two-stage recipe resolves two intrinsic flaws of SSL features for generative modeling, paving the way for future unified speech systems. Codes and checkpoints are available at https://github.com/yanghaha0908/WavCube.

eess.AS · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.12657

When Does Sliced Inference Pay Off? Resolution, Tiling and Dense Fusion for Small Object Detection

Stefan Becker, Jens Bayer, David Münch, Wolfgang Hübner

原文摘要

Sliced inference such as SAHI is the standard remedy for small objects in high-resolution imagery, but its gains are usually measured against low-resolution baselines. We revisit sliced inference with scale as the explicit variable and ask when tiling actually pays off. We compare seven dense detectors from four families on VisDrone and DOTA, under pre-specified hypotheses, calibration-only tuning and a single evaluation on held-out test data. Two findings emerge. First, much of the benefit attributed to slicing is a resolution effect: on VisDrone, a single pass trained at a higher resolution outperforms tiling with box fusion (merging decoded boxes) for every detector that could be trained at that resolution, and at equal compute a higher resolution helps more than a larger model. Second, tiles carry complementary information that box fusion wastes. We introduce SCAHI (Slicing with Coverage-Aware Hyper Inference), which accumulates the dense outputs of all passes with weights that give every image position the same total coverage, and reads objects off a peak grid fine enough to keep crowded neighbours apart. On identical passes, SCAHI outperforms box fusion for every YOLO detector on both datasets and matches it for FCOS. On DOTA, whose images far exceed the resolution a single pass can be trained at, tiles with SCAHI beat the best single pass for every detector, by 4.3 to 5.6 mAP50 at 2048 px, and replacing only SAHI's merge step by SCAHI adds 2.3 to 4.0 mAP50. An ablation attributes the gain to the border weighting and the resolution of the peak grid. Source code is available at https://github.com/beckerio/scahi.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15268

Knowledge in the Harness, Reliability in the Weights: Teacher-Free Co-Evolution of an LLM Agent

Yujia Zhang, Xinqi Ren, Shixiong Zhou, Jia Meng

原文摘要

Small open models suit private customer-service deployments but trail frontier models in two ways: they miss what the written policy requires in a given situation, and they act inconsistently on what they know. We study whether such a model can close both gaps from its own deployment logs and their reference outcomes, without a stronger teacher model. Our starting point is a Gemma 4 12B agent that reads its domain policy from on-demand skills rather than from its system prompt. In each round, the deployed system serves a fresh batch of tasks; the base model diagnoses failed conversations and writes rules into the skills, and a rule survives only if it passes code checks, counterexample self-review, a paired retest, and a noise-calibrated validation gate. Reinforcement learning (GRPO) then trains a LoRA adapter on complete multi-turn, tool-using conversations. On the retail and airline domains of $τ^2$-bench, without training or selecting on official tasks, the agent after two rounds improves on this starting point by 12.5 pass$^1$ points in retail and 19.5 in airline, and by 18.4 and 22.0 pass$^4$ points. It also exceeds the benchmark's reference agent, which runs the same model with the whole policy in its system prompt, by 11.8 and 8.0 pass$^1$ points and by 22.8 and 16.0 pass$^4$ points, closing most of the gap to three frontier models under the same protocol. A $2\times2$ ablation shows that the rules rescue tasks the agent never solved and carry policy knowledge that RL with the rules in context does not internalize, whereas the trained weights make solved tasks reliable.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13243

GigaEdge Spench: An SDK for Practical Streaming Speech Enhancement

Artem Sokolov, Artem Khaidarov, Yana Lysova, Alexander Gladkikh, Vitaliy Yulis

原文摘要

We present GigaEdge Spench, an open-source SDK for streaming speech enhancement on CPU servers, mobile devices, and in browsers. Applications can build enhancement channels from neural denoising, normalization and dynamics blocks, sample-rate conversion, and acoustic echo cancellation where supported. These stages can be combined, while normalization can also run without a neural model. The release includes an 8 kHz INT8 denoiser and discriminative and hybrid 48 kHz FP32 models. A shared C++ core supports ONNX Runtime and TensorFlow Lite through native interfaces, Android and iOS SDKs, and WebAssembly integration. Independent stream contexts share model resources, and consecutive frames from one stream can be processed in a single inference call. We evaluate the released models on EARS-WHAM v2 and compare their quality and processing costs with RNNoise and DPDFNet2. All tested native and Web configurations process files faster than real time, although larger chunks require more time to collect input. We also measure how many streams a shared model can process on a CPU. Our contribution is a configurable deployment system and an experimental study of how model choice, chunk size, and execution environment affect its use. All reported SDK timing uses ONNX Runtime. Index Terms: speech enhancement, streaming inference, cross-platform deployment, temporal frame grouping, computational efficiency

cs.LG · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15267

A Closer Look at Language Model Introspection: Probing Information and Reporting

Dustin Rubin, Vincenzo Timmel, Xufeng He, Aritra Saha, JooMan Kim, Vijay Madisetti

原文摘要

One way to study language-model introspection is to test whether models can identify where their activations have been perturbed. We train a simple linear classifier to identify the perturbed sentence from the model's activations, then compare its predictions with the model's own answers across pretraining and injection strengths. This tests whether the model is being asked to report information that is already easy to recover. If so, successful localization may be less demanding than it first appears and may not extend to the broader uses that motivate introspection research, such as faithfully explaining a model's reasoning or helping researchers assess the reliability of its answers. With an injection four times the typical activation norm at layer 0 and probe readout at layer 24 in OLMo~3 32B, the supervised probe reaches 98.3\% accuracy after 8.4 billion training tokens, while the model's zero-shot answer remains at chance (11.1\%). At the released base checkpoint, these accuracies reach 99.1\% and 89.6\%, respectively. Across 7B and 32B, location is already decodable in randomly initialized networks, showing that the architecture can support these traces without pretraining. In these experiments, location information lies close enough to the surface for a simple linear probe to recover it, so successful reporting need not imply broader access to the model's internal computation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15263

Probe-Based Routing for Join Optimizer Selection

Vladimir Burlakov, Alena Rybakina, Sergey Kudashev, Ilgam Latypov, Konstantin Gilev, Alexander Demin, Denis Ponomaryov, Yuriy Dorn

原文摘要

In optimizers that choose a join-order solver by a size rule, join ordering is an algorithm-selection problem, because dynamic programming (DP), genetic search (GEQO), and Monte Carlo tree search (MCTS) each win on different queries. PostgreSQL nevertheless chooses among them by relation count alone, although queries with the same relation count can favor different solvers. This paper introduces two landscape features that a probe computes from random join orders in microseconds per query. The tail spacing $α$ describes how the costs of the best sampled orders are spaced, and the crossover surprise $θ$ describes how far the cost of a crossover child deviates from the mean cost of its parents. The router clusters training queries by these features and the relation count, assigns a solver to every cluster that this solver wins in total end-to-end time by a margin, and leaves all other queries to PostgreSQL's default rule. On JOB and IMDb-CEB, the router lowers mean end-to-end time relative to the default rule, and on IMDb-CEB the probe features nearly double the gain obtained from the relation count alone, so they carry information about the queries that the relation count lacks.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15262

CastWorld: Benchmarking Context-Aware Agentic Time Series Forecasting Beyond Predictive Accuracy

Bokai Pan, Ruijie Yang, Mingyue Cheng, Jiahao Wang, Xiaoyu Tao

原文摘要

Agentic time series forecasting extends conventional approaches beyond one-shot numerical prediction toward autonomous, context-aware interaction. However, existing benchmarks offer limited integrated support for diverse contextual information, forecasting-specific adaptive interactions, and systematic evaluation of forecasting agents. In this paper, we introduce CastWorld, an agentic benchmark for context-aware time series forecasting. First, its context-rich dataset suite spans 8 domains and 25 real-world datasets, covering external variables, events, and historical cases under a unified context specification. Second, a lightweight, modular forecasting-native harness provides 49 core tools and a state-adaptive loop that tracks forecast versions and enables iterative evidence gathering and forecast revision. Intermediate forecasts can expose information gaps, while newly acquired evidence guides subsequent revisions and final version selection. Third, model-level evaluation assesses forecast quality, process execution, behavioral trustworthiness, and resource efficiency through decision trajectories and forecast-version histories. Also, systems-level evaluation compares predictive accuracy across forecasting systems. Experiments reveal distinct decision behaviors among agents with comparable accuracy. Additional interactions do not necessarily improve forecasts, and agents may fail to select their best previously generated predictions. Allowing evidence acquisition during forecast refinement improves task-aware forecast scores across all three evaluated models. CastWorld provides a reusable foundation for evaluating agentic time series forecasting under controlled conditions.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15260

Driving World Models Move the Camera, Not the Scene

Yuqiao Feng, Xiaoyu Ao

原文摘要

Plan-conditioned driving world models are used to compare candidate plans, so their forecast should change with the plan as the real scene would, yet widely used control metrics check only whether the camera follows the command. Recorded drives already contain real outcomes of plans that were never driven: retiming a log gives pose-matched images and LiDAR for other speeds, and a stereo rig records a laterally shifted view. Against these references, released world models move their camera but barely move the scene: their scene response, the share of the real change in distance that the forecast reproduces, reaches at most about a third of real video's, and the trajectory score cannot tell an executed speed command from an ignored one. Interventions inside the generator trace the failure to the plan's channel. The forecast geometry follows the context frames; once they carry the planned geometry, plan tokens add little. ReTime-Compose therefore delivers the plan as geometry, without training. It transports the frames of one logged-speed rollout to the planned cameras, and the frozen model completes only what no frame covers. Frozen generators then follow a 0.54 m lateral shift nearly as the real scene does on KITTI, nuScenes and Argoverse 2, and respond more than re-sampling to slow-down plans in three generators and to speed-up plans in two.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.13585

Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation

Binglei Li, Mengping Yang, Zhiyu Tan, Qiang Xiang, Junping Zhang, Hao Li

原文摘要

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior approaches enhance such interactions via architectural design or handcrafted textual condition weighting, but lack flexibility and overlook the dynamic interactions across different blocks and denoising stages. To provide a more flexible and efficient solution to this problem, we propose Diff-Aid, a lightweight inference-time method that adaptively adjusts per-token text and image interactions across transformer blocks and denoising timesteps. Beyond improving generation quality, Diff-Aid yields interpretable modulation patterns that reveal how different blocks, timesteps, and textual tokens contribute to semantic alignment during denoising. As a plug-and-play module, Diff-Aid can be seamlessly integrated into downstream applications for further improvement, including style LoRAs, controllable generation, and zero-shot editing. Experiments on strong baselines (SD 3.5 and FLUX) demonstrate consistent improvements in prompt adherence, visual quality, and human preference across various metrics. Our code and models will be released.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15258

Exact Decisions and Certified Values in $L_\infty$-Norm Computation from State-Space Representations

Alban Quadrat, Fabrice Rouillier, Grace Younes

原文摘要

Computing the $L_\infty$-norm of a time-invariant linear ordinary differential control system is a routine task in robust control, usually delegated to floating-point routines that perform well on most practical systems. Behind the numerical value, however, lies a discrete decision: whether a pole lies on the imaginary axis, and whether a mode of a realization is actually a pole of the transfer matrix. Floating-point arithmetic can only replace this decision with a tolerance. This paper explains, for a control audience, what reliable symbolic-numeric computation offers for this problem: exact arithmetic where a decision has to be made, and certified enclosures where a value has to be computed. We show how the problem is turned into a small polynomial system directly from state-space data, how this system is solved in practice, and what it costs. A benchmark on the {\tt COMPleib} library and on families of systems with known norms shows that two standard numerical routines err in opposite directions on the imaginary-axis decision, and never on the same system, while the certified method decides it correctly on every instance tested and computes the norm at a cost comparable to that of the numerical routines on most systems. We conclude with practical guidelines for users of numerical tools.

math.OC · cs.SC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12079

Correct First, Fast Second: What a Local 7B Code Model Can and Cannot Do for GPU Kernel Optimization

Jui-Chien Tsou, Po-Yi Wu

原文摘要

We study how much the interaction strategy around a fixed, locally hosted 7B-parameter code model (Qwen2.5-Coder-7B-Instruct) affects its ability to replace PyTorch operators with custom CUDA kernels. On 30 KernelBench tasks (levels 1-3, first 10 each, evaluated on a V100), we compare four regimes of increasing structure: zero-shot prompting, profiling-guided prompting, iterative refinement on execution feedback, and a multi-agent loop (analysis, retrieval, generation, evaluation, feedback triage) in which the same model fills four roles around a non-LLM evaluator. Three findings stand out. (1) Correctness, not speed, is the binding constraint: even correct generated kernels average 0.97-0.99x the speed of eager PyTorch, because a 7B model cannot out-write cuBLAS/cuDNN on dense GEMM and convolution; the only real wins are fused memory-bound epilogues. (2) The best strategy depends on difficulty: profiling-guided prompting is strongest overall (43% correct, 27% faster than baseline), but the agent loop is the only method that solves any level-2 fusion problem (3/10 vs. 0/10 for all others). (3) Naive agentic scaffolding is actively harmful: our first agent scored 3% correct, below zero-shot's 30%, and the decisive repairs were matching the agent's ambition to the model's competence and spending compute on best-of-n sampling under a real execution oracle (3% to 33% correct from n=1 to n=8), not on more reasoning steps.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.19363

LongReasonArena: A Long Reasoning Benchmark for Large Language Models

Jiayu Ding, Shuming Ma, Lei Cui, Nanning Zheng, Furu Wei

原文摘要

Existing long-context benchmarks for Large Language Models (LLMs) focus on evaluating comprehension of long inputs, while overlooking the evaluation of long reasoning abilities. To address this gap, we introduce LongReasonArena, a benchmark specifically designed to assess the long reasoning capabilities of LLMs. Our tasks require models to solve problems by executing multi-step algorithms that reflect key aspects of long reasoning, such as retrieval and backtracking. By controlling the inputs, the required reasoning length can be arbitrarily scaled, reaching up to 1 million tokens of reasoning for the most challenging tasks. Extensive evaluation results demonstrate that LongReasonArena presents a significant challenge for both open-source and proprietary LLMs. For instance, even GPT-5 achieves only 27.8% accuracy on Level 3. Further analysis also reveals that the accuracy exhibits a linear decline with respect to the logarithm of the expected number of reasoning steps. Our code and data are available at https://github.com/LongReasonArena/LongReasonArena.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15250

Multi-head Quantum Neural Networks: Replacing Transformer Blocks with NISQ Modules inside a 30-Billion-Parameter LLM

Maforikan Amoussou, Borja Aizpurua, Sukhbinder Singh, Román Orús, Hans-Arno Jacobsen

原文摘要

We introduce the multi-head quantum neural network (QNN), a quantum module compatible with noisy intermediate-scale quantum (NISQ) devices that can replace transformer blocks inside pre-trained large language models (LLMs) with little loss in accuracy and with far fewer parameters than the blocks it replaces. Encoding a model's $D$ hidden neurons into a qubit register is the obstacle: amplitude encoding scales poorly in circuit depth and angle encoding in qubit count, so neither is practical at production-scale width. We instead partition the hidden space into $k$ disjoint heads, angle-encode each into an $n_q$-qubit register, process the heads in parallel, and couple them through constrained classical linear layers, the mixers. Performing surgery on Qwen3-30B-A3B-Instruct-2507, we show that a single multi-head QNN with $145\,281$ trainable parameters ($D=2048$, $k=32$, $n_q=8$, $L=4$) can replace a contiguous span of eight transformer blocks, displacing $16.33\%$ of the model's parameters. Ablations show that, for a single replaced block, the quantum heads (circuits followed by a learned readout), and not the classical mixers alone, recover the displaced function, whereas for fused spans the mixers alone come within $1$-$3\%$ of the full module in perplexity. Whether this benefit is specific to trained, entangling quantum circuits is not established: controls that switch the entangler off (two seeds), or freeze the circuit at its initial or at uniformly random angles (one seed), beat the full module on held-out perplexity, and a parameter-matched classical multilayer perceptron remains a few percent ahead of the full module. We train classically with exact statevector simulation, then execute the quantum heads of our fusion checkpoints on a $156$-qubit IBM Heron processor, showing that NISQ-scale quantum modules can be installed in a production-scale LLM and run on hardware.

quant-ph · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2511.05963

Next-Latent Prediction Transformers Learn Compact World Models

Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward S. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam 等 10 位作者

原文摘要

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with consistent transition rules. This often leads to learning solutions that generalize poorly. We introduce Next-Latent Prediction (NextLat), which extends standard next-token training with self-supervised predictions in the latent space. Specifically, NextLat trains a transformer to learn latent representations that are predictive of its next latent state given the next token. Theoretically, we show that these latents converge towards belief states, compressed information about the history necessary to predict the future. This simple auxiliary objective injects a recurrent inductive bias into transformers while leaving their architecture, parallel training efficiency, and inference unchanged. NextLat effectively encourages transformers to form compact internal world models with coherent belief states and transition dynamics -- crucial properties not guaranteed by standard next-token prediction alone. Empirically, across benchmarks in world modeling, reasoning, planning, and language modeling, NextLat demonstrates significant gains over standard next-token prediction and other baselines in downstream accuracy, representation compression, and lookahead planning. Furthermore, NextLat enables variable-length self-speculative decoding, accelerating inference by up to 3.3x in language modeling. NextLat offers a simple yet effective paradigm for learning compact, predictive representations in transformers that generalize better. Our code is available at https://github.com/JaydenTeoh/NextLat.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15247

Protected Unbiased Sparsification: A Sharp Loewner Curve

Ziyang Wang, Menghao Li

原文摘要

Random sparsification replaces a probability vector by a random vector with few nonzero entries. We ask for unbiasedness, exact preservation of prescribed linear statistics, and a covariance guarantee for every downstream linear response. Let $p$ have $k$ positive coordinates, let $A$ specify the protected statistics, and let $d\le k-2$ be their effective rank. For every $d+1\le m\le k$, we construct an unbiased random probability vector $Q$ with at most $m$ nonzero coordinates, $AQ=Ap$ on every realization, and $\operatorname{Cov}(Q)\preceq h C_{p\mid A}$, where $h=(k-m)/((m-d)(k-d-1))$ and $C_{p\mid A}$ is the categorical covariance after optimal linear adjustment for the protected statistics. This coefficient is sharp uniformly over instances, even among biased estimators when error is measured by its second moment. A residual covariance bridge extends the concurrent unprotected curve to arbitrary pathwise linear protection. We also characterize instance-optimal constants for partitions with uniform weights within classes and derive bounds for peaked weights. For rational inputs, an exact Las Vegas sampler attains the curve within a factor $1+ε$ in expected polynomial time. A separate fast block-pivotal sampler preserves block masses and is no worse in covariance order than independent sampling within blocks. Experiments illustrate the theory on synthetic weights and language-model attention. In Qwen2.5-7B-Instruct decoding, the fast sampler preserves block masses, while comparisons with VarOpt remain statistically inconclusive and top-$m$ truncation scores highest on RULER.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15246

Dual Representation Enhanced Diffusion Policy for Flexible Job Shop Scheduling

Yunyi Zhao, Wei Zhang, Cheng Xiang, Vadakkepat Prahlad, Zuming Liu

原文摘要

The Flexible Job-Shop Scheduling Problem (FJSP) is a fundamental and challenging optimization problem in smart manufacturing. Although recent deep reinforcement learning (DRL) approaches can learn effective scheduling policies through interaction with the environment, their performance often degrades as problem scale and processing-time uncertainty increase. In this paper, we propose DredRL, a dual representation enhanced diffusion-policy reinforcement learning scheduler. DredRL first constructs enhanced dual representations of operations and machines through self- and cross-attention mechanisms to capture both intra-entity and inter-entity dependencies. A diffusion model is further employed as the policy network, generating scheduling decisions through iterative denoising conditioned on the encoded state to enhance policy expressiveness and robustness. Extensive experiments on synthetic, public, large-scale, and stochastic FJSP benchmarks demonstrate that DredRL outperforms state-of-the-art learning-based schedulers across most configurations. Compared with SOTA learning-based methods, DredRL reduces makespan by up to 5.44% on synthetic instances. It also achieves the best learning-based performance on three of four public benchmarks and outperforms the stochasticity-aware algorithms on stochastic benchmarks. These results demonstrate that combining enhanced dual representations with diffusion-based policies provides an effective and robust approach for large scale scalable FJSP scheduling in complicated environment.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.34982

ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning

Di Zhu, Ziheng Yan, Fang Wan

原文摘要

Vision-Language-Action (VLA) models have shown great promise for robotic manipulation by mapping multi-modal semantics to physical actions. However, this mapping inherently struggles to align these coarse-grained semantics with fine-grained temporal execution. It leaves VLA models with limited generalization and insufficient robustness in cluttered environments. To overcome this issue, we propose ActionUNet, an efficient multi-scale fine-tuning framework that enhances pre-trained VLA models with minimal computational cost. ActionUNet first constructs a lightweight temporal U-Net within the temporal-aligned action feature space to fuse hierarchical structural priors, effectively bridging the scale gap between semantics and temporal executions. Recognizing that multi-scale modeling can disrupt microscopic temporal continuity and cause mechanical oscillations, ActionUNet then employs a conditional SIREN as a continuous action decoder. Equipped with explicit second-order smoothness constraints, this decoder guarantees temporal continuity and reduces high-frequency motion jitter. By smoothing temporal discontinuities from multi-scale fusion, this continuous formulation reduces mechanical execution failures while preserving the base VLA model's generalization and manipulation robustness. Extensive experiments on RoboTwin 2.0 and LIBERO-Plus benchmarks, together with real-world hard evaluations, demonstrate that ActionUNet significantly improves π0.5 success rates by absolute 9.8%, 6.1%, and 11.4%, respectively, while also generalizing to the regression-based OpenVLA-OFT backbone, highlighting its effectiveness and efficiency as a fine-tuning strategy. Code and implementation details are available at https://github.com/Di-Zhu123/ActionUNet.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15242

Computational Raga Recognition: A Theory-Driven Approach

Janay Sukheja, Shailaja D. Sharma

原文摘要

Raga recognition in Hindustani classical music is difficult because a raga is not defined only by the notes used in it. Its identity also depends on the way notes are emphasized, the movement between notes and characteristic phrases. In this work, we develop a computational approach to analyse these characteristics directly from audio recordings. The method uses pitch extracted from recordings and represents it using a 44-position note framework based on the 22-shruti system. From this representation, Raga features based on the Indian classical musicology are extracted.Each feature is compared with a reference representation of the raga and the resulting scores are combined to obtain an overall similarity score. The method is first studied using Raga Yaman and is then tested on recordings of other ragas. The computational results are also compared with the theoretical description of Yaman to identify which raga characteristics are captured well and where the method has limitations.

cs.SD · cs.HC · cs.LG

查看论文
arXiv ↗PDF ↗