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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 04:39 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 05:33 — 2026-11-20 05:33(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:2026-11-20 04:39最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 7,681 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 04:38(北京时间)
版本更新 · v3arXiv:2608.05180

The Nuclear Decision-Making Benchmark: Evaluating Frontier LLM Tendencies in Escalation, Proliferation, Non-Proliferation, and Arms Control Scenarios

Benjamin Jensen, Ian Reynolds, Yasir Atalan, Martin Pollack, Austin Woo, Anna McConkie, Robert Sincero

原文摘要

Large language models (LLMs) are entering defense and national-security workflows. Seven of the nine nuclear-armed states have committed to keeping humans in control of decisions to use nuclear weapons, but LLMs may still shape the assessments and options that reach decision-makers. Scrutinizing that influence calls for evidence about how these models behave on nuclear-policy questions. Such evidence should cover more than crisis escalation and should separate a model's tendencies from artifacts of a single phrasing, ordering, or run; evaluations to date have not focused on these questions. We introduce the Nuclear Decision-Making Benchmark (NDM Bench), a dataset and reproducible framework for testing how the choice of model and the design of a question shape LLMs' answers on nuclear policy. Its 151 scenarios, written by international relations experts, span four domains: nuclear escalation (76), arms control (25), non-proliferation (25), and proliferation (25). Each scenario can be posed with different states in the decision-maker's role and with added framing sentences. Eight frontier LLMs answered every prompt five times, about 380,000 responses in all. Results highlight that models' choices differ by model and domain, and that in escalation, how often they choose a nuclear threat or nuclear use depends on the state being advised and, for some models, the framing. However, agreement across identical runs is often low, with all five runs agreeing on only 43% of escalation prompts. We release the scenarios, the prompts with their answer orders, and the parsed responses, along with documentation of how they were built and recommended practices for evaluations where there is no correct answer to grade against.

cs.CY

版本更新 · v2arXiv:2411.02830

Mixtures of In-Context Learners

Giwon Hong, Emile van Krieken, Edoardo Ponti, Esmeralda S. Whitammer, Pasquale Minervini

原文摘要

In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting the memory. As a solution, we propose Mixtures of In-Context Learners (MoICL), a novel approach to treat subsets of demonstrations as experts and learn a weighting function to merge their output distributions based on a training set. In our experiments, we show performance improvements on 5 out of 7 classification datasets compared to a set of strong baselines (up to +13\% compared to ICL and LENS). Moreover, we enhance the Pareto frontier of ICL by reducing the inference time needed to achieve the same performance with fewer demonstrations. Finally, MoICL is more robust to out-of-domain (up to +11\%), imbalanced (up to +49\%), or noisy demonstrations (up to +38\%) or can filter these out from datasets. Overall, MoICL is a more expressive approach to learning from demonstrations without exhausting the context window or memory.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.24731

HandWorldBench: A Unified Benchmark for Hand-Centric World Models

Zhaolu Wang, Jiacheng Xu, Lihong Wang, Shuqing Wang, Jianjie Fang, Ziyou Wang, Xvyuan Liu, Rongze Tang 等 15 位作者

原文摘要

Recent advances in world models are opening new possibilities for fine-grained embodied tasks, with hand-object interaction offering a particularly demanding setting. Modeling these interactions involves capturing how hand actions change objects and how the resulting states persist over time. Yet systematic evaluation tailored to these hand-centric capabilities remains underdeveloped. To address this gap, we introduce HandWorldBench, a unified benchmark that systematically evaluates hand-centric world models across human hands, simulated dexterous hands, and real dexterous hands along six dimensions: visual quality, hand fidelity, appearance consistency, instruction following, physical consistency, and temporal coherence. To construct the benchmark, we develop a data curation pipeline that extracts hand-object interaction clips and screens them for quality, yielding 20,500 high-quality egocentric clips from over 600 hours of footage. We then manually select 500 clips covering seven task families for evaluation. Benchmarking eleven models under a unified protocol reveals that stronger hand-pose control does not consistently translate into coherent object-state evolution and persistence or robust cross-embodiment performance, with several specialized hand-control models underperforming general-purpose text/image-to-video generators on dexterous-hand tasks.

cs.CV

版本更新 · v3arXiv:2603.18945

A conceptual framework for ideology in online discourse beyond the left and right

Kenneth Joseph, Kim Williams, David Lazer

原文摘要

Computational social science (CSS) has largely operationalized ideology along a single left/right partisan axis when studying online discourse. This approach obscures how people interpret and engage with more specific ideological formations related to race, climate, gender, and other domains. We introduce a framework that instead conceptualizes ideology as a multi-level socio-cognitive concept network and then explain how this conceptual model of ideology can be linked to the study of online discourse. In doing so, our framework clarifies how ideology manifests in discourse alongside related social processes such as framing, and provides an argument for better understanding of when and why we might study multiple concepts, such as values and beliefs, together in one analysis. More broadly, it bridges methods used to study online discourse with ideology theory, enabling richer analyses of social discourse that benefit both fields. Although primarily theoretical, we provide a concrete operationalization of the framework on a sample of data, allowing us to show one example of how it can be used on real data.

cs.CY · cs.CL

版本更新 · v3arXiv:2210.01293

ThinkSum: Probabilistic reasoning over sets using large language models

Batu Ozturkler, Esmeralda S. Whitammer, Zhen Wang, Nebojsa Jojic

原文摘要

Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context (few-shot in-context learning). However, recent studies show that even the more advanced LLMs fail in scenarios that require reasoning over multiple objects or facts and making sequences of logical deductions. We propose a two-stage probabilistic inference paradigm, ThinkSum, which reasons over sets of objects or facts in a structured manner. In the first stage (Think - retrieval of associations), a LLM is queried in parallel over a set of phrases extracted from the prompt or an auxiliary model call. In the second stage (Sum - probabilistic inference or reasoning), the results of these queries are aggregated to make the final prediction. We demonstrate the possibilities and advantages of ThinkSum on the BIG-bench suite of LLM evaluation tasks, achieving improvements over the state of the art using GPT-family models on thirteen difficult tasks, often with far smaller model variants. We also compare and contrast ThinkSum with other proposed modifications to direct prompting of LLMs, such as variants of chain-of-thought prompting. Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs. Overall, our proposed paradigm represents a promising approach for enhancing the reasoning capabilities of LLMs.

cs.CL

新论文 · v1arXiv:2611.24718

Meta-LSQ: A Closed-Form Sobolev Inner Solver for Few-Shot Meta-Learning

Antonin Sulc

原文摘要

Gradient-based meta-learners such as model-agnostic meta-learning (MAML) adapt to a new task with an inner loop of gradient descent that has to be differentiated through, and they meta-learn every network weight. Meta-LSQ instead fits each task with one regularised least-squares solve over a fixed random Fourier basis and meta-learns only three scalars, a bandwidth, a ridge and a derivative weight. Since the derivative of a sinusoid is again a sinusoid, the same solve can also take derivative observations, and the fitted model has exact closed-form derivatives of any order. On 10-shot sinusoid regression Meta-LSQ trains in 14 s and ends with a 5.5 times lower error than a first-order MAML baseline that trains 36 times longer, and a Gaussian-process control suggests that most of this gain comes from sharing one kernel across tasks. In simulated beam tuning at DESY's ARES facility with model derivatives it is slightly more accurate than an ALPaCA-style model and well ahead of gradient descent. Over DESY's full range of target beams, again in simulation and from measurements alone, its best setting has a median error of 7.3 $μ$m, against 14.4 for the published final beams of their reinforcement-learning agent, which has the lower median on their 300 trials of small targets. On real sensor-calibration data a learned prior mean puts it ahead of MAML on two of four targets, but an exact Gaussian process with the same change and an ALPaCA-style model stay more accurate on most targets, and it breaks down on non-smooth targets. On noiseless targets outside the span of the basis, in-sample criteria such as generalised cross-validation choose too small a ridge.

cs.LG · cs.LO

版本更新 · v3arXiv:2110.08294

Coherence boosting: When your pretrained language model is not paying enough attention

Esmeralda S. Whitammer, Zhen Wang, Nebojsa Jojic

原文摘要

Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present coherence boosting, an inference procedure that increases a LM's focus on a long context. We show the benefits of coherence boosting with pretrained models by distributional analyses of generated ordinary text and dialog responses. It is also found that coherence boosting with state-of-the-art models for various zero-shot NLP tasks yields performance gains with no additional training.

cs.CL

新论文 · v1arXiv:2611.24702

Task-Oriented Network Ranging via Joint Graph and Schedule Design

Zijian Zhang, Yuan Shen

原文摘要

Measuring inter-node distances is the basis for network localization, whereas acquiring node positions does not require a fully connected graph of distances. Existing complete-ranging protocols for network localization require every node pair to exchange signals, which prolongs the ranging cycle. In this paper, we propose sparse signal-multiplexing network ranging (S-SM-NR), a task-oriented framework that adapts the transmit-listen schedule to the ranging task required by network localization. First, we establish the S-SM-NR framework by formulating the joint design of the task graph and the transmit-listen schedule. Then, we analyze the minimum round count required by S-SM-NR and establish a connectivity condition for network localization. Subsequently, we develop a closed-form joint design that constructs the sparse task graph and the balanced transmit-listen schedule. In particular, the joint design can achieve the minimum round count under the complete physical connectivity. Finally, simulations show that the proposed S-SM-NR scheme reduces the occupied-round count and improves the localization accuracy by shortening the ranging cycle.

eess.SP · cs.IR · cs.IT · cs.NI · eess.SY

新论文 · v1arXiv:2611.24697

Depth Before Breadth: Reverse-to-Forward Curriculum with Advantage Decomposition for LLM Agent

Siyuan Du, Yuxin Liu, Meng Tang, Haoran Li, Yechao Bai, Feiyang Pan, Jia He

原文摘要

Reinforcement learning (RL) has become a common approach for training large language model (LLM) agents on long-horizon tasks. However, learning from sparse terminal rewards makes credit assignment and exploration difficult. We approach these challenges through a policy-induced capability region, the set of states from which the current policy can reliably complete a task. Near its boundary, an agent may need only a few actions to reach a more solvable state, even when the goal remains distant. This reduces long-horizon learning to two coupled subproblems of reaching that state and completing the task from there. We address them with paired advantages and a progressive reverse-to-forward curriculum. The advantages provide separate signals for reaching more solvable states and completing the task from them, while the curriculum expands the capability region backward along successful reference trajectories and then into off-reference states through on-policy exploration. On ALFWorld and WebShop, our method outperforms competitive agentic RL methods at both model scales, achieving success rates of 90.1%/96.1% and 80.2%/82.6% with Qwen2.5-1.5B/7B-Instruct, respectively.

cs.AI

版本更新 · v5arXiv:2605.14867

REALM: Retrospective Encoder Alignment for LFP Modeling

Peicheng Wu, Zhenyu Bu, Runze Ma, Lin Du

原文摘要

Spike activity has been the dominant neural signal for behavior decoding because its high spatiotemporal resolution supports accurate decoding. However, as intracortical brain-computer interfaces (iBCIs) move toward higher channel counts and wireless operation, the high sampling rates required to record spikes create substantial power and bandwidth demands. Local field potentials (LFPs) offer complementary advantages, including greater long-term stability, lower energy consumption, and lower bandwidth requirements. However, LFP-based decoders often achieve lower accuracy and rely on non-causal architectures that cannot be used directly for real-time deployment. We propose REALM, a retrospective knowledge distillation (RKD) framework for causal LFP behavior decoding. Inspired by offline-to-online distillation in speech recognition, REALM transfers non-causal representational knowledge from a pretrained, multi-session bidirectional LFP teacher to a causal student model. We first pretrain a bidirectional Mamba-2 teacher across multiple recording sessions using continuous masked autoencoding (CMAE), and then distill its representation into a compact causal student using a combined objective of representation alignment and autoencoding. REALM achieves the highest mean accuracy among the compared decoders in both label-free and fine-tuned pipelines, with statistically significant improvements over each baseline, including the state-of-the-art CrossModalDistill. It does so using LFPs alone throughout pretraining, distillation, and decoding, with less than half the parameters of CrossModalDistill's published student and one-tenth of its pretraining time. These results show that a causal LFP-only model can achieve decoding accuracy competitive with a non-causal multi-modal model, offering a practical and scalable approach for next-generation wireless and implantable iBCIs.

cs.LG · cs.AI · q-bio.NC

新论文 · v1arXiv:2611.24681

DrawScore: Evaluating Generated CAD Models against Engineering Drawings

Haorui Chen, Shiteng Lu, Zhanyu Guo, Zaixi Li, Yunhe Ni, Yaosong Du, Yichen Xiang, Xiande Huang 等 9 位作者

原文摘要

Automatic CAD generation is commonly evaluated with volumetric IoU, Chamfer Distance, and surface F-score, which barely penalize local errors that occupy only a small fraction of a part's volume or surface area, such as a misplaced hole or a slot on the wrong face, even though such errors are critical to manufacturing. We formalize these metrics in a unified integral form and show that the weight of a local error decays as the $(k+q)$-th power of its size, where $k$ is the dimension of the integration domain and $q$ is determined by the penalty function. Guided by this analysis, we propose DrawScore, which projects both models into three orthographic views with visible and hidden lines, as in engineering drawings, and applies a saturating penalty along the projected curves, so that the weight of a local error decays only linearly. Controlled experiments confirm the predicted decay orders, and on outputs of existing CAD generation agents, DrawScore exposes errors in outputs that IoU rates as nearly perfect. DrawScore further improves generation as a reinforcement learning reward and, for CAD generation from engineering drawings, serves as a test-time verifier without 3D ground truth or an additional reward model. Our code is available at https://github.com/UESTC-Simon/DrawScore.

cs.CV · cs.SE

版本更新 · v2arXiv:2611.23034

M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation

Nguyen Quang Trung, Hoang Phan, Shuo Sun, Longyin Zhang, AiTi Aw

原文摘要

Multi-Teacher On-Policy Distillation (MOPD) enables a single student to absorb the skills of several domain teachers by learning from its own generated responses. We present Multimodal Model Multi-Teacher On-Policy Distillation Reasoner (M3OPD-Reasoner), a fully open recipe for post-training vision-language models (VLMs) over three reasoning domains: image STEM, image perception, and video. We curate two datasets, M3OPD-SFT-1.35M for supervised fine-tuning (SFT) and M3OPD-RL-193K for reinforcement learning (RL) with verifiable rewards. On these data, we compare post-training recipes that start from Qwen3.5-9B: training one model on the mixed data of all domains (MixSFT and MixRL), and training one teacher per domain with Group Sequence Policy Optimization (GSPO), directly or after an SFT warm-up, and distilling the teachers into one student with MOPD. We evaluate on 21 image STEM, image perception, and video reasoning benchmarks after we decontaminate the training data against them. The comparison establishes MOPD of teachers trained with GSPO directly from Qwen3.5-9B as the best recipe: the student closely matches each teacher on its own domain and is on average above the mixed-training baselines on the same prompts. Since MOPD already merges the domain capabilities that MixRL would otherwise have to learn, its student is a stronger starting point for RL, and we ask whether the same data can carry the model further from there: we add MixRL on top of the MOPD student, on the same prompts and with the same settings, which, to our knowledge, no prior VLM recipe has studied. The same prompts still improve the MOPD student, with no collapse, and give our main model, M3OPD-Reasoner-9B. MOPD and MixRL can therefore work as consecutive stages that get more out of the same data. We release all data, the training code, and the checkpoints of every stage.

cs.CV

新论文 · v1arXiv:2611.24672

Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery

Christian Lange, Joakim Bruslund Haurum, Bingchen Zhao, Oisin Mac Aodha

原文摘要

Widely used category discovery benchmarks have become increasingly saturated and often fail to reflect real-world discovery settings, making long-term evaluation of new methods difficult. We introduce PS-SPLIT, a large-scale fine-grained benchmark for category discovery, motivated by taxonomic splitting: the real-world process by which what was once considered a single species is found to comprise multiple distinct ones. PS-SPLIT contains 79K globally distributed, high-quality, community-collected bird images spanning 771 species, derived from 257 recent real expert-verified taxonomic splits, with associated geographic metadata and full taxonomic hierarchy. The visual differences between categories arising from real taxonomic splits can be very subtle, often requiring significant human expertise to tell apart, making PS-SPLIT a challenging benchmark which we hope will assist in advancing fine-grained category discovery research. Based on taxonomic splitting, we introduce the task of discovery by category splitting, where the goal is to determine which known categories should be subdivided into new finer-grained subcategories. We adapt four generalized category discovery methods to this setting, evaluate existing methods, and show that there is substantial room for future progress.

cs.CV

新论文 · v1arXiv:2611.24650

Self-Rewarded Reinforcement Learning for Better-Structured Medical Explanations in Small Language Models

Prakhar Mishra, Bhavya Yajush Awasthi, Tanuja, Nishant

原文摘要

Small language models (SLMs) can run on commodity hardware and support privacy-preserving, on-premises clinical deployment, but their medical explanations are often short and poorly structured compared with large language models. Recent supervised approaches such as Meerkat transfer chain-of-thought reasoning into 7B-8B backbones, yet their training objective does not directly target the style or organization of the generated rationales. Building on the instruction-tuned Mistral-7B backbone, we investigate whether a lightweight reinforcement learning (RL) step can improve explanation structure without human preference labels.We apply Proximal Policy Optimization (PPO) with LoRA adaptation to 2,000 Meerkat-derived medical prompts, guided by a simple self-supervised reward that favors longer, lexically diverse, and well-punctuated responses while penalizing very short ones. Training for about 170 PPO steps on a single NVIDIA A100 GPU yields a stable increase in the average reward. Quantitative and qualitative comparisons show that the RL-tuned model produces longer, more organized, multi-point explanations while preserving the underlying medical content.We discuss the promise and the limitations of self-rewarded RL for shaping the style of medical explanations.

cs.AI · cs.CL

新论文 · v1arXiv:2611.24646

Conceptual full-vehicle modeling of a modular all-wheel-drive robotic ADS test platform as a foundation for a digital twin architecture

Felix Florian Schwald, Martin Meiners, Michael Viehof, Erik Hultman, Edwin Kamau

原文摘要

This paper presents the development of an initial full-vehicle simulation model of the PixKit modular electric test platform in IPG CarMaker. The objective is to create a physics-based and extendable model structure that can serve as a low-level foundation for future digital twin applications. The reference vehicle is a skateboard chassis combining unconventional vehicle characteristics such as four independent wheel-hub motors and rear axle steering capable of high steering angles. Since complete measurement data of the vehicle is not yet available, the model parameterization is based on a combination of manufacturer documentation, derived values and engineering assumptions. The modeling approach focuses on the system-level integration of the main vehicle subsystems rather than on a fully validated representation. The resulting model was assessed through basic driving scenarios with different steering inputs and configurations. The simulations showed stable model behavior and physically plausible interaction between the subsystems. The all-wheel-drive configuration produced symmetric wheel responses in longitudinal driving, while counter-phase rear axle steering increased the yaw response and reduced the simulated turning circle diameter compared with front axle steering only. The circular driving scenario further indicated bounded roll and slip behavior. Overall, the implemented CarMaker model provides a traceable and functional simulation basis for the PixKit vehicle. It can support future model refinement, calibration with real vehicle data and development with the goal of creating a validated digital twin architecture.

cs.RO

新论文 · v1arXiv:2611.24644

Equal Steps, Unequal Curvature: Where Muon's Update Goes Wrong

Biswa Sengupta, Jinhua Wang, Léo Maxime Brunswic

原文摘要

Muon updates each hidden weight matrix along the polar factor of its momentum, the steepest-descent direction under the spectral norm. That choice fixes two allocations without consulting the loss: every singular direction of the momentum receives the same step, and in a non-square matrix each neuron's step is set by its leverage score. Whether they are good is a question about curvature, which steepest-descent arguments do not answer; we measure it. Using held-out gradients and Hessian-vector products, we decompose Muon's step by singular-value band and by neuron group and compute each group's second-order optimal multiplier. In a 124M-parameter decoder trained on FineWeb-Edu, the multipliers rise monotonically from the top singular directions to the tail: Muon over-steps the high-curvature top of its spectrum. We prove in Lean when such a diagnostic licenses an intervention at Muon's own update norm. On the measured curvature, the criterion predicts, and held-out losses confirm, that moving step length off the top helps mid-training and early in the cooldown, but not at its end. We then test interventions under per-step norm matching, tuned baselines and paired seeds. Orthogonalizing Q, K and V separately rather than as one fused matrix lowers the loss by 0.0250 nats and accounts for all of the gain of block-wise variants. A matmul-only, rotation-equivariant spectral tilt $σ^{-1/4}$ applied in the cooldown lowers the loss of this stronger baseline by a further 0.0120 nats, additively with NorMuon (0.0158 nats together, three seeds; the baseline needs about 4.3% more tokens to match), and by 0.0188 nats at 355M parameters (three seeds). Energy-matched Schatten-1 weight decay adds a further 0.0052 nats. Geometrically principled changes that do not act on the measured miscalibration, namely exact polar factors, steepest-descent input whitening and top-heavy decay, do not help.

cs.LG

新论文 · v1arXiv:2611.24643

AggCLIP: Aggregating CLIP for Zero-Shot Multimodal Anomaly Detection

Zhi Li, Hanyu Wang, Fei Shen, Zhengtao Zhang

原文摘要

Zero-Shot Multimodal Anomaly Detection (ZSMAD) aims to identify both appearance and geometric defects in novel categories without relying on target-specific training data, making it especially valuable in real-world scenarios constrained by data scarcity, privacy concerns, or high annotation costs. While recent approaches successfully adapt vision-language models like CLIP to achieve this open-vocabulary generalization, they still face significant challenges: (i) severe geometric information loss during 3D-to-2D point cloud rendering; (ii) spatially noisy 2D feature maps produced by raw CLIP patch embeddings, compounded by shallow late-stage modality fusion; and (iii) severe cross-modal semantic misalignment due to decoupled processing streams. To address these limitations, we propose AggCLIP, a novel framework that adapts frozen CLIP representations for ZSMAD by explicitly incorporating local geometric structure and visual spatial context. Specifically, to accurately localize fine-grained defects, we design a Geometry-Aware Spatial Aggregation (GSA) module that refines back-projected 3D point features via density-adaptive neighborhood weighting, alongside a Context-Aware Spatial Aggregation (CSA) module that smooths multi-scale 2D patch embeddings using a lightweight trainable adapter. Furthermore, to prevent semantic drift between modalities, we introduce a Dual-Stream Prompt Contrastive (DSPC) loss, which aligns the abstract concepts of normality and abnormality across the point cloud and RGB streams. Extensive experiments demonstrate that the proposed AggCLIP framework achieves state-of-the-art performance on the MVTec 3D-AD and Eyecandies benchmarks under both one-vs-rest and cross-dataset zero-shot settings, notably surpassing the strongest competitive methods by up to 2.9% in pixel-level AUPRO.

cs.CV

版本更新 · v3arXiv:2605.09020

Direct Cartesian Integration vs. Filtered Back Projection: A Note on Direct Discretization and Variance Preservation

Mikhail G. Mozerov

原文摘要

This note compares two reconstruction operators for the parallel-beam inverse Radon problem, each obtained by the most direct discretization of a continuous inversion formula. The first is Filtered Back Projection (FBP), discretized with a sampled ramp filter and no zero-padding or empirical normalization. The second, termed Direct Cartesian Integration (DCI), evaluates the two-dimensional spectrum of the image point-wise on a Cartesian frequency grid by integrating each projection along the corresponding radial direction, using an identity that follows from the Central Slice Theorem and Hermitian symmetry. The comparison is deliberately restricted to these unmodified discretizations: its purpose is to expose properties of the discrete operators themselves, not to rank DCI against engineered FBP implementations. On a set of ten 512 x 512 test images with 800 projections, DCI preserves the standard deviation of the reference image (mean ratio 0.997, mean absolute deviation from unity 0.003) and produces spatially uniform error maps, whereas the direct FBP discretization changes the standard deviation by -38% to +20% depending on the object and exhibits the radially structured "cupping" error. The observation is consistent with the fact that DCI never discretizes the polar Jacobian |omega|, which is the source of the scale distortion in a direct ramp-filter discretization.

cs.CV

新论文 · v1arXiv:2611.24637

Hypnos: A Dual-Phase End-to-End Platform for Scalable Continual Learning at the Edge

Guilherme Guedes, Marco Apolinario Lainez, Charlotte Frenkel

原文摘要

Continual learning (CL) enables neural networks to adapt to non-stationary data streams by mitigating catastrophic forgetting, offering a path to robust, private, and adaptable edge devices. Yet, porting CL to real-world edge devices remains challenging for two reasons: (i) online operation, where sensor data arrives one sample at a time and the device must adapt on-the-fly, and (ii) the low footprint of edge devices, which makes traditional error backpropagation training prohibitive. Inspired by the brain's wake and sleep cycles, the former for rapid adaptation with minimal resources and the latter for long-term consolidation, we introduce Hypnos, an open-source dual-phase platform for efficient CL at the edge. In the wake phase (e.g., daily operation), Hypnos relies on a low-footprint system-on-chip with a RISC-V microcontroller unit (MCU) targeting efficient inference and supporting lightweight gradient-free prototype updates. In the sleep phase (e.g., night-time charging), where wall-plug energy and larger memory budgets are available, a smart charger performs rehearsal-based gradient updates for consolidation. Deployed on a ZCU104 field-programmable gate array (FPGA) and synthesized in a 28-nm process, Hypnos is benchmarked on the CORe50 NICv2-391 protocol. It sets a new state-of-the-art accuracy of 78.6%-81.6% for edge CL systems, with an on-device latency of 7.79s-10.54s per sample depending on activation precision, and requires $3.8\times$ fewer learning steps and $22\times$ less learning compute than quantized latent replay at higher accuracy and comparable latency.

cs.AR · cs.AI · cs.CV

新论文 · v1arXiv:2611.24616

EgoJev: Finding Evidence in Egocentric Video by Reading VLM Decisions

Chunggi Lee, Hanspeter Pfister

原文摘要

Questions about long egocentric video often depend on one brief moment, such as the second a hand puts an object down. A vision-language model (VLM) that sees a few evenly spaced frames usually misses it. Training-free methods rank frames with a separate image-text model or ask the VLM to write a time. In a controlled test, the VLM itself locates the moment better when it chooses among labeled frames, and we read this choice from its output distribution. With the same candidates, this choice lands on the evidence more often than image-text scores or a written time span, and it compares all candidates in one decision. Based on this finding, we propose EgoJev, a training-free frame selector for wearable assistants. EgoJev reads where the evidence is from labeled thumbnails and looks again at the windows it points to. It places its few answer frames at the quantiles of the resulting distribution. One frozen VLM selects, answers and returns the evidence time, with no second model. A wearable device can encode its coarse thumbnails while it records. With Qwen3.5-4B and 8 answer frames, EgoJev raises QAEgo4D accuracy from 51.2% with uniform sampling to 62.0%, and it outperforms recent training-free frame selectors on QAEgo4D and MyEgo. A single-level version runs on a Mac and an iPhone.

cs.CV

新论文 · v1arXiv:2611.24609

Negotiating Control and Accountability among Stakeholders in High-Risk AI Use Cases: Development and Evaluation of the Method ALIGN

Lena Schneider, Daniel Boos, Gudela Grote

原文摘要

Characteristics of Artificial Intelligence (AI) severely restrict human control. This creates new challenges for socio-technical systems design especially in safety-critical domains, where control over risks is essential along with the accountability for any harm caused. Drawing from human factors and AI governance literature, expert interviews and participant observation in a complex high-risk AI use case from the railways, we developed ALIGN, a scenario-based method that supports the governance of and stakeholder involvement in AI development and implementation in three ways: raising awareness for potential accountability-control misalignments in socio-technical systems and their negative consequences, offering a structured approach to assessing the alignment between accountability and control for stakeholders in a given use case, and supporting effective design decisions to mitigate AI risks. We describe the iterative development and evaluation of ALIGN and discuss how this method promotes AI governance by highlighting the relevance of control-accountability alignment throughout the AI life cycle.

cs.HC · cs.AI

版本更新 · v3arXiv:2609.23816

SPLASH: Co-Designing Flash-Aware Sparse Attention with a Virtualized HBM-HBF Hierarchy

Aditya Anirudh Jonnalagadda, Rohan Juneja, Pranav Dangi, Agasthi Haputhanthri, Wenshuo Yue, Aritra Bagchi, Bin Gao, Anurag Agrawal 等 9 位作者

原文摘要

As context lengths, request lifetimes and concurrency grow, the key-value (KV) cache dominates memory usage in large language model (LLM) inference. High-bandwidth memory (HBM), the memory on contemporary GPUs, achieves far higher bandwidth than off-package memory, yet its capacity, bounded by DRAM density, has not kept pace with this demand. High-Bandwidth Flash (HBF), an emerging memory technology, bridges this gap, combining the advanced packaging of HBM with the density of flash to deliver terabyte-scale capacity at HBM-class read bandwidth. Exploiting this capacity for long-context KV caches, however, requires hiding the vastly different physical characteristics of flash from the GPU while keeping decode interactive. We therefore introduce Splash, an architecture that virtualizes HBM and HBF for the KV cache. We architect custom HBM and HBF base dies with novel memory and flash controllers that handle the access semantics and device management of flash. These controllers keep the GPU agnostic of the underlying memory, allowing the HBM-HBF hierarchy to behave as one logical memory for the KV cache. The added capacity of HBF enables long contexts, but dense attention, which reads the entire KV cache for every generated token, cannot keep decode interactive at these lengths. Splash therefore makes sparse attention flash-aware through query-driven address translation, in which the HBF base die resolves each query into the flash addresses of the relevant KV pages and schedules their reads across flash planes. Since the HBF base die holds the location of every page, this translation hides flash from the GPU and balances the selected reads across flash planes, coupling abstraction with performance. Across five models and up to one million tokens, Splash improves per-GPU decode throughput by up to 4.5x over the strongest baseline under a 100 ms latency budget.

cs.AR

新论文 · v1arXiv:2611.24578

BaseRSI: Recursive Self-Improvement of a Base Vision-Language Model via Training-Free Harness Internalization

Mingda Zhang, Yuanhao Dong, Qiang Huang, Rui Qian, Yanjin Li, Zhenyu Liu, Xiao Huang, Zihao Yang 等 11 位作者

原文摘要

Recursive self-improvement (RSI) is moving from the harness of prompts and tools around a base model toward the model itself. However, existing RSI still faces key challenges, including harness-bound gains that stay outside the base model, black-box supervision that reads only the model's outputs, and imprecise edits whose site and strength are fixed in advance. To address these challenges, we propose BaseRSI, a new paradigm of Recursive Harness Internalization: the base model improves its harness, then writes what the harness adds into its own weights through training-free edits, round after round on its own responses. To support this paradigm, we introduce ReGap, a mechanism that supervises every transformer block with the high-dimensional activation difference that the harness makes at that block alone, and updates the block's weights along this signal in a low-dimensional subspace. Building on this mechanism, we further propose ReKey, an algorithm that writes this signal by regression into a few key-value neurons of every block, and measures the site and strength of each edit on the model's own responses. Moreover, the base model fills every role of this recursion with forward passes alone, and its edits, written at different sites, compose in one checkpoint without refitting. Experimental results on ten visual reasoning benchmarks show that BaseRSI consistently improves a base vision-language model both in distribution and on held-out benchmarks. Our code is available at https://github.com/beita6969/BaseRSI.

cs.CV · cs.AI

新论文 · v1arXiv:2611.24576

Late Entry in Looped Language Models

Ziqi Jin, Jiaxi Li, Weiwen Xu, Aixin Sun

原文摘要

Looped language models deepen reasoning at a compact parameter count by iterating a shared layer stack T times per token, turning recurrence depth directly into sequential decoding latency. Conventional early-exit decoding halts after initial passes without cache completion, truncating cached key-value states of past tokens to shallow depth. We study the opposite strategy, late entry, where new tokens skip initial passes and enter directly into the final K < T passes over a deep context cache. Once lightweight fine-tuning resolves hidden-state norm mismatch at the entry boundary, deep cached context substitutes for skipped token-local passes, allowing late entry to outperform matched early exit across model families and pass budgets. To turn this asymmetry into wall-clock speedups without stalling to build deep caches, candidate blocks verify through only the final K passes on the critical path while previously committed tokens complete passes 1 -> T alongside subsequent steps at zero extra serial calls. Projecting these finished T-pass wake states inside the existing output GEMM (Wake verification, governed by logit-margin tolerance tau in [0, inf]) unifies greedy-exact T-pass decoding (tau = 0, matching K = T block decoding within bf16 reduction order), margin-gated verification (tau > 0), and non-rollback lossy late entry (tau = inf) inside a single static CUDA graph. On Ouro-2.6B (T = 4), K = 2 Wake reaches 5.2x greedy-exact speedup at tau = 0 (+26% over K = 4 block decoding on GSM8K) and 6.8x at tau = inf (+16.9 points over trained early exit at matched speed). Scaling test-time recurrence across T in {8, 16, 32, 64} on Huginn-3.5B cuts K = T/4 rollbacks 21.5x with depth, driving greedy-exact (tau = 0) speedups to 6.1x (T = 32) and 8.4x (T = 64, +153% over K = 64 block) and tau = inf speedups to 10.6 to 12.5x.

cs.CL

版本更新 · v3arXiv:2603.17102

Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency

Lucas Bandarkar, Alan Ansell, Trevor Cohn

原文摘要

Modern LLMs continue to exhibit significant variance in behavior across languages, such as being able to recall factual information in some languages but not others. While typically studied as a problem to be mitigated, in this work, we propose leveraging this cross-lingual inconsistency as a tool for interpretability in mixture-of-experts (MoE) LLMs. Our knowledge localization framework contrasts routing for sets of languages where the model correctly recalls information from languages where it fails. This allows us to isolate model components that play a functional role in answering about a piece of knowledge. Our method proceeds in two stages: (1) querying the model with difficult factual questions across a diverse set of languages to generate "success" and "failure" activation buckets and then (2) applying a statistical contrastive analysis to the MoE router logits to identify experts important for knowledge. To validate the necessity of this small number of experts for answering a knowledge question, we deactivate them and re-ask the question. We find that despite only deactivating about 20 out of 6000 experts, the model no longer answers correctly in over 40% of cases. Generally, this method provides a realistic and scalable knowledge localization approach to address increasingly complex LLMs.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.24549

TTL Approximations for a Family of CLOCK-Like Cache Replacement Policies

Yirong Wang, Peter Desnoyers, Benny Van Houdt

原文摘要

While CLOCK-like cache replacement policies are highly appealing in practice due to their frugal memory usage and implementation simplicity, analytical models for their performance remain limited. The difficulty stems from the "eviction hand" itself. As it scans sequentially for an evictee, sparing objects with survival counters along the way, it inherently entangles the state of one cached object with the next. This strong coupling heavily obscures the system's steady state. To address this gap, we introduce a time-to-live (TTL) approximation for a family of eviction policies---which we term CLOCK($K$)---that decouples individual object dynamics using a globally fixed timer. In contrast to the intrinsic coupling induced by assuming a fixed cache capacity, such a TTL proxy yields a tractable matrix-analytic solution for the steady-state miss ratio functions across a broad and highly expressive class of phase-type renewal traffic. Among other benefits, this effectively reduces the analysis per-object to solving a linear system of order $O(Kd)$, where $d$ is the phase dimension. Moreover, our model for CLOCK($K$) recovers the canonical CLOCK when $K=1$ and FIFO when $K=0$, while empirically exhibiting Schur-concavity under the Independent Reference Model (IRM). Finally, we validate the model against a suite of trace-driven simulations.

cs.OS · cs.PF

版本更新 · v4arXiv:2606.02502

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei Zhou

原文摘要

Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands continuous capability expansion, making Multimodal Continual Instruction Tuning (MCIT) essential. Existing methods either update all tasks with a shared parameter set or allocate dedicated modules for each new task. Shared updates force heterogeneous tasks to compete, causing forgetting of learned capabilities. Conversely, isolated expansion prevents interference but severely limits parameter efficiency over long task streams. To address this dilemma, we propose CRAM (Centroid-Routing and Adaptive MoE). Specifically, by isolating task-specific patterns into independent modules, CRAM mitigates catastrophic forgetting across tasks. To further boost parameter efficiency, we utilize adaptive-rank instantiation to identify the capability gap between existing expert capability and new task demands, and dynamically allocate only the necessary parameters. To ensure stable reuse among tasks, centroid-guided routing recognizes and activates existing experts' capabilities, while an orthogonality penalty confines new updates to task-specific directions, preventing re-learning general capability. Extensive experiments across diverse benchmarks demonstrate its superiority over existing methods. Code is available at https://github.com/LAMDA-CL/EMNLP2026-CRAM.

cs.CL

版本更新 · v2arXiv:2609.01209

Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening

Zhilong Song, Heung Law, Lixue Cheng

原文摘要

Generative models and autonomous agents now propose candidate inorganic crystals by the million, yet most screens test little beyond a minimum-distance cutoff and give no chemical reason for failure. For nearly a century, Pauling's rules have served as the main empirical theory of crystal-structure stability, but they remain qualitative and idealized, leading to only 6.5% of known ionic crystals satisfying rules 2--5 simultaneously. Here our agents generate, test and refute two million candidate laws to discover eight Plausibility Rules for Inorganic Structures (PRIS). These laws encode five physical mechanisms: short-range repulsion, ionic contact and packing, electrostatic balance, bond-valence conservation and crystallographic site simplicity. Experimental structures satisfy the PRIS law sets in 82--99% of cases, and the strictest set detects 87.9% of artificially damaged structures, far above the 1.6--3.2% of conventional distance cutoffs. Although derived without synthesis labels, PRIS plausibility is highly linearly correlated with synthesizability, and a continuous PRIS-derived synthesis score (PSS) explainably filters out 83.7% of hard-to-synthesize structures while retaining 80.7% of experimental structures. In an inverse-design task targeting ultra-incompressible crystals, explainable screening by PRIS and PSS cuts the density functional theory (DFT) validation queue by up to 67.3% while retaining 99.2% of the DFT-verified target candidates. Beyond screening, PRIS traces GNoME's low-symmetry excess to artificial element ordering and identifies falsified crystal structures. PRIS moves screening from a pass-or-fail verdict to a chemical reason for failure, showing that autonomous agents can discover, by active refutation, physicochemical laws that guide calculations and experiments.

cond-mat.mtrl-sci · cs.AI

版本更新 · v3arXiv:2606.16624

GA-VINO: A Geometry-Aware Variational Physics-informed Neural Operator for Mindlin-Reissner Plates

Siqi Wang, Daobo Sun, Yizheng Wang, Yilong Zhang, Yabin Jin, Xiaoying Zhuang, Timon Rabczuk

原文摘要

Plate and shell structures are widely used in engineering fields. Rapid response prediction for such structures under complex geometries, heterogeneous materials, and varying loads is important for engineering design, but conventional numerical methods usually require repeated modeling and solution when the physical configuration changes. To address this issue, this study proposes a geometry-aware variational physics-informed neural operator (GA-VINO) for Mindlin-Reissner plates. GA-VINO represents the plate geometry using boundary point clouds and incorporates a material encoder, a load encoder, and a scalar-parameter branch to handle spatially random material fields, spatially varying pressure loads, and sample-level uniform parameters. Through multi-branch point cloud encoding and cross-attention, GA-VINO fuses geometric, material, loading, and query point information, and predicts the transverse deflection and rotations at arbitrary query locations. Unlike conventional data-driven neural operators, GA-VINO requires no labeled solution data during training. Instead, it minimizes a variational physics-informed loss constructed from the discretized total potential energy of the Mindlin-Reissner plate. Compared with grid-based neural operators, GA-VINO directly processes irregular point clouds and allows different physical fields to be discretized on different point sets, avoiding forced interpolation onto a common grid. The method is validated on multiple examples involving different geometries, material fields, and load distributions. The results show that GA-VINO achieves promising accuracy in deflection, rotation, gradient-sensitive, and energy-based metrics, completes full-field inference for new samples within milliseconds, and exhibits promising cross-geometry generalization capability.

cs.AI

版本更新 · v2arXiv:2610.35801

FOCUS: Active Critic Learning for Long-Horizon Language Model Agents

Zhengping Jiang, William Jurayj, Liaoyaqi Wang, Chunsheng Zuo, Anqi Liu, Benjamin Van Durme

原文摘要

Sparse outcome rewards make it difficult for long-horizon language-model agents to assign credit to earlier actions. Learned critics provide value estimates for intermediate states, but these estimates can be inaccurate, while estimating intermediate values with repetitive continuation samples from points within a trajectory incurs substantial costs. To mitigate these issues, we introduce FOCUS, an RL method that uses selective branching to help the critic network learn its value estimator. The rollout controller facilitates active learning for the critic by sampling continuations from states that are expected to most reduce the critic's estimation error. These refined value estimates then score the segment between consecutive states with a TD($λ$) advantage, while the sampled evidence supplies training targets for the critic. FOCUS supports long-horizon agentic reinforcement learning through a modular context-management interface that decouples context management from rollout allocation. Our experiments show that using compaction-induced segment boundaries for value estimation and credit assignment, FOCUS outperforms GRPO and VinePPO with matched per-step generation budgets on legal reasoning, deep search, and code localization benchmarks, improving held-out accuracy at Qwen3.5-9B scale by 7.2 points over the strongest baseline on BrowseComp-Plus (55.4 vs. 48.2) and by 4.1 points on DeonticBench (56.5 vs. 52.4).

cs.LG