跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 05:29 — 2026-11-09 05:29（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：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
版本更新 · v2arXiv:2611.03412

DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects

Yumou Liu, Mingju Chen, Zhoufutu Wen, Qianyu Yang, Zijie Wang, Sihan Chen, Yeqian Liu, Chenghao Yang 等 24 位作者

原文摘要

LLM agents are judged by what they deliver, and in professional work what gets delivered is a project, not a task. A project pays off only if the whole package holds, and one weak part can limit the value of the rest. Yet existing benchmarks mostly test agents on one task at a time, leaving a gap between the capability we measure and the outcome that makes agents useful. To address this gap, we introduce DeliverBench, which tests whether agents can carry a project from brief to final delivery. Its 11 projects, spanning financial due diligence, legal contract drafting, and drug safety reporting, are reconstructed with 13 domain experts from real materials and chain 150 subtasks through 2-15 rounds of new materials and client feedback. Because no reference outputs are injected, agents inherit their own errors from one task to the next. Expert rubrics then score every checkpoint as well as the final package. Across seven model-harness systems, even the best system scores only 65.0 out of 100 on final delivery and passes 50.0% of subtasks at a 90-point threshold. The failures are often failures of carrying work forward: in one audit project, all seven systems addressed the review findings, but only one preserved traceability. Together, these results suggest that task-level capability does not simply compose into delivery, which also depends on keeping the work coherent as it evolves.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.12309

G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models

Junxian Li, Kai Liu, Zizhong Ding, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang

原文摘要

The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on understanding-side visual token reduction for improving the efficiency of separate-encoder UMMs. While this topic has been widely studied for MLLMs, existing methods typically rely on attention scores, text-image similarity and so on, implicitly assuming that the final objective is discriminative reasoning. This assumption does not hold for UMMs, where understanding-side visual tokens must also preserve the model's capabilities for editing images. We propose G$^2$TR, a generation-guided visual token reduction framework for separate-encoder UMMs. Our key insight is that the generation branch provides a task-agnostic signal for identifying understanding-side visual tokens that are not only semantically relevant but also important for latent-space image reconstruction and generation. G$^2$TR estimates token importance from consistency with VAE latent, performs balanced token selection, and merges redundant tokens into retained representatives to reduce information loss. The method is training-free, plug-and-play, and applied only after the understanding encoding stage, making it compatible with existing UMM inference pipelines. Experiments on image understanding and editing benchmarks show that G$^2$TR substantially reduces visual tokens and prefill computation by 1.94x while maintaining both reasoning accuracy and editing quality, outperforming baselines on almost all benchmarks. Code is at: https://github.com/lijunxian111/G2TR.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05108

From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks?

Jeremy Qin, Ruizhi Deng, Mohamed Osama Ahmed, Frederick Tung, Leo Feng

原文摘要

Autoresearch has shown that agents can autonomously write code, run experiments, and iteratively improve machine learning solutions. Yet most evaluations start a new agent session from scratch for each new problem, making them costly and leaving unclear whether agents can retain and apply prior insights when adapting to new tasks. We introduce CONTINUAL AUTORESEARCH, an open-ended environment that compares persistent and reset instances of the same agent under matched task streams, data, and time budget. Continual AutoResearch covers nine task families, spanning synthetic tasks, symbolic regression, time-series forecasting, and tabular AutoML. Across five frontier agents, we measure first-solution quality, research efficiency, and final held-out performance. To distinguish insight transfer from session continuity, we run a memory ablation that vary what information agents retain from prior tasks. We show that persistent state improves research efficiency of all five agents, allowing them to find stronger solutions sooner. However, these gains do not consistently translate into better final solutions. Overall, our findings suggest that retaining experience and utilizing it effectively are distinct capabilities.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02978

CAREFUL-Bench: Effect-Aware, Judge-Free Evaluation of Multi-Turn LLM Function Calling

Alexander Kovalenko, Artem Redchych

原文摘要

The multi-turn checker of the Berkeley Function Calling Leaderboard (BFCL) checks only the final state of a simulated service, never the calls that produced it. Extra calls cost nothing, no function doc says what a function does, and the scripted user never answers a proposal, so a model that asks before deleting or paying fails the turn; 322 of the 734 reference turns in the base category act destructively without confirmation. We add effect information to BFCL without replacing it. Effect declarations for all 128 functions are inferred by executing each function in BFCL's own simulators and diffing the state; the remaining judgment, which writes are destructive, is made by four annotators, two humans and two language models (Fleiss' kappa = 0.75), and adjudicated. A judge-free replay scorer re-scores any logged BFCL run, reproduces BFCL's results on all 800 reference trajectories, and reports, alongside the official score, unrequested destructive calls, duplicate writes, redundant reads, surplus steps and their token cost. A confirmation-aware protocol adds a deterministic user that answers proposals. On 11 open models the effect-aware score preserves the official ranking (rho = 0.99) but changes the gaps: the leader loses 14.0 points to unrequested destructive calls, and surplus steps account for 2-28% of all input tokens. Effect hints in the function docs produce no measurable change for any of eight models, consistent with their advisory status in the Model Context Protocol. A user that answers recovers up to four points for the models that ask and none for the rest, with every comparison paired on the same conversations. The gains come from clarifying questions rather than requests for permission: of the 712 conversations that require a destructive call, no model completes more than 6 with every such call confirmed, a difference the official score does not record.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05106

Label-Preserving Fourier Domain Adaptation with Generative-AI and Real Style Donors for 3D Mitral Valve Segmentation

Javeria Javed, Ahmed Salim, Muhammad Mahboob Ur Rahman

原文摘要

Accurate segmentation of the mitral valve from three-dimensional transesophageal echocardiography (3D TEE) is severely restricted by the scarcity of publicly available expert- annotated volumetric datasets. To address this critical limitation, we investigated Fourier Domain Adaptation (FDA), utilizing general-purpose generative-AI images (from platforms like Chat- GPT, Google Gemini, and Microsoft MAI) as annotation-free style donors for 3D mitral valve segmentation. We employed a DeepMitral residual U-Net model on the public MVSeg2023 dataset, comparing six conditions over three runs: real-only training, traditional augmentation, FDA with each generative source, and a non-AI FDA control using real-image style donors, plus an optimization-matched real-only control and a \b{eta} sensitivity analysis. Case-level paired testing showed that FDA with these generative sources led to significant reductions in boundary- and surface-related errors across all three donor conditions relative to the primary real-only baseline. However, the impact on the core segmentation metric, Generalized Dice Score (GDS), proved generator-dependent. ChatGPT-FDA showed a significant GDS advantage over the optimization-matched control but not over the primary baseline, and Gemini-FDA showed no significant GDS difference. Notably, only MAI-FDA provided a statistically robust and significant increase in GDS compared to the primary baseline. The \b{eta} sensitivity was not robust across training runs. These findings confirm that FDA remains an important augmentation mechanism. While generative-AI images offer a practical means of acquiring style diversity without new annotations, the non-AI control performed comparably to ChatGPT-FDA, so we do not conclude that this approach is superior to training with real-image donors.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05104

Workload-Static Optical Circuit Switching For Scalable LLM Inference Decode

Maximilian Thürmer, Nicolas Scotto di Perto, Eloise Stein, Natanijel Vasic, Mikaeil Bagherli, Zhenguo Wu, Benjamin Klenk, Holger Fröning 等 9 位作者

原文摘要

LLM inference decode executes fine-grained collectives whose latency directly limits per-user interactivity, yet scale-up fabrics are still built from electronic packet switches designed for training. We observe that, for a given model deployment and parallelization, the communication structure of decode is fixed, and propose workload-static optical circuit switching (OCS): circuits are configured once per deployment, co-designed with model parallelism and with topology-aware collective schedules that turn spare accelerator ports into fewer communication phases or higher bandwidth. We evaluate this design with GXNET, a graph-based workload emulator coupled to analytical and flit-level network models grounded in hardware measurements. In a 576-accelerator scale-up domain serving 5T-parameter MoE models with up to 5M tokens of context, all-OCS fabrics improve interactivity by up to 65% and energy efficiency by up to 119% over 4:1 oversubscribed packet-switched fabrics.

cs.DC · cs.AI · cs.AR · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05443

SurgTransfer: Multi-Step Latent Action Modeling for Action Transfer in Surgical World Model

Saurabh Koju, Love Panta, Deepak Thapa, Rudra P. K. Poudel, Prajwal Ghimire, Angus Watson, Yash Raj Shrestha, Prashnna Kumar Gyawali 等 9 位作者

原文摘要

Surgical world models have the potential to provide intra-operative guidance, accelerate risk-free training and facilitate transfer of expert surgical maneuvers. However, the use of world models for transferring surgical expertise has been largely unexplored. Moreover, recent approaches in this domain have mainly relied on ground truth kinematics actions or expert annotations for specific tasks, limiting their applicability beyond the narrow range of tasks with ground-truth annotations. In contrast, existing works in the natural domain have shown promising results in learning latent actions solely from unlabeled videos and transferring the learned actions across contexts. We observe that this paradigm is short-sighted for the surgical domain, failing to capture the hierarchical and goal-directed structure of surgical procedures. Thus, we propose a novel multi-step action learning framework to learn context-invariant latent actions that are easily transferable across various surgical contexts. We perform extensive experiments on the publicly available datasets, SurgToolLoc-2022 and PitVis-2023, verifying our approach with both quantitative metrics and qualitative evaluation by surgical experts. We have published our code and the implementation details at https://github.com/bhattarailab/Surgical-Vision-World-Model.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05103

Molecular Prior Networks

Pawel Gomoluch, Anthony Bradley

原文摘要

Predicting affinity between small molecules and their protein targets remains one of the central problems in drug discovery. Due to the substantial cost of wet-lab experiments, machine learning models of drug-target affinity are usually trained on relatively small datasets, ranging from tens to hundreds of molecules. Given the inherent difficulty of generalization between different targets and chemical series, existing datasets of protein-ligand affinities are typically not used for new projects. At the same time, tabular foundation models, including Prior-data Fitted Networks, have recently shown how transformers can be used to solve machine learning problems in a single forward pass of the network, after being trained over a large corpus of, typically, synthetic datasets. Inspired by that line of work, we propose a novel affinity modelling approach, in which the labels of the query molecules are predicted from the labelled support molecules in a single forward pass of a transformer model. The model is trained on thousands of existing affinity datasets, enabling it to capture the general patterns of molecular activity across different targets, chemical series and dataset sizes. For the smallest support sets, our model matches the state of the art on the regression variant of the FS-Mol benchmark, while being faster than existing methods, thanks to the lack of task-specific training. A comparison against a reduced variant of our architecture, which amounts to kernel regression in a meta-learned feature space, shows that the predictive performance of the transformer model is only partially explained by simple molecular similarity.

cs.LG · cs.AI · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05102

Characterizing the vertical continuity of fuel strata based on TLS point clouds Gaussian decomposition and overlap metrics

Jesús Torralba, Luis Á. Ruiz, Pablo Crespo-Peremarch, Marina Simó-Martí, Juan Pedro Carbonell-Rivera

原文摘要

Vertical forest structure influences fire behavior by regulating understory-to-canopy fuel connectivity, yet operational fuel-type models represent this complexity through discrete classes that only indirectly capture vertical continuity. High-density point clouds offer an opportunity to characterize vertical fuel connectivity in a more explicit and continuous manner, but specific methodological approaches are still required. We applied Gaussian decomposition to vertical height profiles derived from terrestrial laser scanning (TLS) point clouds across 25 permanent forest plots to characterize geometric vertical fuel continuity. A multiscale analysis spanning from the plot scale to ~0.5 $m^2$ units was used to evaluate geometric, probabilistic, and overlap metrics for characterizing fuel strata. The method reproduced the vertical transition between shrub and tree strata, with median Pearson correlations ranging from 0.83 to 0.96 across analysis levels. Probability density overlap metrics and separability indicators, such as the Jeffries-Matusita distance, provided complementary descriptors of vertical continuity. Intermediate spatial scales (3-6 m cells) provided a useful compromise between spatial detail and the consistent representation of shrub-canopy interaction patterns. Finer scales increased variability due to point density reduction and profile irregularity, and low mean squared error values were found insufficient as sole performance indicators. Gaussian decomposition applied to TLS point clouds enables explicit quantification of vertical fuel continuity, a limitation of current discrete classification systems. Continuous vertical connectivity metrics derived from this approach offer a pathway for improving ladder fuel characterization and strengthening decision-making support in wildfire risk assessment.

cs.CV · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05099

Dual-VaDE: Efficient and Robust Prototype Learning via Variational Dual-Domain Mixture Priors

Wugeng Zheng, Song Wang, Jian Wang

原文摘要

In this paper, we propose Dual-VaDE, an unsupervised generative framework for learning interpretable anatomical prototypes from unlabeled medical images. In contrast to previous variational methods that rely on a single spatial latent code, which often entangles global geometry with local textures and fails to capture their cross-domain dependencies, Dual-VaDE introduces a dual-domain Gaussian mixture prior that explicitly couples spatial anatomy with phase-preserving Fourier spectral representations. We derive an exact, closed-form variational lower bound that fuses this joint prior into the decoder and optimizes the entire network end-to-end via an alternating EM formulation, avoiding heuristic two-stage clustering while ensuring superior training stability and robustness. Evaluated on OASIS-3 brain MRI, Dual-VaDE delivers substantially sharper and more plausible prototypes, achieves superior cluster separation with improvements of up to 94% over spatial-only baselines, exhibits markedly reduced variance across random seeds, and incurs negligible inference overhead (0.28 ms per image).

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05097

The Platonic Brain: Representational Convergence in EEG Foundation Models

Nicolas Waehner, Enzo Tagliazucchi, Jacobo Sitt, Demian Wassermann, Giovanni Franco Gabriel Marraffini, Trinidad Borrell

原文摘要

The Platonic Representation Hypothesis (PRH) predicts that artificial neural networks converge on shared representations as scale and performance increase. We test whether these predictions hold for representations of the human brain with EEG foundation models. Using EEG recordings from six participants watching a television series, together with aligned visual and language content, we tested whether EEG foundation-model representations converge within and across modalities as their embeddings become better at decoding an informative set of EEG markers. We found that EEG models with greater decodability showed stronger cross-family alignment in both local neighbourhood similarity and global structure, not consistently increasing with model parameter count. Cross-modal convergence was modality and metric dependent: greater EEG decodability was associated with stronger global alignment to language, but not consistently to vision models, while local alignment showed no consistent association. This dissociation may reflect local sensitivity to low-level sensory features, whereas global geometry may capture weaker shared semantic structure.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05093

LoopQ: Fair, Closed-Loop Evaluation of Quantized Vision-Language-Action Models

Syed Umer Bukhari, Magnus Almgren, Ahmed Ali-Eldin

原文摘要

Post-training quantization (PTQ) for vision-language-action (VLA) models promises smaller and faster VLA deployments. However, when analyzing existing VLA quantization works, we realised that it is hard to reason about the performance of the suggested quantization method compared to existing, similar, or in many cases, simpler PTQ methods. We present LoopQ, a closed-loop benchmark that compares multiple quantization policies on the same checkpoint, layers and engine, varying only the method and the kernels. We evaluate RTN, AWQ, GPTQ, ActQuant and QuantVLA on four VLAs with more than 180,000 episodes of LIBERO and LIBERO-plus, compare against QVLA's reported results on the same layers, and benchmark whether the four public VLA-quantization releases can be reproduced. We benchmark the methods on an NVIDIA H100, an L4, and a Jetson AGX Thor. Our results show that while quantization reliably saves memory, 2-3x for real low-bit models, VLA-specific PTQ methods underperform compared to simpler generic baselines. At 4 bits, RTN, AWQ and GPTQ match or exceed ActQuant and QuantVLA, plain RTN matches the calibrated methods, and plain AWQ matches the success QVLA reports for itself. Standard LIBERO hides the losses that do exist: configurations with no significant LIBERO loss lose 1.5-4.3 points under paired LIBERO-plus perturbations. Speed is a weaker story. At batch 1 on the H100, no quantized pi0.5 or OpenVLA-OFT configuration is faster than its 16-bit model (1.06-1.58x slower on library kernels); only the L4 with int8 kernels gains (4-14%), the Thor is slower on every 4-bit configuration, and the engine alone changes latency by 2.1x. Profiling explains why: pi0.5's quantized backbone is compute-bound, while its memory-bound action expert, 63% of GPU time and 13% of the parameters, stays in 16 bits.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07249

MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol

Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, Heuiseok Lim

原文摘要

Multilingual Information Retrieval is increasingly important in real-world search settings, where users issue queries over mixed-language corpora. Existing evaluations mainly reward language-agnostic semantic relevance, treating relevant passages equally regardless of language. Yet retrieval utility also depends on the language of the retrieved passages: users may prefer results they can read and verify in the query language, and query--passage language mismatch can complicate downstream grounding and answer verification in Retrieval-Augmented Generation systems. To evaluate this language-aware dimension, we introduce MLAIRE, a Multilingual Language-Aware Information Retrieval Evaluation protocol that disentangles cross-lingual semantic retrieval from query-language preference. MLAIRE constructs controlled pools with parallel passages across languages, enabling measurement of semantic retrieval accuracy and query-language preference when equivalent translations are available. We propose language-aware metrics, including Language Preference Rate (LPR) and Lang-nDCG, together with a 4-way decomposition separating semantic and query-language preference failures. Evaluating 31 dense, sparse, and late-interaction retrievers, we show that standard metrics obscure distinct behaviors: semantically strong retrievers may return correct content in a non-query language, while retrievers with stronger query-language preference may retrieve less semantically relevant passages.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05088

LatentTriad: Pre-Action Risk Representations for Malicious Agent Skill Detection

Zhe Yu, Yi Liu, Ying Zhang, Simin Chen

原文摘要

Large language model agents are increasingly extended with reusable skills, but untrusted skill content can induce operations outside the user's task. Detecting this contextual risk requires more than suspicious-pattern matching, while dynamic analysis incurs the cost of skill execution. We find that hidden states formed during prefill contain readable information about task-operation consistency, including across held-out expression forms in controlled evaluations. Matched Operation-state interventions also affect later Boundary states and shift fixed risk readouts toward the donor label. Based on these findings, we introduce LatentTriad, which combines contextual Boundary features, group-adjusted Operation directions, and departures from benign state relationships. All branches share one prefill: detection generates no output tokens, invokes no tools, and executes no skill code. Across 5,830 skill packages from five sources and seven backbones, LatentTriad achieves 99.0-99.2% pooled F1 and 93.0-94.6% source-macro F1. A separately measured compact implementation completes prefill and detection in a median of 259-284 ms. These results connect pre-action risk readability and functional influence to execution-free skill screening.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03446

Clinician-AI Collaboration in Endovascular Neurointerventions: In-Vitro User Study of Copilot Assistance Modes for Robotic Navigation Across the Autonomy Spectrum

Nikola Fischer, Harry Robertshaw, S. M. Hadi Sadati, Xingyu Chen, Weiyuan Deng, Benjamin Jackson, Michael Adofo Kwakye, Sara Sciacca 等 19 位作者

原文摘要

Mechanical thrombectomy (MT) is an effective treatment for acute ischemic stroke, yet access remains limited by the availability of neurointerventional expertise. Telerobotic and AI-assisted systems may help address this challenge, but it remains unclear how clinicians interact with different levels of autonomy and how autonomous navigation systems perform in realistic environments. This work introduces Copilot Assistance Modes (CAMs), a framework for clinician-AI collaboration in robotic endovascular navigation spanning the autonomy spectrum from manual operation to full autonomy. In the first in-vitro user study comparing clinician-AI collaboration strategies, 11 experts and two students evaluated six navigation modes in a patient-specific vascular phantom. Objective performance metrics were combined with subjective assessments, including workload and usability. Autonomous performance was additionally evaluated both in silico and in vitro to investigate sim-to-real transfer. Hands-on manual navigation achieved the strongest overall performance (100% success). While fully autonomous navigation achieved 81% success in simulation, performance dropped to 23% in vitro. In contrast, several clinician-AI shared-autonomy modes achieved success rates of 92-97%, approximately four times higher than full autonomy and comparable to direct robotic control (95%), demonstrating mitigation of sim-to-real domain shift through clinician-AI collaboration. Among the evaluated AI-driven approaches, user-directed task delegation and rotational shared control demonstrated the most favorable balance between performance and clinician acceptance. These findings suggest that effective clinician-AI collaboration and allocation of control authority may currently be more important for reliable robotic neurointerventional navigation than increasing autonomy alone.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.18413

Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models

Nicola Farronato, Niccolo Avogaro, Thomas Frick, Mattia Rigotti, Rizwan Ullah Khan, Michele Magno, Konrad Schindler, Cristiano Malossi 等 9 位作者

原文摘要

Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structural integrity, but progress in defect segmentation for civil infrastructures has been held back by an extreme scarcity of data, which requires costly expert annotation. The need for data is accentuated by algorithmic hurdles intrinsic to the problem, including center-bias and the need to rely more on shape when inspecting nearly textureless building materials. To remove the bottleneck, we introduce Cracks in the Foundation (CiF), the largest and most detailed civil infrastructure (instance) segmentation dataset to date, comprising $\approx$150,000 high-resolution tiles meticulously curated over five years in collaboration with civil engineering experts. With the help of this unprecedented data source, we expose a blind spot of current visual AI: despite the advent of promptable Foundation Models (FMs) and Vision Language Models (VLMs), and despite the impressive abilities of today's specialised segmentation models, it turns out that dense image understanding in the built environment is nowhere near solved. Our evaluations indicate that even the most recent zero-shot FMs face significant challenges when deployed on real-world infrastructure and even the performance of specialised models with domain-specific supervision plateaus at $\approx$25\% mAP. CiF establishes inspection of civil infrastructure, an elementary and seemingly easy perceptual task, as an open challenge that reveals fundamental weaknesses of present-day models trained predominantly on internet images, literally and figuratively highlighting cracks in the current foundation model paradigm. Dataset available at: https://huggingface.co/datasets/ibm-research/cif-dataset

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.24715

When Do Repetition Loops Lock? Truncation Sampling, Bounded Penalties, and a Blind Spot in DRY

Yichuan Chen, Xin Wang

原文摘要

Language models sometimes repeat verbatim until the generation limit. We study the exit rather than the entrance: given that a span has already been repeated $n$ times, when is escape still possible? Along the loop the context is deterministic, so the probability that a loop survives $m$ more repetitions is, under any sampler, a product of per-step continuation probabilities computable from one forward pass. A lock, where this probability stays exactly one, is its limiting case. Pure sampling never locks; top-$p$ with threshold $π>1/2$ locks a position exactly when the continuation probability reaches $π$. A bounded penalty can leave a position locked; a penalty that outgrows the model's preference for the loop over unseen tokens guarantees escape under top-$p$. The same analysis shows a blind spot in the widely deployed DRY sampler: its sequence breakers cap the penalty at $λb^{g-1-a}$ for loops whose longest breaker-free run has $g$ tokens. On eleven open models, 61% of locked units with $g=6$ stay locked under DRY and 0.2% with $g=8$. In free generation with llama.cpp, all 199 loops that survive DRY, on six models, have $g\le 7$. We propose a count term that grows exponentially with the number of verbatim recurrences, up to its look-back window, and closes this blind spot. Added to DRY (DRY-C), it cuts loops in 1,800 structured generations on five models from 167 to 34, and loops reaching the length limit from 150 to 0, with reasoning accuracy and item coverage on par with DRY. DRY's own length term costs 2.5 to 14.2 points of accuracy on GSM8K and MATH-500; used in its place, the count term keeps the default sampler's accuracy and leaves one of the 1,800 generations at the limit.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05084

Sparse Anchors for Visual Multi-Session Registration in Changing Environments

Yunus Talha Erzurumlu, Niklas Trekel, Saurabh Gupta, Nico Koltermann, Olga Vysotska, Jens Behley, Louis Wiesmann, Cyrill Stachniss

原文摘要

Repeated robotic monitoring requires localization across visits to the same environment, even if the environment changes. Such changes can substantially reduce persistent visual content, and repetitive structures can lead to incorrect cross-session correspondences. In this paper, we address visual multi-session registration of a new data recording (the query session) to a previously reconstructed reference map. Under substantial visual and structural changes, cross-session localization may be possible only for parts of the trajectory. In our approach, we therefore rely on a sparse set of reliable absolute pose constraints and combine them with within-session relative-pose information to register the complete trajectory to the reference map. We first estimate absolute alignment hypotheses through visual place recognition, local feature matching, and geometric verification. We then use sequence consensus to reject hypotheses that are inconsistent with a common query-to-reference alignment and retain the remaining poses as absolute anchors. These anchors are refined through featuremetric alignment against a Gaussian feature field and combined with within-session relative-pose constraints in a robust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently reconstructed Structure-from-Motion geometry. Our results show that sparse, reliable absolute anchors can provide accurate and complete trajectory registration even when reliable cross-session correspondences are available only for part of the query session.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05083

Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps

Nafie El Amrani, Moritz Heep, Florian Bernard

原文摘要

Estimating semantic correspondences between different object instances of similar categories in real-world images is a fundamental challenge in computer vision. While the recent progress in foundation models has significantly advanced solutions for such difficult image correspondence problems, respective methods are often insufficiently regularised. For example, common nearest-neighbour matching with foundation model features often results in noisy correspondences, which is particularly prominent when solving for dense correspondences. In this work, we tackle image matching via functional maps, which have been popularised for 3D shape matching due to their powerful spectral formalism utilising an efficient low-dimensional linear representation. However, functional maps require that domains (in our cases the rectangular image grids) are equipped with an informative and non-trivial geometry. To define a meaningful manifold structure for images, we use Galerkin's method from finite elements to derive a discrete Laplace-Beltrami operator (LBO) based on a manifold embedding of deep image features. Further, we leverage a neural adjoint map that allows to represent non-linear mappings. We demonstrate that our method sets the new state of the art among zero-shot image correspondence methods on multiple dense correspondence benchmarks of real-world images. Our code is publicly available: https://github.com/NafieAmrani/NAMI

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05080

CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation

Po-Yi Wu, Djengo Cyun-Jyun Fang, Dian Cheng, Tsung-Wei Ke

原文摘要

Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments. However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for real-world deployment due to the need for substantial human intervention. While prior work has studied non-episodic RL in relatively small policies trained from scratch, its behavior when fine-tuning modern large-scale pre-trained vision-language-action (VLA) models remains underexplored. In this work, we introduce CRONOS, a simulation benchmark for RL fine-tuning of VLAs under non-episodic scene resets. CRONOS leverages high-fidelity physics simulators and adopts shared-scene multi-task settings. Using CRONOS, we show that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models. Moreover, we find that non-episodic training enhances long-horizon manipulation and improves generalization to previously unseen object configurations and task sequences. Project page: https://embodiedai-ntu.github.io/cronos/

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05079

Data informed Ansatz Selection for Variational Quantum Circuits

Manav Seksaria, Advith Desu, Anil Prabhakar

原文摘要

Choosing a variational quantum circuit (VQC) usually means searching over ansatze and depths, and training each candidate. We give three rules that fix these choices from the data and the gate set alone, before any training. First, a circuit without entangling gates has a rank-one Fourier coefficient tensor on every subset of qubits. A singular value decomposition of a dataset's Fourier coefficients therefore indicates whether entanglement is needed, which qubits it connects, and a lower bound on the error of omitting it. Second, the rank of the quantum Fisher information matrix grows by $p_0$ per layer, after a first-layer deficit $d_0$, until it reaches a ceiling set by the dynamical Lie algebra. This law fixes the depth. Third, reading out all $2^N - 1$ Pauli-Z products from one batch of shots resolves half of the state's directions, the most any single-basis readout can. A single-qubit readout resolves an exponentially small fraction. For the Madelon dataset, the rules prescribe 7 blocks of 3 qubits at depth 3: a 239-parameter classifier with 78.5% test accuracy, found without a grid search. Ablations confirm three predicted effects: shallower circuits, smaller blocks and dropping reuploading all lower accuracy.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.23952

Score-Based Modeling of Effective Langevin Dynamics with State-Dependent Mobility

Ludovico T. Giorgini

原文摘要

In a previous work [L. T. Giorgini, Phys. Rev. E 114, L012102 (2026)], we introduced stochastic reduced-order models that reproduce by construction the stationary density and short-time correlations of the observed variables, using a constant mobility matrix and the score, the gradient of the logarithm of this density. Here we generalize the framework to state-dependent mobilities, calibrated so that the model also reproduces the finite-lag correlation functions of chosen target observables. The calibration uses exact finite-lag forms of the generalized fluctuation-dissipation theorem, which express time derivatives of lagged correlations as averages over observed pairs of states and are linear in the mobility. When the mobility is expanded on a basis of known fields, its coefficients follow from a least-squares problem involving only the stationary score, and the observables and basis are selected by data-driven diagnostics. Otherwise, a neural-network mobility is calibrated through the conditional score of the finite-time transition density. We validate the approach analytically on a Cox-Ingersoll-Ross process and numerically on a two-dimensional nonequilibrium diffusion with multiplicative noise and a 36-dimensional soft-spin Landau-Lifshitz chain. Both methods reproduce the stationary statistics and the target correlations accurately. Because the identities can be integrated between consecutive lags, so that no time derivatives need to be estimated, the recovered drift and diffusion are much less sensitive to coarse sampling than Kramers-Moyal estimates, which require short sampling intervals. Calibration requires no simulation of the model and applies to high-dimensional systems.

stat.ML · cs.LG · nlin.CD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.03405

Surprisal-Rényi Free Energy

Shion Matsumoto, Ankur Arjun Mali

原文摘要

The forward and reverse Kullback-Leibler (KL) divergences arise as limiting objectives in learning and inference, yet they induce markedly different inductive biases that cannot be explained by expectation terms alone. We introduce the Surprisal-Rényi Free Energy (SRFE), a normalized Rényi-Chernoff log-moment functional of the likelihood ratio. Although SRFE is algebraically related to Rényi divergence for fixed values of the order parameter, its endpoint-symmetric normalization yields a distinct free-energy viewpoint for analyzing how forward- and reverse KL behavior emerges near singular limits. We show that SRFE recovers the forward and reverse KL divergences as endpoint limits and derive local expansions around both regimes in which the variance of the log-likelihood ratio appears as a first-order correction away from the KL objective. These expansions reveal an explicit mean-variance tradeoff governing departures from KL-dominated behavior. We further establish a Gibbs-type variational characterization in terms of weighted KL projections and prove that SRFE controls large deviations of excess code length through Chernoff-type bounds, giving a Minimum Description Length interpretation of the functional. We evaluate SRFE on two synthetic settings (two-dimensional Gaussian-mixture variational inference and multi-class classification) and the long-tailed CIFAR-10 and CIFAR-100 (CIFAR-LT) datasets. On CIFAR-LT, retraining the best configuration of each loss over five seeds, SRFE matches cross-entropy accuracy on CIFAR-10-LT and gives mixed results on CIFAR-100-LT, improving few-shot accuracy at one of three imbalance factors. Together, these results position SRFE as a variance- and tail-sensitive, normalized Rényi-Chernoff free energy that clarifies the geometric, statistical, and large-deviation structure underlying the transition between forward- and reverse-KL limits.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.03876

An Open Book, On Whose Terms? Power Dynamics in Sensor-Derived, LLM-Generated Summaries Sharing Between Older Adults and Remote Families

Jiachen Li, Reina Szeyi Chan, Shihan Fu, Zijian Wang, Akshat Choube, Yingtian Shi, Rosemarie Santa Gonzalez, Thomas Ploetz 等 12 位作者

原文摘要

As older adults (OAs) increasingly favor aging in place, remote family members (RFMs) need meaningful awareness of their loved ones without intrusive monitoring. Large language models can provide rich interpretations of non-intrusive sensing data, yet recent work has largely emphasized technical accuracy over how families use or benefit from this information. We conducted formative interviews with 12 RFMs and 2 OAs, followed by a three-month deployment case study with one OA-RFM dyad. Our system provided daily AI-generated summaries of multimodal sensing data, which we iteratively refined with both parties using a research-through-design approach. Although the summaries integrated well into the dyad's daily routine, sustaining over 90% engagement, their lived experience revealed evolving tensions around agency, reassurance, privacy, trust, and communication, shaped by sensor limitations and existing communication misalignments. Our findings inform the design of future AI-mediated sharing systems that account for real-world sensing constraints and complex family care dynamics.

cs.HC · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19652

On Global Joint Lower Bounds in Zeroth-Order Nonconvex Optimization

Yuxuan Xia, Xiao-Tong Yuan

原文摘要

Must the dimension and accuracy costs of zeroth-order optimization multiply? Global upper bounds for smooth stochastic nonconvex optimization scale as $O(dε^{-4})$, with both factors separately necessary. We show that their product is unavoidable. We establish an $Ω(dε^{-4})$ lower bound for smooth stochastic nonconvex optimization, yielding an $Ω(dδ^{-1}ε^{-3})$ bound for nonsmooth Goldstein stationarity. Both match the best-known full-space upper bounds, establishing joint minimax optimality in dimension and accuracy. These bounds hold against fully adaptive randomized algorithms with unrestricted queries and outputs, even under arbitrary sample reuse. As a byproduct, we establish noiseless exact-value lower bounds for both smooth and Goldstein stationarity, even against randomized algorithms.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05074

Nested Field-of-View Barriers for Teleoperated Multi-Robot Relay Chains

Arthur Vangasse, Theo Cruz, Thales Soares, André Cid, Vinícius Gonçalves, Gustavo Freitas, Luciano Pimenta

原文摘要

Teleoperation of mobile robots in communication-denied environments requires maintaining a communication link while allowing the operator to maneuver freely. We propose a shared-autonomy framework in which a teleoperated leader is followed by a chain of autonomous robots that relays a line of sight to a fixed base station, a geometric proxy for the link. Connectivity is enforced geometrically through visibility-based Control Barrier Functions (CBFs), with each agent computing its control input locally through a quadratic program. A strict visibility constraint guarantees connectivity, but a follower with no independent motion objective remains stationary, stalling the leader at the boundary of the safe set. Relaxing it preserves mobility at the cost of the guarantee. Our framework resolves this conflict through nested hard-soft visibility constraints: a full field-of-view (FoV) constraint enforced strictly to guarantee connectivity and a contracted FoV constraint imposed on each follower as a relaxed behavioral objective that drives it inward before the connectivity boundary is reached. We prove feasibility of the local quadratic programs and forward invariance of the connected, collision-free set under the resulting distributed controller. The contraction parameter shapes follower behavior without affecting the guarantee, which follows from the strict constraint alone. The framework is evaluated in confined and cluttered environments on two simulated systems: a kinematic integrator and software-in-the-loop Crazyflie quadrotors. Compared with a baseline tuned to reach the goal in comparable time, the framework keeps the links far closer to the connected set and moves the followers less.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05072

Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving

Junzhe Wang, Jinqing Zhang, Qingjie Liu

原文摘要

Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring future-aware by explicitly predicting candidate-conditioned future states over the planning horizon, which we term rollout. However, rollout incurs high inference cost and accumulates prediction errors. We argue that planning does not require reconstructing a full future scene for each candidate, but only future-relevant information for reliable comparison. We therefore propose RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation. RFWorld constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low. At inference time, candidate trajectories directly query the shared memory via sparse spatial readout for scoring, reducing computation by roughly the planning horizon times the number of candidate trajectories, while avoiding recursive rollout errors. Experiments on NAVSIM and Bench2Drive show that RFWorld learns a more planning-aligned world representation and achieves state-of-the-art performance.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.13969

Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning

Wen-Chun Lin, Kuan-Peng Chen, Nan-Yow Chen, Yu-Chee Tseng, Jen-Jee Chen

原文摘要

Ptychographic phase reconstruction is commonly formulated as an iterative inverse problem, requiring repeated object-probe updates and resulting in substantial computational cost for large-scale 4D-STEM data. We present a direct local-to-global learning framework that reconstructs full-field phase maps from diffraction measurements without iterative refinement during inference. The proposed network predicts local wrapped-phase patches from individual diffraction patterns using a sine-cosine representation, and the predictions are assembled into a full-field reconstruction using calibrated scan positions and Gaussian-weighted stitching. To evaluate generalization beyond the training domain, the model is trained on one material and directly applied to another in a zero-shot setting without target-domain fine-tuning. Experiments on AuPd and MoS$_2$ demonstrate consistent cross-material transfer in both directions, with the proposed method achieving the best full-field MSE, PSNR, and MS-SSIM among the evaluated learning-based methods. Compared with the iterative ePIE approach, the proposed direct local-to-global pipeline reduces end-to-end reconstruction time by approximately 10$\times$, demonstrating its potential for efficient and transferable ptychographic reconstruction.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11984

Example-driven Parametrisations for Bayesian Shape Optimisation

Gabriel Diaz-Aylwin, Joseph Neighbour, Abiel Malkani Talwar, Rui-Yang Zhang, Henry B. Moss

原文摘要

Bayesian optimisation is the natural tool for shape design when objectives are expensive and non-differentiable, but it needs a compact yet expressive parameterisation of the search space. Hand-crafting one is a complex endeavour requiring domain expertise, and often yields implicit infeasible regions, artificial bounds, and coupled, unordered coordinates. We instead learn the parameterisation from a collection of existing designs, applying principal component analysis to the deformations between shapes. The result is a linear, interpretable search space in which the number of components explicitly trades expressivity against dimensionality. Across aerofoils, wings, and radio-frequency cavities, spanning 2D geometry to 3D aerodynamics and electromagnetics, we show improved sample efficiency and the ability to explore beyond the confines of hand-crafted baselines.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05071

Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning

Ornella Irrera, Matteo Lissandrini, Daniele Dell'Aglio, Gianmaria Silvello

原文摘要

Researchers struggle to find relevant datasets amid the growing volume of data across repositories and scholarly publications. Manual dataset retrieval is time-consuming and often fails to identify valuable resources that are not easily discoverable through direct links or popularity metrics. Dataset recommendation, which aims to identify datasets relevant to a paper, author, or query, has become essential for improving dataset discoverability and reuse. However, this task remains challenging because Scholarly Knowledge Graphs (SKGs) are large-scale, heterogeneous, dynamic, and incomplete. Although openly available SKGs organize scientific knowledge by linking scholarly outcomes, they often lack meaningful connections between datasets, leaving them isolated and underutilized. These graphs contain millions of evolving relations but still suffer from missing or inaccurate metadata, duplicate records, and weak dataset integration. This work presents the Multimodal Scholarly Attention Network (MM-SAN), a heterogeneous multimodal graph representation learning method for recommending datasets relevant to research publications within real-world SKGs. MM-SAN combines topology-aware and text-based embeddings, enabling effective recommendations even when textual metadata is limited or absent. It operates in transductive, semi-inductive, and fully inductive settings, adapting to evolving SKGs without requiring retraining. Experiments show that MM-SAN outperforms state-of-the-art methods, providing a robust and scalable solution for dataset recommendation.

cs.IR

查看论文
arXiv ↗PDF ↗