跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-21 11:13 — 2026-11-22 11:13(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

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

浏览论文库

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

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.26186

Reward misalignment as an opportunity for materials discovery

Ryotaro Okabe, Shoki Kishida, Abhijatmedhi Chotrattanapituk, Dominic Bollettieri, Takuya Isogawa, Yongqiang Cheng, Mingda Li, Masaki Adachi

原文摘要

Reward misalignment is usually regarded as a failure of artificial intelligence. In materials discovery with generative AI models, however, disagreement between predefined rewards and expert judgment may reveal materials that the rewards overlook. We investigate this possibility using electronic flat bands as a prime example. Experts mostly agree with a numerical bandwidth score, but their disagreements are systematic and cannot be explained by an estimated 5% rate of mistaken labels. We learn the experts' preferences from pairwise comparisons and use them to guide a crystal diffusion model. The learned preferences and numerical score agree on the flattest bands but diverge elsewhere. For example, the preferences favor KCo2As2 and CoGa, reported compounds with partially flat bands that the score would discard. The framework also extends to synthesizability and phonon properties. Our findings suggest that reward misalignment can expose opportunities for materials discovery beyond what fixed rewards are designed to find.

cond-mat.mtrl-sci · cs.LG

新论文 · v1arXiv:2611.26183

Thermodynamically Consistent Neural Networks for a Universal Fluid Gibbs Free Energy Equation of State

Xurui Li, Zhiguo Gan, Jiaming Zhang, Hongxi Zeng, Diannan Lu

原文摘要

Over the past three centuries, many thermodynamics researchers have worked to develop fluid equations of state with both high accuracy and broad applicability, proposing various theoretical frameworks and models. Building on these efforts, this study uses Gibbs free energy as the starting point and introduces thermodynamically consistent neural networks to construct a fluid equation of state based on Gibbs free energy (GEoS). This approach establishes a novel machine learning framework that provides a unified representation of fluid states. GEoS performs well on the vapor- and liquid-phase density test sets, with average absolute relative deviations (AARDs) of 5.25% and 3.96%, respectively. It outperforms conventional volume-translated cubic equations of state and existing machine learning models, demonstrating its effectiveness. Further analysis using the UMAP dimensionality reduction method shows that most molecules in the test set belong to extrapolation systems, confirming the strong generalization ability of the model. Finally, the test results show that the PC-SAFT equation fitted using GEoS maintains high predictive accuracy, providing a reliable basis for its practical application in industry.

cs.LG

版本更新 · v3arXiv:2606.27786

SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation

Ruochang Li, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun

原文摘要

Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts between retrieved context and parametric knowledge can cause LLMs to rely on inconsistent internal knowledge, hindering their ability to faithfully leverage retrieved evidence. Existing approaches mitigate this issue by editing parametric knowledge to resolve such conflicts. However, locating and modifying knowledge encoded in model parameters is challenging and may inadvertently compromise the backbone LLM's capabilities. In this paper, we introduce SPARK, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation. Specifically, SPARK introduces a lightweight participation policy that dynamically modulates the contribution of FFN-mediated parametric knowledge while keeping the backbone LLM frozen. The participation policy is optimized with a faithfulness-oriented reward, enabling fine-grained control over parametric knowledge participation during generation. Extensive experiments on six datasets validate the effectiveness of SPARK, which introduces and optimizes only 0.01\% additional trainable parameters while keeping the backbone LLM fully frozen, thereby preserving its general capabilities and achieving more faithful generation than competitive baselines. All datasets and code are available at https://github.com/OpenBMB/SPARK.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.06863

RMRRT: Riemannian Barrier Metric RRT for Inequality-Aware Steering on Equality Manifolds

Minhyeong Kang, Sanghyun Kim

原文摘要

This paper presents a motion planning framework that unifies equality and inequality constraints within a single geometric formulation for sampling-based planning in high-dimensional robotic systems. In conventional sampling-based planners, equality constraints are typically enforced through projection, whereas inequality constraints are handled separately through binary validity checks such as collision testing, often leading to inefficient exploration. To address this limitation, we propose Riemannian Barrier Metric RRT (RMRRT), which constructs a unified local geometry for planning on equality-constrained manifolds. RMRRT first builds an ambient barrier metric from inequality-sensitive barrier terms and then induces a tangent-space metric via a G-orthogonal projection associated with the equality constraints. The resulting tangent-space metric is used consistently in both steering and nearest-neighbor selection, biasing exploration away from nearby inequality boundaries while preserving first-order equality consistency. In this work, the metric is instantiated from signed-distance-based geometric proxy inequalities to provide collision-informative tangent-space directions; hard feasibility is enforced separately through standard validity checks. Experimental results show that RMRRT achieves a 100% success rate across diverse constrained manipulation tasks in both simulation and real-world settings, while reducing planning time relative to representative constrained planning baselines. Ablation studies further demonstrate that the proposed metric improves exploration quality by reducing rejected samples and shortening path length. Experiment videos and source code are available at: https://rcilab.khu.ac.kr/rmrrt/

cs.RO

版本更新 · v16arXiv:2507.12311

Ontology Interoperability: A Comprehensive Framework for Industry-Scale Applications

Zhangcheng Qiang

原文摘要

Different ontologies with conflicting and overlapping concepts cause havoc in the design, develop, and deploy of ontology-driven applications. In this work, we propose a comprehensive ontology interoperability framework for industry-scale ontology-driven applications. The framework employs three state-of-the-art semantic techniques in different phases of the ontology engineering (OE) life cycle: ontology design patterns (ODPs) in the design phase, ontology matching and versioning (OM&OV) in the develop phase, and ontology validation (OVA) in the deploy phase, to achieve better ontology interoperability.

cs.IR

版本更新 · v2arXiv:2611.23445

Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops

Michael Schroeder

原文摘要

Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strategies aim to rescue accuracy by selectively retaining high-precision parameters, the fundamental mechanics of where and why these models collapse remain poorly understood. In this study, we systematically analyze the anatomy of quantization collapse across standard Vision CNNs (including ResNet and EfficientNet backbones) evaluated on the full 50,000-image ImageNet-1k validation set. First, we map the exact progression of degradation, demonstrating that collapse is highly non-linear and concentrated in late-stage pointwise projections and depthwise layers. Second, we introduce a structured, multi-step recovery waterfall that evaluates selective integer precision (INT4/INT8) and selective floating-point scales. We show that keeping less than 5% of critical layer activations in 8-bit precision recovers up to 92% of the accuracy lost during aggressive sub-4-bit compression. Finally, we bridge the hardware reality gap by evaluating deployment performance on standard ARM and x86 CPU architectures. We show that while low-bit quantization reduces memory storage requirements, standard runtime software bit-unpacking introduces a 1.48x to 21.5x execution slowdown depending on batch size, highlighting a critical trade-off between model footprint and actual edge throughput. Our findings provide a practical blueprint for navigating the limits of sub-4-bit deployment without sacrificing hardware performance.

cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.26179

RegionAgent: Two-Stage Preference Optimization for Regional Image Restoration

Weiyu Zhou, Jiacong Tang, Tao Hu, Axi Niu, Jinqiu Sun, Peng Wu, Wei Dong, Qingsen Yan

原文摘要

Images under non-uniform coupled degradations require diverse restoration capabilities for different degraded regions. Existing methods employ globally uniform operations, potentially overlooking regional differences and causing incomplete restoration or even damage to image content. Moreover, a degraded region may require successive restoration actions, and earlier actions may alter residual degradation characteristics or introduce artifacts, potentially hindering subsequent restoration. To address these challenges, we propose RegionAgent, an adaptive restoration framework that trains a Vision-Language Model (VLM) through two-stage preference learning to generate a region-specific restoration action at each iteration. Specifically, we first train the VLM to select an action suited to the current region through step-level Direct Preference Optimization (DPO), using preferences derived from immediate restoration feedback to supervise only the differing component in each action pair. To account for the effects of current actions on subsequent restoration, we then apply trajectory-level DPO, using preferences derived from complete trajectory scores to supervise the sole differing action in each trajectory pair. Furthermore, as conventional image-pair datasets do not directly provide preferences over regional restoration decisions, we construct a regional restoration preference dataset comprising 10K action pairs and 20K trajectory pairs for two-stage VLM training. Experiments across multiple datasets demonstrate strong restoration performance under both mixed and single degradations. Ablation studies further validate the effectiveness of two-stage preference learning in improving restoration quality.

cs.CV · cs.AI

新论文 · v1arXiv:2611.26178

FlexVSR: Continuous-Scale Super-Resolution for Streaming Video Generation

Ji Wang, Haonan An, Jiasheng Zhang, Renlong Chen

原文摘要

Real-time streaming video generation has gained rapid momentum in live content creation and interactive media. Deploying such systems in practice requires flexible scaling factors to accommodate diverse source resolutions, target displays, and computational budgets. However, extending fixed-scale generative video super-resolution (VSR) to varying target scales poses two challenges: downsampling from a larger fixed scale incurs redundant cost, while re-optimizing the diffusion transformer (DiT) is costly and alters the shared generative prior. To address both, we propose FlexVSR, a decoupled framework for continuous-scale streaming generative VSR with supervision at only a few scales. Our key insight is that naively resampling fixed-scale latents onto a new target grid induces scale-dependent input mismatch, which can be effectively addressed through parameter-efficient, scale-aware adaptation of the latent interface without updating the DiT. To this end, FlexVSR introduces ReLSA (Refined Latent Scale Adaptation), a lightweight latent adapter that constructs and refines target-grid latents before they enter the DiT, enabling a shared frozen VSR prior to generalize across continuous scales with only 0.274M trainable parameters and an adaptation cost of 7.3 H100 GPU-hours, while introducing no additional temporal dependencies and preserving the native causal streaming protocol. Extensive experiments demonstrate competitive or superior reconstruction and temporal quality, lower latency than most native-scale streaming baselines and offline methods, and effective generalization to unseen continuous scales, filling the continuous-scale gap in real-time streaming generative VSR.

cs.CV

版本更新 · v2arXiv:2611.23446

Where Global Context and Weight Sharing Work in Compact Vision Backbones

Michael Schroeder

原文摘要

Compact convolutional backbones such as EfficientNet achieve strong parameter efficiency through local depthwise separable convolutions, yet two structural questions remain central to hybrid design: where does global self-attention improve recognition over pure convolution, and can repeated blocks share weights without losing representational capacity? We investigate both questions on ImageNet-1k (50,000-image validation) using controlled EfficientNet-B0 experiments. First, we show that wrapping a classification backbone in multi-scale feature pyramids (BiFPN) fails to outperform a plain MBConv trunk (69.99% - 71.81% vs. 72.86% plain B0) until paired with stage attention (73.15%). In contrast, keeping the MBConv trunk intact and inserting lightweight zero-gated residual self-attention adapters at stages P3 (28x28 windowed), P4 (14x14 global), and P5 (7x7 global) reaches 74.02% standalone and outperforms a bit-for-bit matched plain-B0 control by +0.954 percentage points (73.88% vs. 72.92%) across an 88-epoch stateless replay schedule, with learned attention amplitude rising monotonically with semantic depth (27.2% at P3 -> 45.4% at P4 -> 66.3% at P5). Second, we evaluate recurrent weight sharing across repeated MBConv blocks with pass-specific BatchNorm statistics (+1,536 parameters per pass). While post-hoc kernel averaging degrades accuracy to 17.03% and single-template stage tying (-27.6% parameters) plateaus at 66.10%, alternating two shared block templates ([B1, A, B, A]) in Stage 6 cuts total model parameters by 10.9% (582K weights) and recovers by +10.82 points in a single epoch to 70.92% (-1.84 points vs. unshared control).

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.26177

SpatialScout-V2: Can VLM Agents Actively Explore Real-World 3D Scenes and Localize Objects?

Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Xu, Yifu Yuan, Kun Liang, Chenming Tang, Meiyi Qiang 等 11 位作者

原文摘要

Spatial intelligence requires agents to acquire visual evidence and integrate partial observations into coherent three-dimensional representations. We introduce SpatialScout-V2, which extends SpatialScout's active mapping task from simulation to real residential scenes through three advances: real visual observations, preservation of original scene content, and interactive exploration of recorded views. Built from 100 homes in Realsee3D, the benchmark covers 3,171 target objects across 29 categories. Given a fixed target inventory, agents autonomously select recorded viewpoints and viewing directions, integrate calibrated RGB observations, and iteratively estimate and revise object centers within a fixed interaction budget. We evaluate the localization accuracy and completeness of object-center maps using mean IoU, IoU-threshold hit rates, and target coverage. Evaluating seven frontier vision-language models (VLMs), we find that six achieve an all-target mean IoU below 20\%. Even the best-performing model, Claude Opus 5.5, reaches only 22.52\%, with just 18.36\% of targets exceeding an IoU of 0.5. Further analysis shows that broad submission coverage can coexist with limited localization accuracy, while target omissions further reduce overall scores. These results highlight substantial challenges in constructing accurate and complete object-center maps through active exploration of real scenes.

cs.CV

版本更新 · v2arXiv:2611.06837

Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token

Tommy He, Thomas Jiralerspong

原文摘要

Under stochastic decoding, a single context can elicit many different answers from a language model. Characterizing this variation typically requires many expensive autoregressive rollouts, each revealing only one realization. We ask whether the activations produced while reading the context can directly forecast the model's rollout activations. We train context--answer metamodels that map a context activation sequence to point or distribution forecasts of mean-pooled answer activations. We find that (i) the four metamodel families we study forecast mean-pooled answer activations with high fidelity, and the distribution metamodels also capture rollout variability; (ii) performance improves as the training set grows to 500,000 prompts, and the metamodels generalize zero-shot to out-of-domain datasets; (iii) their forecasts retain behavior-predictive signal; and (iv) context activations from Qwen2.5 predict mean-pooled answer activations from Qwen3.5 and Gemma 4, suggesting that activation forecasts can transfer across models. Together, these results suggest that context activation traces can support scalable forecasts of behaviors in LLM answers before the first answer token is generated.

cs.LG · cs.AI

版本更新 · v3arXiv:2506.00508

Higher-Order Functional Networks from Event Time Series

Andrea Civilini, Fabrizio de Vico Fallani, Vito Latora

原文摘要

Inferring relations among the units of a complex system from their activity is a fundamental problem across many fields. Here, we introduce a method to identify functional dependencies of arbitrary order from multivariate event time series. The method maps the data onto a symbolic sequence, and uses a Bayesian framework to extract statistically significant motifs of symbols. These motifs define the hyperedges of a hypergraph, providing a compact representation of higher-order functional dependencies in their original data and enabling their analysis with network-based tools. Applications to neural and social systems reveal nontrivial higher-order dependencies associated with collective brain activity and social behaviour. Our framework thus provides a general approach for uncovering higher-order functional organization directly from event data.

physics.soc-ph · cs.SI · physics.app-ph · physics.data-an

新论文 · v1arXiv:2611.26172

Budget Internalization: Fixed-Budget RLVR Trades Test-Time Scaling for In-Budget Accuracy

Ilia Zavidnyi, Alexander Kovrigin, Arina Puchkova, Kirill Gelvan, Sergey Titov

原文摘要

Reasoning models often become more accurate when they can generate longer answers at test time. This behavior is known as test-time scaling. However, RL with verifiable rewards (RLVR) usually trains them with a fixed rollout cap. We find that this cap changes model behavior, not only training cost. After training, models use few additional tokens beyond the training budget. They outperform the base models near that budget, but their accuracy stops improving and falls below the base model at larger budgets. The rollout cap thus becomes a learned constraint, that limits model's test-time scaling. We call this effect budget internalization. We observe it across Qwen3.5-4B, Gemma4-E2B, and Nemotron-3-Nano-4B and two reasoning training tasks: mathematical reasoning and diverse, procedurally generated problems. This effect also transfers from math training to science and coding tasks. Training-objective level ablations on Qwen3.5-4B show that most changes recover little test-time scaling. Stronger KL regularization and lower training-data truncation preserve more scaling, but stronger KL reduces in-budget accuracy. Forcing an answer on truncated training rollouts largely removes budget internalization, but also removes most of the in-budget gain. SFT on artificially truncated traces reproduces budget internalization, whereas SFT on naturally short traces does not, which shows that the effect is not specific to RL. This result links budget internalization to length-censored post-training rather than to an RL-specific objective term. Thus, a rollout cap does not only control training cost. It can trade low-budget gains for lower performance when additional inference compute is available.

cs.LG · cs.AI

新论文 · v1arXiv:2611.26171

The FrontierOR Challenge: Agentic Algorithm Design for Operations Research

Hai Wang, Bretislav Hajek, Chonghe Jiang, Minwei Kong, Ao Qu, Huatian Gong, Bo Dong, Cynthia Barnhart 等 9 位作者

原文摘要

Operations research (OR) relies on algorithms that experts tailor to each problem: a new routing, scheduling or network design problem can take weeks of specialist work before it is solved well at scale. Large language model (LLM) agents now write, test and improve code, but whether they can design algorithms that scale to realistic instances is open: in the FrontierOR benchmark's one-shot evaluation, the strongest model matches Gurobi, with an objective within 1% of Gurobi's and no slower, on only 39% of the large instances. The FrontierOR Challenge asks teams to build agentic workflows that design, test, and improve algorithms for many optimization problems at once. Stage 1 releases 60 of the benchmark's 180 audited problems, spanning six application categories and five formulation types, in weekly rounds of 15; Stage 2 introduces new problems outside the benchmark, with unseen instances. Two tracks are ranked separately: in the Main track we run the submitted algorithms in a network-isolated sandbox with open-source dependencies only; in the Self-hosted track teams solve the instances on their own machines, with any software, within a timed window. Every solution is checked for feasibility, and a feasible solution scores the ratio of its objective to a frozen known reference, averaged over hidden instances.

cs.AI · math.OC

新论文 · v1arXiv:2611.26167

Planning to Stop: Factored Certification and Terminal Repair for Noncircular Robots

Runtian Zheng, Congpeng Zhang, Ying Liu

原文摘要

Tight-space navigation requires a robot to clear obstacles and stop inside its goal despite uncertainty. We present GeoDiff, a motion-program planner coupling original-goal stopped-set inclusion, witness-guided terminal repair, and factored proof compilation. An exact feasible-translation characterization guides repair; request-local reuse reduces repeated geometric work. We establish conditions for compiler equivalence and reach-and-stop soundness. Across 11,440 floorplan-derived jobs, GeoDiff certifies 61/139 tasks at 5-cm tolerance within 15 s, versus 44/139 for the stop-set baseline. The strongest observed external certificate adapter certifies 13/139 tasks from 119/139 native routes, separating route availability from certification. On tasks derived from public BARN maps, GeoDiff certifies 202/270 at 5-cm tolerance for a Jackal-shaped body, versus 3/270 for the portal baseline. Development analyses distinguish emitter savings from solver coverage, and 1,420 route-tracking episodes characterize the execution interface. These results show how terminal reasoning and proof reuse increase finite-budget certification coverage while preserving the original physical task and goal.

cs.RO

新论文 · v1arXiv:2611.26165

StreamEgo: Streaming Exocentric-to-Egocentric Video Generation

Tianyi Xu, Boyang Lyu, Yunkai Tang, Kairan Ding, Jiahang Li, Weiyu Guo, Yandong Guo, Shuchen Weng 等 9 位作者

原文摘要

Exocentric-to-egocentric (Exo2Ego) video generation transforms third-person recordings into first-person viewpoints, unlocking immersive AR/VR experiences and scalable demonstration synthesis for embodied robotics. Extending it to a streaming setting is expected to further enable live applications. However, existing methods suffer from degraded manipulation regions, overfitting and confinement to fixed-length clips with prohibitive latency. To address these limitations, we present StreamEgo, a real-time framework for unbounded, generalizable Exo2Ego video generation. To resolve intricate manipulation dynamics while supporting the streaming pipeline, a streaming dual-branch prior provides pixel-aligned guidance for translating appearance and skeletal kinematics. We also introduce a region-aware loss curriculum to improve generalization and stabilize multi-objective diffusion training. Furthermore, we distill the model into a chunk-wise autoregressive model, augmented with a region-aware corruption mechanism and a first-chunk curriculum, enabling high-quality, generalizable real-time streaming Exo2Ego generation at 24.3 FPS on a single H100 GPU.

cs.CV

新论文 · v1arXiv:2611.26164

MultiBinder: Preventing Multi-Subject Identity Leakage in Personalized Video Generation

Wei Li, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Xiaoyan Sun, Tao Mei

原文摘要

Personalized video generation faces a significant scalability challenge: as the number of custom subjects increases, existing methods suffer from severe identity leakage and semantic entanglement, resulting in videos with blended attributes and incoherent narratives. We identify that this stems from a lack of explicit binding between textual entity phrases and their corresponding visual patterns prior to fusion in diffusion models. To address this, we propose MultiBinder, a novel framework built on a ``bind-then-narrate'' paradigm. Our approach introduces a two-stage conditioning process before video diffusion. First, Cross-modal Entity Binding devises an entity-aware Q-Former to extract identity-centric features from each subject's reference image and tightly align them with its unique entity phrase, yielding disentangled ``identity tokens.'' Second, a Multimodal Large Language Model (MLLM) acts as a ``narrative director'' in the Narrative-Aware Subject Arrangement stage, capturing the action of each subject from the text prompt and synthesizes contextualized subject features that encapsulate ``who is doing what'' and preserve role-specific distinctions. These features are then injected into a video diffusion model via dedicated conditioning pathways, ensuring precise attribute allocation. Extensive experiments on both general and newly curated multi-subject benchmarks show that MultiBinder significantly outperforms existing methods in multi-subject identity fidelity.

cs.CV

新论文 · v1arXiv:2611.26161

One View, One Action: Spatially Generalizable VLAs through Observation-Aligned Experts and Cross Graph Consistency

Jinxi Liu, Ruifeng Zhai, Hao Liu, Guangrun Wang

原文摘要

Multi-view vision-language-action (VLA) models still face challenges in spatial generalization, particularly under changes in camera viewpoints and robot initial states. These models typically receive action supervision only in the robot base frame, requiring them to implicitly learn the spatial correspondence between observations from each view and base-frame actions. We propose One View, One Action (OVOA-VLA), which learns to predict actions in each view's camera frame, allowing the same physical motion to provide diverse, observation-aligned supervision across views. OVOA-VLA jointly trains a base-frame expert and view-specific action experts, whose robot-state inputs and action targets are expressed in their respective camera frames. Two complementary directed attention graphs model both directions of interaction between the base and view-specific experts, jointly leveraging view-specific action supervision to improve base-frame prediction. Cross Graph Consistency further encourages agreement between the two graphs' base-frame predictions for the same sample. With the same multi-view inputs, the model supports both full and base-only inference. Experiments across multiple simulation benchmarks demonstrate improved manipulation performance and robustness to camera-viewpoint and robot-initialization perturbations. Full and base-only inference achieve average success rates of 88.1% and 85.7% on LIBERO-Plus, respectively. In real-world evaluations, base-only inference raises the average success rates from $π_{0.5}$'s 28.3% to 58.3% across three tasks under spatial distribution shifts.

cs.RO

版本更新 · v2arXiv:2610.38401

Beyond Robustness of Magic: Quantifying Quantum State Convertibility

Satoshi Kanno, Yoshi-aki Shimada

原文摘要

In fault-tolerant quantum computing, magic states provide essential resources for implementing non-Clifford operations. The robustness of magic (RoM) quantifies the magic contained in a quantum state and is closely related to the cost of classical simulation. However, knowing how much magic two states contain is not sufficient to determine whether one can be converted into the other using free operations. In this work, we develop a geometric framework in which RoM is represented as half the distance to the set of free states, and extend this framework to state conversion. We introduce a directed conversion deficiency that measures how far a target state lies from the states freely reachable from a given input. This quantity vanishes exactly when free conversion is possible and, beyond being a mathematically well-defined measure, has an operational interpretation in terms of stabilizer quasiprobability. Furthermore, our framework provides lower bounds on the additional magic states required for conversion that can be strictly stronger than conventional RoM-based bounds. We demonstrate this distinction analytically by constructing a continuous family of mixed single-qubit states with identical RoM for which free conversion is possible in one direction but impossible in the reverse. Our results reveal that the usefulness of magic for quantum state conversion depends not only on its amount but also on the specific transformation being performed.

quant-ph · cs.IT · math.QA

新论文 · v1arXiv:2611.26159

When Foundation Models Disagree: Representational Heterogeneity for Calibrated Uncertainty in Whole-Slide Image Classification

Yekai Shen, Yuqian Wang, Zishun Liao, Rongsheng Wang, Wenting Chen, S. Kevin Zhou, Qingsong Yao

原文摘要

Pathology foundation models supply strong representations for whole-slide image classification, yet the confidence attached to their predictions remains hard to trust. Prevailing uncertainty estimators act within a single feature space and thereby overlook the uncertainty that the choice of foundation-model representation itself induces. This work introduces CALIFUSE, a calibration-oriented framework that fuses several pathology foundation models for the specific purpose of uncertainty estimation. Departing from accuracy-driven fusion, CALIFUSE reads representational heterogeneity across encoders as an explicit confidence cue. Slide-level decision consensus is coupled with chunk-level evidence agreement quantified through Jensen-Shannon divergence, so that both prediction stability and fine-grained evidence consistency inform the estimate. Foundation-model encoders stay frozen. A task-specific nnMIL classifier is still trained for each FM; CALIFUSE then estimates confidence at inference without training an extra fusion module. Evaluated on seven WSI classification tasks under several foundation-model combinations, the framework sharpens calibration, misclassification detection, and selective prediction relative to both the strongest single-encoder baseline and naive ensemble averaging, all while preserving competitive balanced accuracy.

cs.CV · q-bio.QM

新论文 · v1arXiv:2611.26157

NariQ: Sub-3-Bit Quantization for Long-Horizon Agentic Tasks

Doyeob Kim

原文摘要

Long-horizon agentic tasks require a model to call tools over many steps at contexts of 100K tokens or more, yet many low-bit quantization methods are calibrated on short web text and judged on perplexity. This mismatch is costly: existing quantizations of Qwen3.8-27B at or below 3 bits per weight match BF16 on shorter tasks like AIME, yet in published results solve at most 72% as many tasks as BF16 on DeepSWE, a long-horizon agentic benchmark. We propose NariQ, a trellis-coded post-training quantization method that calibrates on tokens generated by the BF16 model in agent sessions. On Qwen3.8-27B, NariQ at 3.0 and 2.5 bits per weight stays level with BF16 on two long-horizon agentic benchmarks, DeepSWE and Terminal Bench, as well as on AIME and RealWorldQA. Our checkpoint at 2.0 bits per weight trails this performance. To our knowledge, these are the first quantizations at or below 3 bits per weight shown to match their full-precision version on long-horizon agentic tasks. We release the files as Qwen3.8-27B-NariQ-GGUF (https://huggingface.co/nari-labs/Qwen3.8-27B-NariQ-GGUF), with inference available through our llama.cpp fork at https://github.com/nari-labs/nari-llama.cpp.

cs.LG

新论文 · v1arXiv:2611.26156

Towards Scale-Up Networking: Challenges and Open Questions

Tingting Xu, Zixun Su, Xinyang Huang, Bowen Liu, Kun Tan, Dong Lin, Hao Wang, Yinben Xia 等 12 位作者

原文摘要

The rapid growth of AI models and the widespread use of distributed training and inference have made inter-accelerator communication a critical system bottleneck. Scale-up fabrics address this bottleneck by combining high per-accelerator bandwidth with low and predictable latency over tightly coupled accelerator domains. However, the appropriate topology, protocol mechanisms, communication semantics, and system integration remain actively debated. We analyze the critical-path communication generated by parallelism strategies and derive the resulting requirements for domain scale, per-accelerator bandwidth, and collective completion latency. We then use these requirements as a framework to examine representative proprietary and open scale-up fabrics, revealing how their physical interconnects, topologies, protocols, and semantics make different trade-offs among performance, scalability, compatibility, and implementation cost. Moreover, based on this analysis and discussions with industry experts, we identify challenges and open problems in physical interconnects and switching, efficient communication, semantics, resource sharing and heterogeneous device interconnection. This paper provides a requirement-driven foundation for analyzing current scale-up fabrics and guiding the design of future systems.

cs.NI · cs.DC

新论文 · v1arXiv:2611.26154

Public-Private Cooperation in the Port of Rotterdam: An Agent-Based Toy Model of Cooperative Efforts Against Cocaine Trafficking

Frederike Oetker, Charlotte Geertman

原文摘要

Cocaine trafficking poses a persistent governance challenge in the Port of Rotterdam (PoR), requiring cooperation between public and private actors. This paper develops an Agent-Based toy Model (ABM) coupled with a Causal Loop Diagram (CLD) to explore interactions between trust, cooperation, competition, pressure, enforcement, and actor skills in public-private cooperation (PPC). Based on empirical data of PPC in the PoR, we explore responses to parameter shocks across different initial configurations. In this model, effectiveness of PPC is strongly state-dependent and measures institutional, relational, behavioral, and resource readiness. The toy model demonstrates that isolated, single-track measures yield limited long-term gains modelled over 5 years due to structural system inertia, whereas coordinated multi-parameter strategies produce substantial improvements. Specifically, combining trust-building, cooperation, and moderate pressure with reduced regulatory enforcement friction raises effectiveness by 25% from a baseline effectiveness, compared to just 13% for an isolated increase in cooperation. Acknowledging the exploratory nature of the model, these findings offer exploratory hypotheses on port security governance. Future work should validate the model against test cases and additional expert input.

cs.MA

新论文 · v1arXiv:2611.26153

Live Migration of Gated DeltaNet Requests: Exact Catch-Up and the Cost of Log Backlog

Hanqing Yu, Jiaqi Yang, Si Wu, Feng Li, Xiuzhen Cheng, Pengfei Hu, Yongbo Yu

原文摘要

Live migration of a streaming Gated DeltaNet (GDN) request requires recovering recurrent state at the correct token boundary on a worker with the same model weights. We adapt snapshots, batched replay, and token catch-up, and design a compact update-log migration path. Exact catch-up preserves native single-token decode and matches the applicable bitwise reference on the tested inputs. We use both a prior-based and a probe-calibrated selector to choose a path for user interruption, source release, or output rate. In 1,350 scheduled pure-GDN trials on two GPU deployments, compact logs achieved the shortest exact handoff gap in all 90 configurations, including 10 winners determined using a replay timeout bound. In the 80 complete configurations, exact catch-up always released the source earliest, while 32-step replay provided the highest output rate when arithmetic differences were allowed. At 10 MB/s, 32-step replay also reduced the median handoff gap from 445--464 ms for logs to about 81 ms across the two deployments. On 40 historical KV-aligned Qwen configurations, retrospective selection reduced the mean gap by 13.9% against the strongest scored simple rule under either numerical contract. We report initial whole-request hybrid results and specify how the joint KV and GDN policy will be evaluated.

cs.DC

版本更新 · v4arXiv:2505.14240

Learning with Local Search MCMC Layers

Germain Vivier-Ardisson, Mathieu Blondel, Axel Parmentier

原文摘要

Integrating combinatorial optimization layers into neural networks has recently attracted significant research interest. However, many existing approaches lack theoretical guarantees or fail to perform adequately when relying on inexact solvers. This is a critical limitation, as many operations research problems are NP-hard, often necessitating the use of neighborhood-based local search heuristics. In this paper, we introduce a principled approach for learning with such inexact solvers. Inspired by the connection between simulated annealing and Metropolis-Hastings, we transform the problem specific neighborhood systems used in local search heuristics into proposal distributions, implementing MCMC on the set of feasible solutions. This allows us to construct differentiable, stochastic combinatorial layers and associated loss functions. Replacing an exact solver with a local search strongly reduces the computational burden of learning on many applications. We demonstrate our approach on a dynamic vehicle routing problem with time windows, binary vector and k-subset prediction tasks, as well as a multi-dimensional knapsack decision-focused learning problem.

cs.LG

版本更新 · v2arXiv:2611.18729

SCALE: Towards Whole-Slide Counterfactual Explanations in Cancer Histopathology

Weiyi Qin, Yingci Liu-Swetz, Shiwei Tan, Yi Wang, Mohammad Alexanderani, Dimitrios Korentzelos, Peizi Li, Soo Yeon Sohn 等 14 位作者

原文摘要

Accurate cancer diagnosis depends on histopathological evaluation, in which tumor morphology drives disease classification and therapeutic decision-making. While deep learning models have demonstrated strong performance in predicting diagnostic and prognostic properties from histopathology images, their clinical adoption remains limited by a lack of interpretability. Unlike conventional medical images where diagnostic findings are spatially localized, histopathological images are characterized by complex textural patterns distributed across the entire whole slide image (WSI), making it difficult to explain model predictions through region-based localization alone. Counterfactual explanations offer a promising alternative by asking "what changes in the image could have altered the model prediction." To achieve this, we propose SCALE, a framework for generating such counterfactual explanations for histopathological DL models. Across nine counterfactual directions spanning multiple cancer types, SCALE generates counterfactual explanations that consistently shift model predictions toward the intended diagnostic target while maintaining biological feasibility. In a blinded review by pathologists, SCALE demonstrated superior morphological plausibility compared to baseline methods (win rate of 91.7%) and robust counterfactual effectiveness (target consistency of 96.7%). These results suggest that SCALE generates morphologically plausible and effective counterfactual explanations that can be applied to improve the interpretability of deep learning models for histopathology.

cs.CV

版本更新 · v3arXiv:2606.02323

Multidimensional Reconciliation in Continuous-Variable QKD: Review, Coding Schemes, and Open-Source Simulation

Lucien Martial, Alexis Rosio, Eleni Diamanti, Adrien Cassagne, Baptiste Gouraud

原文摘要

Continuous-variable quantum key distribution (CV-QKD) requires highly efficient reconciliation techniques to operate at low signal-to-noise ratios and long distances. Multidimensional reconciliation addresses this challenge by transforming the physical Gaussian quantum channel into a virtual binary-input additive white Gaussian noise (BIAWGN) channel, enabling the use of modern errorcorrecting codes. In this work, we review the principles of multidimensional reconciliation, with a particular focus on high-dimensional constructions beyond the algebraic dimensions 1, 2, 4, 8. We describe the construction of the virtual channel, discuss practical coding schemes for reverse reconciliation, and analyse their integration with linear error-correcting codes. We also present an opensource simulation framework, HDirac, implementing multidimensional reconciliation for arbitrary dimensions, and use it to evaluate state-of-the-art LDPC codes. The results highlight key trade-offs between dimension, reconciliation efficiency, and frame error rate, providing practical guidance for CV-QKD system design.

cs.IT · cs.CR · quant-ph

版本更新 · v3arXiv:2607.00978

Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications

Xuying Huang, Sicong Pan, Maren Bennewitz

原文摘要

Privacy-preserving perception is increasingly important for robotic systems operating in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. We study this problem under an RGB-prohibited deployment setting motivated by scene-specific visual information disclosure, where real RGB observations are unavailable during scene acquisition and fusion. To reflect this deployment constraint on existing 3D datasets, we adopt a stricter depth-only evaluation protocol that re-runs scene fusion without RGB and exposes only the resulting depth-derived geometry to the segmentation pipeline. This constraint removes appearance cues that are often critical for open-vocabulary recognition, making depth-only predictions more uncertain and less reliable. To address this challenge, we propose UTTO, a model-agnostic uncertainty-guided test-time optimization framework that uses structured predictive uncertainty as a reliability signal to refine predictions from frozen open-vocabulary 3D backbones. Experiments across ScanNet and Matterport3D demonstrate consistent improvements over multiple depth-only backbones. Privacy recoverability analyses and a real-robot semantic goal grounding case study further support the proposed privacy-constrained setting and applicability.

cs.CV · cs.RO

版本更新 · v2arXiv:2602.01978

SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays

Roel Koopman, Sebastian Otte, Sander Bohté

原文摘要

Neuromorphic hardware implementations of Spiking Neural Networks (SNNs) promise energy-efficient, low-latency AI through sparse, event-driven computation. Yet, training SNNs under fine temporal discretization remains challenging, hindering low-latency responsiveness and the mapping of software-trained SNNs to efficient hardware. In current approaches, spiking neurons are modeled as self-recurrent units, embedded into recurrent networks to maintain state over time, and trained with BPTT or RTRL variants based on surrogate gradients. These methods scale poorly with temporal resolution, while online approximations exhibit instability for long sequences and tend to fail at capturing temporal patterns. To address these limitations, we develop SpikingGamma, an SNN architecture in which neurons maintain a compact bank of smoothed-delay states and communicate through sigma-delta spike-coding. We show that in feedforward networks, SpikingGamma supports direct online error backpropagation through the continuous reconstruction signal, avoiding surrogate gradients through the spike discontinuity. This enables stable learning of temporal patterns with minimal spiking and scales feedforward SNNs to complex tasks and benchmarks with competitive accuracy, all while remaining robust to the temporal resolution of the model. Our approach offers both an alternative to recurrent SNNs trained with surrogate gradients, and a novel route for mapping SNNs to neuromorphic hardware.

cs.NE · cs.LG

新论文 · v1arXiv:2611.26146

A Practical Proprioceptive Data Collection Utility for the Unitree GO1

Jack Anders Smitterberg, Tan Chen

原文摘要

The Unitree Go1 is a widely used platform for legged robotics research, yet collecting proprioceptive data from it is unnecessarily difficult: the Unitree SDK is sparsely documented, and ROS1 (Robot Operating System), the Go1's native middleware, is fully deprecated. We present an open-source graphical utility that enables researchers to reliably record proprioceptive data from the Go1, including joint states, IMU (Inertial Measurement Unit) readings, foot force sensor data, and gyroscope measurements, without requiring ROS expertise. The tool provides a simple GUI (Graphical User Interface) for starting, stopping, and labeling recordings in real time. The contribution of this paper is the collection utility. We characterize the acquisition quality of 51 recordings collected with it, including the achieved sampling rate and repeated samples. As a secondary, deliberately modest check that the data is useful, we train a terrain classifier on it. The results are weak: a Temporal Convolutional Network reaches about 38% accuracy on held-out recordings across ten terrain classes (10% would be chance), and a window-level split that ignores recording boundaries inflates the same measurement to about 99%. We report this as a demonstration that the logged signals carry terrain information, not as a competitive classifier. The utility is designed to lower the barrier to collecting Go1 proprioceptive data without ROS.

cs.RO · cs.CV