跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 22:09 — 2026-11-16 22:09(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

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

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2412.19439

Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design

Yijie Lu, Zhimin Zong, Junjie Zhang, Shenghan Su, Zeyun Zhao, Ziteng Cui, Yan Pu, Jing Lu 等 11 位作者

原文摘要

The evolution of colour vision is captivating, as it reveals the adaptive strategies of extinct species while simultaneously inspiring innovations in modern imaging technology. In this study, we present a simplified model of visual transduction in the retina, introducing a novel opsin layer. We quantify evolutionary pressures by measuring machine vision recognition accuracy on colour images shaped by specific opsins. Building on this, we develop an evolutionary conservation optimisation algorithm to reconstruct the spectral sensitivity of opsins, enabling mutation-driven adaptations to more effectively spot fruits or predators. This model condenses millions of years of evolution into seconds using GPU, providing an experimental framework to test long-standing hypotheses in evolutionary biology, such as vision of early mammals, primate trichromacy from gene duplication, retention of colour blindness, blue-shift of fish rod and multiple rod opsins with bioluminescence. Beyond validating existing paleontological hypotheses, our model further enables speculative explorations of hypothetical species, such as organisms with visual systems adapted to Martian conditions. These constitute our contributions to AI for life science and neuroscience. Besides, the principles derived from these biological studies can translate into practical engineering solutions. In practice, our findings suggest a minimalist yet effective approach to task-specific camera filter design, optimising the spectral response function to meet application-driven demands. Code repository: https://github.com/luyijie-research/PaleVision.

cs.CV

新论文 · v1arXiv:2611.11763

LangDepth: Vision-Language Scene Priors for Semantic Binning and Cross-Domain Monocular Depth Estimation

Reyhaneh Ahani Manghotay, Jie Liang

原文摘要

Monocular depth estimation has advanced through large-scale pretraining and strong visual backbones, yet metric depth remains sensitive to scene-level scale. Indoor rooms and outdoor driving scenes occupy very different depth ranges, but most depth decoders infer this global structure implicitly from visual features. We ask whether scene-level semantic structure can instead act as an upstream prior that shapes the metric output space before dense prediction. We present LangDepth (SemanticBins), a monocular depth architecture that couples strong visual features with a scene-conditioned output space. A frozen CLIP encoder and a learnable bank of scene- and geometry-oriented concept keys convert image features into a compact scene descriptor, without requiring per-image text or an external captioner. A Scene Prior Module (SPM) maps this descriptor to a scene-conditioned metric depth interval, providing a global range anchor before dense decoding. In parallel, a DINOv2-L backbone with a lightweight FPN extracts dense visual features, and a Per-Pixel Assignment Network (PPAN) assigns pixels to the scene-prescribed bin structure. A confidence gate fuses the dense visual estimate with the SPM prior. We train LangDepth jointly on NYU Depth V2 and KITTI under a modest supervised depth budget, without web-scale depth supervision or pseudo-labelled depth data. A single model achieves delta_1 = 0.960 on NYU, 0.960 on KITTI, 0.887 on DIODE indoor, 0.946 on iBims-1, and 0.861 on SUN RGB-D. Beyond aggregate accuracy, the SPM predicts compact indoor ranges and much wider outdoor KITTI ranges, the gate becomes SPM-dominant on outdoor scenes, and perturbing the routed scene context causes large drops on KITTI and iBims-1. These results support scene-conditioned output spaces as a practical and interpretable mechanism for cross-domain monocular depth estimation.

cs.CV

新论文 · v1arXiv:2611.11761

BridgeKV: Large-Model Prefill and Small-Model Decoding for LLM Inference via KV Cache Translation

Payman Behnam, Debopam Sanyal, Pranav Ponnusamy, Kusum Meda Ravi, Pranav Sastry, Mani Chandana Bandaru, Alind Khare, Myungjin Lee 等 9 位作者

原文摘要

LLM inference has two phases with different bottlenecks: LLM prefill runs once per request and is compute-intensive. Decoding repeats for every output token and is limited by memory bandwidth. To address the challenges associated with this issue, different solutions have been proposed. All of these solutions use the same model for both prefill and decode phases. We propose BridgeKV, which uses a larger model for prefill and a smaller model of the same family for decoding. A lightweight KV-stitching module translates the larger model's prompt cache into the smaller model's cache layout. It handles differences in cache shape and representation through learned local layer mixing and separate nonlinear maps for keys and values. With both models frozen, we train the module to align their caches and make the smaller model follow the larger model's next-token predictions. A second training stage adds low-rank adapters when further task adaptation is needed. Across six model pairs and five datasets, BridgeKV outperforms fine-tuned small-model baselines with matched trainable parameter budgets in all 30 settings. It closes up to 80% of the quality gap to using the larger model for both phases. On one A40 GPU, Llama-3.1-Instruct-8B to Llama-3.2-Instruct-1B achieves 3.0X faster requests than the larger model alone, with latency close to the smaller model alone. BridgeKV can improve the hardware and system solutions that separate prefill and decode phases across GPUs. A separate serving simulation models request arrivals, queues, and cache transfer. For Llama-3.1-Instruct-70B to Llama-3.2-Instruct-1B, it predicts up to 33.86X faster requests and 27.5X lower energy use than using the larger model for both prefill and decode phases.

cs.CL

新论文 · v1arXiv:2611.11757

Calibrated Alarm Thresholds for Compact Fire and Smoke Detectors

Vikas Sandireddy

原文摘要

Compact object detectors such as YOLOv8n are a common choice for camera-based fire and smoke detection on low-power devices. These detectors are usually evaluated with box-level metrics such as mean average precision, and their outputs are turned into decisions with a fixed confidence threshold such as 0.25 or 0.5. A fire monitoring system, however, makes one decision per image: raise an alarm or not. In this paper we evaluate two publicly available compact detectors on the D-Fire test set at the image level. We compare three simple rules for turning box detections into one alarm score per image, and we use a split conformal procedure to choose the alarm threshold from held-out images so that the expected fraction of missed fire and smoke images stays below a chosen target. We find that the same fixed threshold leads to very different miss rates for the two detectors, 17.3 and 8.4 percent at a threshold of 0.5, while the calibrated threshold meets miss-rate targets of 10, 5 and 1 percent for both detectors and all three rules. At a 5 percent target, the false alarm rate on images without fire or smoke stays between 1.2 and 3.0 percent. We also find that smoke-only images stay below the target even when the overall target is met, and we describe the main failure cases.

cs.CV · cs.AI

新论文 · v1arXiv:2611.11756

Causal Resolution of Undefined Answers in Datalog with Negation

Ratan Bahadur Thapa

原文摘要

Unstratified negation may leave the answer to a Boolean Datalog query undefined under the well-founded semantics. We study database causality in this setting by asking which fact insertions and deletions realize a prescribed transition and which other changes preserve the observed query answer while making a designated fact pivotal. Such a set of changes to other facts is a contingency for the designated fact and the prescribed transition. Our game representation assigns one shared move to each mutable fact and preserves query values and intervention distances. Pairing source and target certificates characterizes all minimum contingencies for the six transitions among true, false, and undefined. When inserting or deleting a move resolves a draw, a directed tree traces the newly winning and losing positions along alternating paths to the source of that move. For the fixed one-rule win--move program, deciding whether a contingency of size at most $k$ exists is $\mathrm{NP}$-complete for each transition, even on bounded-degree graphs. Computing the minimum size is $\mathrm{FP}^{\mathrm{NP}[\log]}$-complete, and counting minimum contingencies is $\#\mathrm{P}$-hard under polynomial-time Turing reductions. When only one of true and false is reachable, the prime implicants of undefinedness satisfied at the observation cover every undefined state, and their supports induce nonempty subtrees of a common tree, we compute a minimum resolving intervention in polynomial time from the game instance. From the explicit tree and these implicants, we construct an equally large family of disjoint supports, certifying optimality.

cs.DB

新论文 · v1arXiv:2611.11755

Graph-Sparse Distributed Predictive Control for Multi-Robot Motion Planning vianEdge-Consensus ADMM

Josep Borras-Borras, Pablo Segovia, Carlos Ocampo-Martinez

原文摘要

This paper presents a distributed model predictive control (MPC) architecture for collision-avoiding motion planning of planar robots with double-integrator dynamics. To reduce coordination demands, a time-varying predicted conflict graph selects relevant pairwise interactions. The associated collision-avoidance constraints are convexified once per MPC update using warm-start trajectories, yielding a fixed convex quadratic program (QP). The resulting QP is then decomposed using an edge-consensus formulation of the alternating direction method of multipliers (ADMM), enabling parallel robot-local optimization and independent closed-form projections onto separating half-spaces. Execution is selectively supervised by a centralized high-order control barrier function (HOCBF) QP when the distributed candidate does not satisfy the direct-execution conditions. Evaluated in C++ simulations involving 8, 16, and 32 robots, the proposed architecture achieves collision-free execution and substantially improves computational scalability while maintaining task-level performance comparable to a centralized complete-graph baseline.

cs.RO · eess.SY

版本更新 · v4arXiv:2512.00053

Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores

Nikhil Rout, Blaise Tine

原文摘要

Efficient mixed-precision MMA operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source GPGPU Tensor Cores rely on discrete arithmetic units causing high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a configurable mixed-precision fused dot product (FEDP) unit microarchitecture implemented as part of the open-source RISC-V Vortex GPGPU's Tensor Core Unit extension. It supports low-precision multiplication in TF32, FP16, BF16, FP8, BF8, INT8 and INT4 with FP32/INT32 accumulation, native OCP Microscaling (MX), and sparse lane clock-gating for dynamic power reduction, while matching NVIDIA Tensor Core numerical accuracy. Ten-Four achieves 4-cycle latency at 300 MHz on the AMD Alveo U55C FPGA, delivering 2.7$\times$--7.9$\times$ speedup over Berkeley HardFloat and FPnew at less than 60% the area cost. We further demonstrate its format extensibility by prototyping LNSF4, an NVFP4-variant matching its perplexity with 6.7% fewer LUTs and 11.1% lower dynamic power.

cs.AR

版本更新 · v2arXiv:2610.29061

OccJEPA: Occlusion as Masking for Amodal Video Segmentation

Genpei Zhang, Runmin Jiang, Xingzu Zhan, Yibo Zhong, Ruien Li, Zhou Zhang

原文摘要

Amodal video segmentation asks for the complete mask of an object in every frame, including the parts hidden behind other objects. The best current methods fine-tune video diffusion models to generate these masks; they need a depth network and tens of denoising steps, and their outputs vary from sample to sample. Self-supervised video world models of the JEPA family are pre-trained on a closely related task, predicting the representations of masked space-time regions from the visible ones, yet their predictor is usually discarded after pre-training. We reuse it by treating occlusion as masking. Tokens not covered by the object's visible mask are dropped, the V-JEPA 2.1 predictor is fine-tuned to fill them in, and a lightweight decoder turns all features into amodal masks. The resulting model, OccJEPA (Occlusion-as-masking JEPA), is deterministic and 32x faster per frame than Diffusion-VAS, the diffusion-based state of the art. It is also more accurate on SAIL-VOS (+3.70 occluded-region mIoU over all occluded frames), on TAO-Amodal (+4.00 AP50 on a held-out test split, +4.32 with SAM2-tracked masks) and on Kubric. Controlled experiments trace most of the gain to the predictor's pre-trained weights rather than its capacity, and the predictor helps at every encoder size tested (87M to 1.85B parameters).

cs.CV · cs.LG

新论文 · v1arXiv:2611.11754

Advantage Distillation in Paired-State Quantum Key Distribution

Luis Adrián Lizama-Pérez, José Mauricio López-Romero

原文摘要

We investigate advantage distillation for paired-state Loop-Back quantum key distribution, with a fixed optical station serving a lightweight portable terminal. Alice prepares two polarization-encoded pulses, Bob selects and applies a polarization filter to each pulse, and Alice infers his selections from the returned detection pattern. The proposed advantage-distillation step selects consistent blocks of three two-bit records using two independent public parity checks on a minimal connected graph. The closing edge of a parity polygon is shown to be redundant: any spanning tree of the same vertices has the same acceptance set. We derive exact acceptance probabilities, residual-error laws, and retention rates. Under independent bit errors, the three-record filter reduces the leading error term from e to e^2, while its cost in discarded records and public information is accounted for explicitly. A modular security theorem bounds the additional guessing advantage available to an adversary after syndrome disclosure and block acceptance, including arbitrary quantum side information. We also evaluate a specified single-photon passive-tap optical channel, obtaining a positive conditional entropy bound and exact accepted-block security quantities. This parity-based advantage-distillation step detects discrepancies by postselection; it does not correct individual errors and is intended to precede conventional reconciliation. The architecture suggests two further directions: hybrid filtering and reconciliation, and key establishment between portable users accessing a shared quantum station.

quant-ph · cs.CR

新论文 · v1arXiv:2611.11753

SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging

Seungki Hong, Zhishuai Zhang, Taekwang Jang

原文摘要

Video snapshot compressive imaging (SCI) recovers multiple frames from one spatiotemporally coded measurement. This paper proposes SpinSCI, a mask-conditioned Spatial-Temporal Spin Transformer whose Mask-Conditioned Ising Refinement Block (MC-IRB) combines attention logits and sensing information to form signed spin couplings. Finite mean-field updates gate residual feature refinement. Physics-guided initialization and final data consistency incorporate the measurement model. Compared with HiSViT$_9$, SpinSCI achieves average PSNR gains of 0.51 dB, 0.23 dB, and 0.04 dB on small-scale gray, mid-scale color, and large-scale color benchmarks, respectively, with 16.9% fewer parameters, 21.0-21.6% fewer FLOPs, 17.1-49.9% lower latency, and 62.3-63.3% lower peak memory. Relative to DU-9stg, average PSNR differs by at most 0.13 dB across these benchmarks, with 28.2-28.7% fewer FLOPs, 64.6-71.7% lower inference latency, and 30.1-35.0% lower peak memory. Qualitative comparisons on the real benchmark further show recovery of fine details and textures. Code and reference checkpoints are available at https://github.com/skethz/SpinSCI.

cs.CV

版本更新 · v2arXiv:2610.37364HF 社区推荐

EmbeddingGemma 2: Unified and Efficient Multimodal Representations

Henrique Schechter Vera, Sahil Dua, Jovan Andonov, Sara Smoot, Sebastian Russo, Ivan Llanos, Max Matveev, Jae Hyeon Yoo 等 77 位作者

原文摘要

We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplified per-layer embeddings and a multi-stage curriculum with modality and objective progression which ensure strong quality across unimodal, cross-modal, and mixed-modal evaluations. Notably, in comprehensive embedding benchmarks across all modalities, EmbeddingGemma 2 establishes a new Pareto frontier, outperforming both specialist models and models two to twelve times larger. Furthermore, our design offers flexibility for resource-constrained environments, supporting selective modality encoder loading, adjustable vision token budgets, truncatable embedding dimensions, and quantized weights. We present ablations analyzing key decisions and release EmbeddingGemma 2 to promote further research.

cs.LG · cs.CL · cs.CV · cs.SD

版本更新 · v2arXiv:2610.30631

Large language models show systematic failures in incorporating evolving medical knowledge

Min Zeng, Zaifu Zhan, Kai Yu, Rui Zhang

原文摘要

Medical knowledge evolves, yet whether large language models (LLMs) faithfully incorporate revisions into clinical recommendations remains unclear. We introduce ChronoEvo, comprising 1,709 recommendation-level revisions across 12 forms of medical knowledge change and 275 guideline lineages, to distinguish recognition of revised guidance from its full incorporation. With updated guideline evidence explicitly provided, revision recognition exceeded full incorporation across 14 models, with a 20.1-percentage-point gap in the strongest model. For Qwen3-4B, 90.8% of responses recognized revisions, 80.2% were clinically correct, and 58.5% fully incorporated them, yielding a 32.3-percentage-point gap. Two clinicians' adjudicated assessment of 300 responses yielded a 40.3-percentage-point gap in this enriched validation sample; 61 of 144 responses with incomplete incorporation were clinically incorrect. Prompting Qwen3-4B to prioritize revised evidence reduced outdated-content retention and improved clinical correctness without significantly improving full incorporation. These findings identify faithful incorporation of revised guidance as a distinct challenge for clinical LLM reliability.

cs.AI

新论文 · v1arXiv:2611.11752

Spectral Rank and Step-Direction Dynamics in Language-Model Post-Training

Khurram Khalil, Khaza Anuarul Hoque

原文摘要

Language-model post-training modifies weights through cumulative updates and successive displacements, yet existing studies report seemingly conflicting spectral properties: nearly full-rank updates and low stable-rank changes. We show these observations are compatible and characterize update directions during training. For singular values following $σ_i \propto i^{-α}$ with $0 < α\leq 1/2$, we prove that stable rank becomes negligible relative to fixed-energy rank as dimension increases. Full singular value decompositions of selected OLMo-2-7B updates confirm this separation: three proximal policy optimization (PPO) attention updates have stable ranks of 9.6-18.3 but require 532-1,222 singular components to capture 80% of their energy. We next compute consecutive checkpoint-displacement cosines from full-model inner products. Across nine publicly released reinforcement learning from verifiable rewards (RLVR) stages, all 131 adjacent pairs have negative cosines on their native checkpoint grids, including PPO and Group Relative Policy Optimization (GRPO) trajectories. Supervised fine-tuning comparisons across four model families show configuration-dependent alignment, including negative late-training cosines for Mistral and FP32 Llama. Finally, a controlled OLMo-2-1B study with three paired seeds and a 2,048-token response cap compares group-relative advantages against a learned critic with generalized advantage estimation (GAE). At matched 60-rollout windows, late-training mean cosines are +0.259 and +0.012, respectively; the paired critic-minus-group difference is -0.247 (seed-level 95% interval [-0.358, -0.137]). These findings distinguish spectral concentration, energy coverage, and trajectory direction, and demonstrate that the advantage system influences directional alignment under matched training conditions.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11751

GeoPilot: Diagnosis-Guided Interventions and Geometric Evaluation for Aerial Reconstruction

Pengyu Yin, Jie Pan, Junxiang Tan, Mengqi Fu, Kun Cheng, Yifan Liu

原文摘要

When a mesh reconstructed from aerial remote-sensing imagery disagrees with reference geometry, deciding what to change requires a diagnosis of the reconstruction process. We present GeoPilot, a workflow that turns diagnostics and prior observations into executable program or camera-configuration interventions. A large language model proposes the change, numerical tools reconstruct the mesh, and an external evaluator measures its geometry under a stated coordinate and reference protocol. The main case tests a shared-intrinsics hypothesis proposed before the comparison. On 224 Metashape-raster development images, shared intrinsics improved all six native-coordinate measures and reduced mean surface-to-reference distance by 7.04%. Reference-assisted alignment fitted and evaluated on separate within-scene checkerboard samples reversed the mean-distance ranking, limiting that gain to native-frame delivery. A separate matched comparison on publisher-undistorted images favored fixed published cameras on all six measures, reducing mean distance by 12.11%; the cameras retain upstream image and laser-scanning adjustment information. With one reconstruction per configuration, these comparisons provide conditional evidence for camera handling. Three end-to-end runs each delivered a mesh and six-metric evaluation from all 327 images of a second development scene.

cs.CV

新论文 · v1arXiv:2611.13009

Instance-preserving graded semantic reporting for surgical action triplets

Yanchong Xue, Wanting Zhang, Lingtao Yu, Guochao Zhang

原文摘要

Complete-or-reject reporting of surgical action triplets can discard a correctly identified instrument and action when the target is uncertain. We introduce instance-preserving graded semantic reporting, which separates instance selection from the choice of semantic detail. Each selected instance retains its predicted mask and labels while hierarchical correctness scores guide instrument (I), instrument-verb (IV), or complete instrument-verb-target (IVT) reporting. The utility-increment rule DELTA weighs the expected gain from finer reporting against its error cost. We compare three decision rules on 5,641 test frames from eight surgical videos using fixed predictions and scores. At the 10% development calibration target, DELTA retains correct partial reports for 80.0% of candidates rejected by a matched complete-or-reject baseline (5,329/6,662). Adding IV increases source-normalized weighted correct-report yield by 19.13 to 23.13 per 100 frames across all three rules relative to separately recalibrated I/IVT controls. Weighted reporting risk changes by -0.77 to +1.01 percentage points, with complete correct-triplet counts unchanged or reduced. Graded reporting makes partial surgical predictions available as localized descriptions, with an explicit trade-off between report utility and completeness.

cs.CV

版本更新 · v2arXiv:2606.03180

GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations

Jonggwon Park, Seongeun Lee, Junhyun Park, Hannah Yun, Hyunwoong Kim, Sohyun Jeong, Hyewon Kang, Byungmu Yoon 等 9 位作者

原文摘要

Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows. However, this pairing reveals a mismatch in scale: each finding occupies only a small region of the image, yet supervision is provided only at the global image-report level. This poses a central challenge: prior approaches spread weight densely across all patches rather than concentrating on the sparse subset relevant to a given query. To address this, we present GLINT (Gated Language-Image alignmeNT), a framework that models this sparse correspondence. On the alignment side, we introduce Sparsely Gated Alignment, a novel architecture in which a sigmoid gate over a separate gate embedding space activates only the patches relevant to each textual query, yielding sparsity. On the representation side, we add Dense Feature Regularization, which anchors the trainable encoder's intermediate features to a frozen self-supervised learning (SSL) teacher, preserving the fine-grained patch features that the gate relies on. The same recipe applies to both 2D chest X-ray (CXR) and 3D chest computed tomography (CT), built with DINOv3 and V-JEPA 2.1, respectively. GLINT enables zero-shot classification, grounding, and segmentation from free-text queries, and to our knowledge is the first to demonstrate zero-shot segmentation on 3D CT volumes without mask supervision. Notably, the most pronounced gains arise on zero-shot grounding and segmentation, where sparse, query-specific localization is required, consistent with our design intent. In downstream evaluation, GLINT outperforms both SSL encoders and medical VLMs on classification, report generation, and segmentation. Code is available at https://github.com/deepnoid-ai/GLINT.

cs.CV · cs.CL · cs.LG

新论文 · v1arXiv:2611.11747

Bounds and Constructions for Optimal Wide-Gap Frequency Hopping Sequences

Jiwen Zhang, Haitao Cao

原文摘要

In a frequency-hopping (FH) system, to reduce interference to the received signal, each user's frequency hopping sequence (FHS) shall have wide-gap property. In this paper, we update the upper bounds on the minimum gaps of optimal uniform wide-gap frequency hopping sequences (WGFHS) with parameters $(v,s,λ;e)$ where $v=ks, k\ge 3, λ=k$ and $s\ge k(k-1)+1$ is odd. We completely prove the existence of such WGFHSs for $k\le 3$.

cs.IT

新论文 · v1arXiv:2611.11745

Reproducible quantum clustering for single-cell transcriptome atlases

Henry Han

原文摘要

Current single-cell clustering pipelines discard most genes and can yield inconsistent clusters across random seeds. We introduce KQE-2, a training-free hybrid quantum-classical framework for reproducible whole-transcriptome clustering. KQE-2 maps cells into entanglement-free quantum states, enabling exact feature evaluation on classical hardware and direct checks on a quantum processor. Theoretically, we prove that removing entanglement is necessary and sufficient to bound single-qubit feature variance locally. Practically, while retraining scVI shifted 14% of cells and altered rare-type markers and drug targets, KQE-2 delivered identical biology across runs. On standard highly variable genes, the quantum encoding alone raised accuracy on a developing cortex from 0.61 to 0.79. KQE-2 scales to 11.4 million nuclei on one server, outperforming the compared methods on eight of ten complete atlases (and within the best method's run-to-run range on two), and leads on six even under standard downstream clustering.

cs.AI · q-bio.GN · q-bio.QM

新论文 · v1arXiv:2611.11744

Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo

Jiajun Liang, Linxuan Wang, Guang Lin, Qifan Song

原文摘要

This work proposes the Adaptive Federated Hamiltonian Monte Carlo (AFHMC) for Bayesian federated learning (FL) tasks. The prior work on HMC applications for FL achieves $O(\sqrt{d}/ε)$ communication cost under log-convex distributions, already demonstrating its advantage over the Langevin dynamic-based counterpart. Based on a refined analysis, this paper further reveals the benefit of HMC for the FL regime by incorporating a control mechanism for local node shifts. We prove that AFHMC at most requires $O(\{d/ε^2\}^{1/3})$ communication cost up to a logarithmic term, which is significantly better than the existing results. Moreover, the proposed method adapts to client heterogeneity. Under low-heterogeneity settings (i.e., the target sampling precision $ε^2$ is higher than the heterogeneity level), the communication rate of AFHMC can be as good as $O(\log(d/ε^2))$, resembling the communication costs for FL optimization tools. To the best of our knowledge, this provides the first logarithmic communication complexity result for federated sampling, even though it requires low heterogeneity. Numerically, we also justify AFHMC's advantage under the low-heterogeneity regime. Our code is available at https://github.com/laaaarrywang/Adaptive-Federated-HMC

stat.ML · cs.LG

版本更新 · v3arXiv:2512.00727

Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learning

Sizhe Wei, Xulin Chen, Fengze Xie, Garrett Ethan Katz, Zhenyu Gan, Lu Gan

原文摘要

Reinforcement learning has enabled impressive locomotion skills on articulated robots, but common policy representations remain only weakly aligned with robot physics. Generic networks ignore kinematic structure, while graph-based policies encode connectivity without specifying how physical quantities transform across symmetric body parts. We introduce a morphological symmetry graph representation for locomotion policy learning, instantiated as MS-PPO with PPO on Go2 and MS-SAC with FastSAC on G1. Starting from the robot's topological graph, our representation explicitly incorporates the permutations and sign changes induced by morphological symmetry on observations and actions, yielding a graph actor with an equivariant action mean and an invariant critic. We evaluate the representation on Unitree Go2 command tracking and asymmetric joint-failure tasks, and on Unitree G1 29-DoF whole-body locomotion, including zero-shot sim-to-real deployment. Our approach achieves the lowest tracking errors in both simulation and hardware, and the highest mean simulation returns across all three joint-failure types on Go2 among the evaluated baselines. On Go2, MS-PPO uses only 34.6% of the parameters of the PPO baseline. These results support the effectiveness of jointly encoding topology and morphological symmetry across robot embodiments and learning frameworks.

cs.RO

新论文 · v1arXiv:2611.11741

Silinx: An Open, Browser-Based HDL Design Platform for Teaching Digital Systems on FPGA Boards

Pedro Malo

原文摘要

Many digital systems courses teach on FPGA boards whose vendor tool is no longer maintained: the Digilent Basys2 and Nexys2 (Xilinx Spartan-3E) and Nexys3 and Atlys (Spartan-6) need Xilinx ISE 14.7, discontinued since 2013 and hard to install on the computers and tablets students use today. The author presents Silinx, a free (AGPL-3.0) HDL design platform for teaching that keeps ISE's Project Navigator workflow but runs in a web browser with nothing to install. A module can be written in VHDL or Verilog, in C or C++ through Silinx HLS, which is compatible with AMD's Vitis HLS and passes all 73 of its introductory examples, or drawn as a schematic, an ASM chart, a state diagram, a Boolean function with its Karnaugh map, or a Petri net, from which its HDL is generated. Designs are checked with explanations written for beginners, simulated, run on an emulated board, built, and programmed onto a real board over WebUSB. The implementation flow is open and runs in the browser: Yosys and nextpnr compiled to WebAssembly, with Silinx's own device data, timing model and bitstream writer for the Spartan-3E and Spartan-6, built by black-box observation of ISE's documented tools; Lattice iCE40 boards use the existing open iCE40 tools, and further families are planned. ISE is the oracle: Silinx's bitstreams are byte-identical to those ISE writes for the same placed and routed design, and pass ISE's design rule check. Against ISE at the same optimization goal, the open flow uses 15% fewer slices with 14% shorter critical paths when optimizing for area, and 21% fewer slices with 8% shorter critical paths when optimizing for speed (geometric means over 45 open-source designs built by both flows). The author also describes how the platform was developed with AI coding agents under test-first project rules.

cs.CY · cs.AI · cs.AR · cs.SE · eess.SY

新论文 · v1arXiv:2611.11740

Creative Priming: Decoupling Process from Product to Escape the Creative Paradox

Alon Albalak, Sebastian Gabriel, David B. D'Ambrosio, Joel Lehman, Kenneth O. Stanley

原文摘要

Many of the most consequential advances promised by AI, from curing diseases and inventing new technologies to formulating new scientific theories, are fundamentally creative acts. Yet creativity is uniquely difficult to learn because it faces a creative paradox: learning to repeat past examples of creative success makes those specific examples more likely to recur, inhibiting the very creativity desired. This work argues that creativity is better modeled as an explicit process rather than as a property of individual artifacts, and proposes to learn the underlying generative principles behind the creative process. In particular, to escape the paradox, we introduce creative priming (CP), wherein a trained priming model generates a prompt-specific primer that assists a response model in being creative, explicitly decoupling the creative process from response generation. The priming model learns through GRPO, rewarding primers that lead to responses that are novel, high-quality, and diverse, thereby reinforcing the process that yields creative responses without reinforcing any specific response.

cs.AI · cs.CL

新论文 · v1arXiv:2611.11739

Why Kubernetes Cannot Contain a Full Lazy-Pulling Cache: Two Impossibility Results and a Bounded, Honest Design for Model Serving

Georgii Kliukovkin

原文摘要

Lazy container-image pulling makes cold starts of autoscaled model-serving fleets on Kubernetes nearly independent of model size, but it moves the model's bytes into a node-level cache that the platform neither bounds nor accounts for. This article establishes, by experiment, two impossibility results for that cache. A monitoring-side remedy cannot catch its failure: a sentinel readiness probe stays green while 272 of 280 files are unreadable. A platform-side remedy cannot contain it: kubelet, given full disk-pressure visibility, frees 0 bytes and evicts 26 bystander pods, because its reclamation actuator is keyed to an accounting that does not know the cache exists. The article then eliminates the failure class inside the component that owns the bytes, with no change to kubelet or the container runtime interface, by two design rules: a byte budget whose pressure signal is keyed to filesystem truth, so that a never-blocking, lossy accounting still enforces a hard bound (held against about 301,000 dropped updates), and pass-through semantics under which a failed cache write never becomes a failed read, with the coupling traced to a single io.MultiWriter. Across six pre-specified campaigns on AWS, upstream stargz-snapshotter fails 273 of 280 model files at 90% cache pre-fill; the proposed system reads all 150.3 GB with zero errors at +18.5% completion cost and holds the budget under a live read, co-tenancy, and a three-node fleet. A source audit shows the missing bound generalizes to SOCI and Nydus. The implementation is open source and has been proposed upstream.

cs.DC · cs.OS · cs.PF

新论文 · v1arXiv:2611.11738

Dense Flow from Adaptive Correspondence

Cheng-Lin Hsieh, Stella X. Yu

原文摘要

Optical flow requires reliable matching from sufficient visual context and precise motion at every pixel. Existing methods such as WAFT match and estimate flow on the same coarse grids, then recover dense flow through learned upsampling, without explicitly linking visual support for matching to dense flow reconstruction. Our key insight is that dense pixel-level flow does not require equally dense matching. We decouple correspondence scale from flow resolution by adapting the size and shape of spatial supports to image structure for reliable matching, while reusing these supports for precise dense flow reconstruction. We realize this in Flow from Adaptive Token Estimation (FATE), whose token supports expand within coherent regions and contract near motion boundaries. Shared pixel-to-token associations pool features for matching and reconstruct pixel flow from token motions. Flow supervision jointly trains pixel grouping, token matching, and flow estimation without grouping labels, allowing FATE to anticipate which pixels are likely to move together from appearance alone. Trained on FlyingChairs/FlyingThings3D, FATE achieves the highest zero-shot accuracy on Sintel Final and KITTI, a critical setting given scarce real-world flow labels. For visible pixels, FATE improves accuracy within coherent regions, and more near motion boundaries. Its largest gains occur where direct matches are unavailable: Occluded or out-of-frame pixels account for roughly 10% of valid pixels but 50% of WAFT's total error. Experiments show that adaptive correspondence through pixel-to-token grouping enables reliable matching and precise pixel-level flow, improving generalization to unseen real scenes.

cs.CV

新论文 · v1arXiv:2611.13008

An Open Implementation Flow for the Xilinx Spartan-3E and Spartan-6 that Runs in the Browser, Checked Byte for Byte Against ISE

Pedro Malo

原文摘要

The author describes an open implementation flow, from HDL to a programmable bitstream, for the Xilinx Spartan-3E (XC3S100E to XC3S1200E) and Spartan-6 (XC6SLX16, XC6SLX45), devices that only the discontinued ISE 14.7 supports. The flow runs unchanged in a web browser or in Node.js: Yosys and nextpnr compiled to WebAssembly, with nextpnr's Himbaechel framework given Spartan-3E and Spartan-6 architectures generated from Silinx's own device descriptions, bit database and timing model, and Silinx's own bitstream writer. The bit database was built by black-box observation of ISE's documented XDL and bitgen tools, using codeword-batched experiments; the router is given only switches whose bits were measured, and the writer refuses a feature it has not measured. ISE is the oracle: for the same placed and routed design, the bitstream is byte-identical to the one bitgen writes and ISE's DRC is clean. Placement and routing were first done by an in-house annealer and PathFinder router, which nextpnr replaced once it matched them. On 67 open-source designs for the XC3S1200E, compared with ISE at the same optimisation goal (45 designs built by both), the flow uses 15% fewer slices and has 14% shorter critical paths at goal Area, 21% fewer slices and 8% shorter paths at Speed, and 20% fewer slices but 12% longer paths at Fast (geometric means). XST cannot read 15 of the designs. The flow is published as the npm package silinx-fpga (Apache-2.0).

cs.AR · cs.AI · cs.SE · eess.SY

新论文 · v1arXiv:2611.11735

Correctness Metric Matters: NWD-Based Calibration Loss for Tiny Person Detection in UAV Infrared Imagery

Tian Zhang, Zhirong Su

原文摘要

Detection calibration aligns predicted confidence with empirical correctness. Existing calibration losses inherit their correctness definition from box regression, specifically IoU against a hard threshold. We show that this target is geometrically ill-posed for tiny objects in UAV infrared imagery, where persons occupy less than 0.1\% of the image. The same pixel error is penalized more heavily as the target shrinks, so binary prediction calibration (BPC) actively suppresses confidences that should be high. On HIT-UAV, BPC with an IoU target degrades image-level localization-aware ECE (LaECE) from 0.0689 to 0.0761, 0.0649 to 0.0733, and 0.0653 to 0.0682 across Low, Mid, and High signal-to-clutter ratio (SCR) groups. We replace the IoU target with a continuous, scale-invariant normalized Wasserstein distance (NWD). The NWD target reduces LaECE\(_{\mathrm{NWD}}\) relative to BPC+IoU on all three groups (\(p<10^{-7}\)) with mAP neutral (0.9356 vs.\ 0.9347), and an independent center-offset anchor confirms that the gain is a genuine geometric correction. The improvement holds across a broad plateau of calibration weights. The NWD formulation requires no inference-time mapping layer. If a validation-fitted isotonic map is applied on top of it, calibration is lowered further, and the two corrections act on different components of the same error. The metric-level remedy has a measurable boundary. Target-background thermal pairing in the training distribution and detection-level aggregation under per-image detection-count heterogeneity lie outside it. Both are quantified independently of the NWD target.

cs.CV

新论文 · v1arXiv:2611.11734

A Bifurcation-Theoretic Framework for the Controllability of Emergent Intelligent Systems

Hao Li, Shaowen Lu

原文摘要

Real-world intelligent systems must reconcile two demands: the adaptability conferred by emergence and the steerability required for accountable deployment. We show that these demands are governed by two distinct bifurcations on the same object and that, consequently, increased capability does not imply increased controllability. Emergence is a bifurcation of the capability variable $S$, with criterion $Γ:=\mathcal F'(0)>1$ equivalent to the existence of a unique positive stable fixed point of a self-consistency equation, following solely from the concavity of $\mathcal F$. Controllability is a bifurcation of the permission variable $c$, whose dynamics include an erosion term and exhibit a saddle-node fold with hysteresis as the gate criterion $ρ^\ast$ crosses unity. Three quantitative results follow: the critical exponent distinguishes families rather than classifying the transition; the gating-cost bound $K(M)\propto\log(1+M)$ grows with scope, not capability; and the fold threshold is $γ_c\approx4μκ$. Calibrated in both directions, the criteria reproduce the two-dimensional Ising transition, admit two true-feedback order parameters, and reject nine candidate quantities, supporting the conclusion that the order parameter is geometric rather than capability-related. Since permission cannot be endogenized and no deployed system has been measured to satisfy $Γ>1$ and $ρ^\ast>1$ simultaneously, increased capability does not imply controllability.

cs.AI · eess.SY · nlin.AO

版本更新 · v3arXiv:2410.03756

The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability

Judah Goldfeder, Victoria Dean, Zixin Jiang, Xuezheng Wang, Bing dong, Hod Lipson, John Sipple

原文摘要

Commercial buildings account for 17\% of U.S. carbon emissions, with roughly half of that from Heating, Ventilation, and Air Conditioning (HVAC). HVAC devices form a complex thermodynamic system, and while model predictive control and reinforcement learning have been used to optimize control policies, scaling to thousands of buildings remains a significant unsolved challenge. Most current approaches are over-optimized for specific buildings and rely on proprietary data or hard-to-configure simulators. We present the Smart Buildings Control Suite, the first open source interactive HVAC control benchmark with a focus on solutions that generalize across building. It has 3 components: real-world data from 11 buildings over 6 years, a lightweight data-driven simulator, and a modular Physically Informed Neural Network (PINN) building model. The buildings span multiple climates, management systems, and sizes, and both the simulator and PINN easily transfer to new buildings, ensuring solutions using this benchmark are robust to these factors and only reliant on fully scalable building models. This represents a major step towards scaling HVAC optimization from the lab to buildings everywhere. To facilitate use, our benchmark is compatible with the Gym standard, and our data is available at our webpage. Code at https://github.com/google/sbsim

cs.AI · cs.CY · cs.DC · cs.LG · eess.SY

版本更新 · v2arXiv:2511.11885

Flash-Fusion: Fast, Expressive Queries over Sensor Streams with LLMs

Kausar Patherya, Ashutosh Dhekne, Francisco Romero

原文摘要

Pervasive sensor deployments have generated significant interest in IoT data analysis across fields such as healthcare, transportation and urban planning. At the same time, the rise of Large Language Models (LLMs) offer a new tool for exploring IoT data through their expressive, natural language interface. Unfortunately, natural language querying of IoT sensor streams is impractical today: raw telemetry exhausts LLM context windows in fractions of a second at scale, incurs prohibitive per-token costs, and produces hallucinated responses. Existing systems work around these limits with lossy text summarization or unconstrained code synthesis, producing expensive, unverified computations. Multi-step queries compound this problem: logical errors in intermediate operations can derail the final answer. We present Flash-Fusion, an agentic framework for natural-language querying of tabular IoT data. Flash-Fusion identifies which available data fields and supported derivations can answer the user's query, constructs a plan using typed, domain-specific operators, and validates its structure and schema compatibility before executing. Because constructing plans still requires costly LLM reasoning, Flash-Fusion caches validated operator sequences for reuse across compatible queries. A smaller LLM adapts a cached plan's parameters to each query, cutting latency and cost. We evaluate Flash-Fusion across human activity recognition, ECG monitoring, and vehicular telematics, covering direct lookups, multi-step reasoning, predictive tasks, and out-of-scope requests. Flash-Fusion achieves 92.2% query accuracy versus 76.1% for ReAct, the strongest baseline, while completing queries 7x faster and consuming 5x fewer tokens. Flash-Fusion enables users across disciplines to explore IoT data without manually constructing queries.

cs.DC · cs.AI · cs.DB

新论文 · v1arXiv:2611.11733

Can the Remaining Answers Change the Prediction? Worst-Case Stability Checks for Personalized Rating Models

Priyanka Siddappa, Muntaqim Ahmed Raju, Shifat Haider Al Amin, Ruizhe Ma

原文摘要

Missing ratings can overturn a personalized model's current prediction. For completed models with additive response scores, exact worst case bounds check all missing assignments without changing the current predictor. We evaluate this audit retrospectively in two self-triage cohorts, 108 clinicians rating three simulated psychiatric interviews, and 126 counseling demonstrations annotated by ten experts. Under shared random half histories, Fisher adaptation based on observed ratings reduces log loss relative to response frequency by 0.1071 nats in the clinician audit (95% CI [0.0867,0.1261]) and 0.0223 in counseling (95% CI[0.0121,0.0321]). The counseling test excludes target experts and source videos from training. Certification covers 5.4% and 10.5% of targets; fixed width acquisition raises coverage to 13.7% and 28.6% at the same budgets. With weights and responses held fixed, the observed-rating update also has lower loss than an affine partial update while certifying exactly the same evaluated targets. The certificate establishes agreement with the completed model, not correctness or stability at intermediate updates. These rating tasks test the method; clinical usefulness remains untested.

cs.AI · stat.AP