探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11238

Artificial Intelligence in Ship Finance: Applications, Opportunities, and a Case Study in AI-Augmented Loan Origination

作者:

Lasse Dierich↗Orestis Schinas↗

arXiv:2606.11238v1 Announce Type: cross Abstract: Ship finance is a data-intensive and document-heavy segment of asset-based lending, requiring the integration of financial, technical, contractual, and regulatory information from heterogeneous and largely unstructured sources. Increasing environmental regulation and ESG reporting requirements are adding further complexity to underwriting and loan-origination processes. Recent advances in artificial intelligence (AI), particularly large language models (LLMs), create new opportunities for processing and analysing such information. This paper reviews potential applications of AI in ship finance, with a particular focus on LLM-based systems for document comprehension, information extraction, and workflow automation. We present ShipFinance.ai, a modular agentic architecture to support loan application workflows in ship finance. The proposed system combines an LLM-based extraction module, financial analysis components, external maritime data services, and a controlled document-generation module with a chatbot interface to support the preparation of standardized financing applications. The paper discusses the key challenges for using such models in production. We argue that AI-assisted systems can support maritime finance professionals in managing increasingly complex information and reporting requirements.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11197

MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation

作者:

Xuzhi Wang↗Xinran Wu↗Ziping Zhao↗Jianhua Tao↗Bj\"orn W. Schuller↗

Speech-based automatic estimation of depression levels is essential for enabling early detection and timely intervention, particularly in resource-constrained mental health settings. In recent years, deep learning has demonstrated impressive success across various domains, including affective computing and mental health assessment. Most existing approaches rely on RNN-based architectures (such as LSTM and GRU) to model temporal information for depression estimation. However, the extracted features often emphasize only a few adjacent speech segments, limiting their ability to capture long-range dependencies. To overcome this limitation, we introduce a memory-based feature augmentation method that enhances the representational capacity of GRU-extracted features. Rather than indiscriminately incorporating historical data, our memory bank is designed to selectively integrate two types of components in order to reduce redundancy and irrelevance: (1) historical temporal features that closely resemble the current GRU output, offering complementary contextual information; and (2) dynamic memory features identified based on feature variability, which capture behavioral and emotional fluctuations indicative of depressive symptoms. To effectively fuse the memory-augmented features with GRU outputs, we further design a Hierarchical Attention Fusion (HAF) module. Our method is evaluated on the widely used DAIC-WOZ and E-DAIC datasets, achieving state-of-the-art performance.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13630

From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation

作者:

Pedro Correa↗Olivier Perrotin↗Samir Sadok↗Paula Costa↗Thomas Hueber↗

The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units and to articulatory deformations. We found that encoding phonetic classes is beneficial for accurate facial animation prediction on both semantic and label-based representations with comparable facial animation quality. From the latter, we introduce an Audio Visual Text-to-Speech (AVTTS) pipeline that leverages, as a shared space, discrete representations to decode speech and 3D facial motion.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2508.18166

PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation

作者:

Bin Tan↗Wangyao Ge↗Yidi Wang↗Xin Liu↗Jeff Burtoft↗Hao Fan↗Hui Wang↗

arXiv:2508.18166v5 Announce Type: replace-cross Abstract: Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization. We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR prediction. PCR-CA first extracts compact multimodal embeddings from app text, then introduces a Parallel Codebook VQ-AE module that learns discrete semantic representations across multiple codebooks in parallel – unlike hierarchical residual quantization (RQ-VAE). This design enables independent encoding of diverse aspects (e.g., gameplay, art style), better modeling multiple-category semantics. To bridge semantic and collaborative signals, we employ a contrastive alignment loss at both the user and item levels, enhancing representation learning for long-tail items. Additionally, a dual-attention fusion mechanism combines ID-based and semantic features to capture user interests, especially for long-tail apps. Experiments on a large-scale dataset show PCR-CA achieves a +0.76% AUC improvement over strong baselines, with +2.15% AUC gains for long-tail apps. Online A/B testing further validates our approach, showing a +10.52% lift in CTR and a +16.30% improvement in CVR, demonstrating PCR-CA's effectiveness in real-world deployment. The new framework has now been fully deployed on the Microsoft Store.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18955

Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos

作者:

Runze Xu↗Yiluo Zhang↗Jian Wang↗Yu Wang↗Jincheng Yu↗

Training generalist Vision-Language-Action(VLA) models typically requires massive, diverse robotic datasets with high-fidelity action annotations. While egocentric human manipulation videos are abundant and capture significant environmental diversity, the absence of action labels makes them difficult to use in conventional training paradigms. To address this, we propose a latent-action-based framework designed to extract general action priors from unlabeled human videos. The architecture features a Hybrid Disentangled VQ-VAE that decouples motion dynamics from environmental backgrounds through physical masks, enabling the construction of a cross-embodiment action codebook. By pre-training on human videos with the codebook, the VLM backbone learns deep representations of action intent. For adaptation to specific embodiments, we introduce an intent-perception decoupling strategy where the VLM predicts the action intent while a separate frozen visual encoder provides state-specific features to the action expert, thereby reducing action hallucinations. Results in simulation and real-world environments show that our method, pre-trained exclusively on unlabeled human videos, performs competitively with state-of-the-art VLA models trained on massive annotated datasets, requiring only 50 trajectories for downstream adaptation.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18812

Reinforcement Learning Foundation Models Should Already Be A Thing

作者:

Abdelrahman Zighem↗Jill-J\^enn Vie↗

arXiv:2606.18812v1 Announce Type: cross Abstract: Foundation models for language and vision are powered by internet-scale data, while structured domains (tabular prediction, time-series forecasting, graph learning, reinforcement learning) are not. The substitute is synthetic data, which shifts the burden from collection to prior design. Such priors already exist for many structured tasks: TabPFN and its successors solve tabular classification with a transformer pretrained on a synthetic Bayesian prior. We make two points. First, reinforcement learning is the conspicuous gap: sampling a synthetic MDP is as feasible as sampling a synthetic tabular dataset, yet no in-context RL work treats prior design as a primary objective. Second, MDPs admit a fixed-size sufficient statistic, independent of the episodes observed and tabular in shape, which makes them directly amenable to the attention-based architectures used for tabular foundation models, with a policy head replacing the supervised target. Together these define the agenda for an RL foundation model. As a proof of concept, we train one model entirely on synthetic MDPs and show that, with no task-specific tuning, it solves held-out tabular benchmarks in context, both online and offline: online, in far fewer episodes than UCB-VI and tabular Q-learning, and offline, competitively with VI-LCB.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16802

LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control

作者:

Anqi Zou↗Han Deng↗Chengyu Zhang↗Junquan Hu↗Yu Wang↗Yuxiang Xing↗Aokai Zhang↗Hanling Zhang↗Zhaoyang Liu↗Ben Fei↗Zhihui Wang↗Wanli Ouyang↗…

arXiv:2606.16802v1 Announce Type: new Abstract: Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment. However, directly evaluating agents on physical high-precision instruments is impractical due to high cost, safety risks, limited accessibility, and difficulty in ensuring reproducible evaluation. This motivates the need for a simulated yet realistic testbed that preserves the operational challenges of scientific instruments while enabling scalable and safe benchmarking. To this end, we introduce LabOSBench, a challenging benchmark for multimodal GUI agents built on a suite of web-based scientific-instrument simulators. Operating directly via a browser, LabOSBench avoids resource-heavy OS virtualization while supporting flexible task configuration and execution-based evaluation. Specifically, LabOSBench constructs 96 subtasks across eight instrument simulators, covering workflows from sample loading, alignment, parameter tuning, and data acquisition to result inspection. We evaluate general-purpose vision-language models, specialized GUI agent models, and advanced agentic frameworks at both subtask and end-to-end levels. Our experiments reveal that while existing agents can complete many structured GUI subtasks, they still struggle with feedback-driven operations and long-horizon workflow execution. Overall, LabOSBench provides a reproducible, low-cost testbed for advancing computer-using agents toward scientific-instrument control.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19867

PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement

作者:

Dong Yeong Kim↗Jaewon Choi↗Youmin Shin↗Jungyu Lee↗Myeongseop Kim↗Jinwook Choi↗Joo Whan Kim↗Young-Gon Kim↗

arXiv:2606.19867v1 Announce Type: cross Abstract: Computed Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused datasets.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2604.22128

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers

作者:

Aryan Sharma↗Cutter Dawes↗Shivam Raval↗

When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: in the geometry of the residual stream, and in stack-like attention patterns maintaining a last-in, first-out ordering. However, it remains unclear whether these representations are causally used or merely decodable. We examine this gap in transformers trained on the Dyck language (a formal language of balanced bracket sequences), where the hierarchical ground truth is explicit. By probing and intervening on the residual stream and attention patterns, we find that depth, distance, and top-of-stack signals are all decodable, yet their causal roles diverge. Specifically, masking attention to the true top-of-stack position causes a sharp drop in long-distance accuracy, while ablating low-dimensional residual stream subspaces has comparatively little effect. These results, which extend to a templated natural language setting, suggest that even in a controlled setting where the relevant hierarchical variables are known, decodability alone does not imply causal use.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12935

MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling

作者:

Wenbo Chen↗Puheng Li↗Mengyang Liu↗Weijie Su↗Tianpei Xie↗

arXiv:2606.12935v1 Announce Type: new Abstract: Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at intermediate checkpoints can extract current answers without disrupting generation, revealing an evolving aggregate vote. Based on this observation, we introduce MARS, a margin-adversarial stopping rule that estimates which active traces are likely to change their answers and stops once the leader remains safe under a conservative bound on future vote movement. The rule separates two sources of uncertainty. It learns the trace-level switch probabilities that determine how much of the current margin is likely to be retained, while handling the harder question of where switching traces land through an adversarial bound calibrated from warmup traces. With true switch probabilities, MARS guarantees with high probability that the early-stopped answer matches the full-budget vote. In practice, a five-feature logistic model closely matches oracle switching behavior. Across three reasoning models and three competition-math benchmarks, MARS saves 25-47% of self-consistency tokens and 14-29% on top of DeepConf Online, a strong confidence-weighted baseline that already filters and truncates weak traces, while matching the accuracy of the corresponding full-budget baselines.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.04364

Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention

作者:

Dhanesh Ramachandram↗

Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable. On fine-grained recognition tasks the concept heads are usually free to attend anywhere in the image, so a head named for one body region can be satisfied by evidence on another. This work studies a part-factorized CBM that removes that freedom by construction. The method has three components built on a frozen DINOv3 vision transformer. A learned foreground gate, trained on DINOv3 patch features, suppresses background patches inside the part attention. A set of part queries cross-attends to patch features and each of the 312 CUB attributes is routed, through a fixed concept-to-part map, to read only from the part token its name implies. A learnable two-dimensional Gaussian prior, injected additively in log space into the attention logits, breaks the permutation symmetry among part queries; its means are initialized from the dataset-average keypoint location of each part, which requires no per-image keypoint supervision at training or test time. On CUB-200-2011 the spatial-prior model matches a fully supervised baseline (88.85% versus 88.95% top-1) while raising pointing accuracy by 16 points (52.6% versus 36.4%). Replacing bounding-box supervision with a PCA foreground target and combining it with the Gaussian prior removes all per-image supervision and reaches 88.6% top-1 at about 70% pointing accuracy. A keypoint-fraction sweep shows that 0.5% of the training set (about 27 images) suffices to initialize the prior with no measurable loss. Removing part identity entirely is the harder case: without any spatial prior, pointing accuracy collapses to $2.9\%$.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14498

A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction

作者:

Yunhong Lou↗Xihang Yue↗Xinran Wei↗Tianqi Deng↗Linchao Zhu↗

arXiv:2606.14498v1 Announce Type: cross Abstract: Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-structure observables that energy-only surrogates cannot resolve. Yet element-wise agreement with the converged Hamiltonian, an implicit fixed point of the self-consistent field iteration, does not determine the occupied subspace that governs orbital energies and densities. Here we present HamEvo, a neural operator that learns the single-step self-consistent update and returns the converged Hamiltonian as its fixed point. HamEvo is pre-trained on intermediate self-consistent trajectories and calibrated at equilibrium with density-matrix supervision. Across benchmarks from MD17 to drug-like QMugs, HamEvo lowers Hamiltonian errors by 35-49% over direct-regression and deep-equilibrium baselines, and predicts QMugs HOMO and LUMO energies with mean absolute errors of 0.036 and 0.053 eV, near the 1 kcal/mol chemical-accuracy scale. Few-shot fine-tuning with only 20 reference conformations extends HamEvo to molecules of up to 122 atoms, well beyond the size range covered by pre-training. With thermal molecular-dynamics sampling, HamEvo captures temperature-dependent HOMO-LUMO gap renormalization beyond the harmonic approximation. Inference is up to 242 times faster than conventional DFT.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14762

Scribby: A Multi-Level LLM Framework for Semantic Video Analysis

作者:

Julian Abelarde↗Hugo Garrido-Lestache Belinchon↗

As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased [1]. Although many existing AI programs provide high-level video summaries based on AI-generated transcripts [2,3,4,5], these approaches are often limited to coarse overviews and lack detailed analysis of a video's structure, thematic progression, and semantic relationships, all of which are required for comprehensive video analysis. This paper proposes an LLM-based video summarization framework that balances macro-level comprehension with micro-level semantic analysis [6,12,13]. The first stage of the process indexes the video at a micro level by (1) analyzing the full transcript, (2) analyzing individual transcript sentences, and (3) grouping these sentences by semantic similarity using an LLM as a judge [6,13]. Contextual continuity is retained during sentence-level processing by incorporating both the global transcript analysis and adjacent sentence information into each evaluation prompt. This framework establishes a foundation for video analysis tools that visualize semantic chunking and semantic matching through relevance-based heatmaps. Limitations and future expansions of the framework are also discussed.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.15882

Finite-Dimensional Type I von Neumann Algebras in PyTorch: A GPU-Accelerated Framework for Random Block-Diagonal Operators

作者:

Irina Nikolaeva↗Andrej Novikov↗

arXiv:2606.15882v1 Announce Type: cross Abstract: We present \texttt{torch\_vn\_algebra}, an open-source Python library built on PyTorch for numerical experiments with finite-dimensional Type I von Neumann algebras (direct sums of matrix algebras). The library provides: $\bullet$ a compact batched tensor representation $(B,C,k_{\max},k_{\max})$ that handles both Monte Carlo samples and multiple direct summands; $\bullet$ lazy evaluation of operators to avoid unnecessary memory allocation; $\bullet$ generation of random operators with arbitrary eigenvalue distributions (user-provided samplers) and various unitary ensembles (Haar, $\mathrm{SU}(n)$, COE, CSE, diagonal phases); $\bullet$ functional calculus via SVD (absolute value, square root, inverse, entropy) and a hybrid method for extreme eigenvalues (exact diagonalisation for $k_{\max}\le256$, otherwise power iteration); $\bullet$ three trace functionals (blunt, normalised subspace trace, and the von Neumann tracial state); $\bullet$ GPU-accelerated batched linear algebra for moderate-scale Monte Carlo studies (e.g., $2\times10^4$ samples of $100\times100$ operators). The library is validated against analytical expectations (Haar moments, trace properties). Performance benchmarks on a Tesla P100 GPU are presented and discussed. Limitations and future work are outlined. The code is open-source.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15932

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

作者:

Xuanle Zhao↗Qiushi Sun↗Jingyu Xiao↗Xuexin Liu↗Haoyue Yang↗Qiaosheng Chen↗Xianzhen Luo↗Jing Huang↗Yufeng Zhong↗Lei Chen↗Shuai Fu↗Zhenlin Wei↗…

While LLMs have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, charts, documents, vector drawings, videos, and interactive states. These tasks require models to connect visual perception to executable programs, because correctness depends not only on syntax but also on layout, geometry, data semantics, editability, interaction behavior, and domain-specific constraints that apply after execution. This survey examines Multimodal Code Intelligence, covering systems that generate, edit, refine, execute, or reason with code under visually grounded inputs and outputs. We first formulate the field by the role that code plays in each task, distinguishing code as a rendered artifact, an editable symbolic structure, a scientific representation, an intermediate reasoning trace, or an executable policy or tool interface. We then organize benchmarks and methods into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. This taxonomy connects mature artifact-generation problems to emerging agentic and unified settings and allows us to compare how different tasks treat evidence of correctness. Looking ahead, we argue that future research may benefit from four verification-centered directions. Multi-signal validation can combine complementary evidence of correctness, multi-state verification can test behavior across execution trajectories, cross-task transfer testing can probe reusable visual-code skills, and verifiable agent traces can reveal whether agent actions are grounded in visual evidence. Together, these directions may move multimodal code generation from single-output imitation toward evidence-grounded executable systems.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16682

Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents

作者:

Zewen Liu↗

When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge. We show that Evaluator Preference Collapse (EPC) is dramatically amplified in multimodal settings. Using GPT-4o to evaluate DeepSeek-chat across text and visual tasks, we find that a single strategy (step_by_step) absorbs 48.4% of all weight – 3.2x the collapse observed in text-only self-evaluation – while three visual-domain strategies receive only 9.1% combined weight. We then demonstrate a novel phenomenon we term cross-modal contagion: evaluator preferences acquired on one modality transfer to and corrupt strategy selection on another. Through a four-phase isolation training paradigm, we measure contagion coefficients and document strategy inversion – the optimal strategy for a modality reverses after cross-modal exposure. A Phase 3 statistical validation across four evaluator configurations (N=53 total independent repetitions, 15,592 API calls) reveals a clear hierarchy: cross-model evaluation (GPT-4o, N=8) produces strong but symmetric bidirectional contagion (mean gamma_{T->V}=1.176, gamma_{V->T}=1.089, Delta=-0.088, p=0.575, Cohen's d=0.29); high round counts (DashScope, 50 rounds) cause collapse to single-strategy dominance (70% zero contagion); and self-evaluation provides near-complete immunity – 97% of runs (N=30, DeepSeek-chat) yield exactly zero contagion (mean gamma=0.033, 95% CI [-0.031, 0.010], p=0.642, d=0.07). No evaluator condition shows statistically significant directional asymmetry. We introduce the contagion matrix indexed by evaluator identity, release the MM-EPC experimental framework, and identify cross-model evaluator architecture as the primary risk factor for preference contagion.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15231

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

作者:

Zhengbo Zhang↗Changtao Miao↗Jinbo Su↗Zhaowen Zhou↗Chunxia Zhang↗Xukai Wang↗Ruiqi Liu↗Kaiyuan Zheng↗Jiansheng Cai↗Bo Zhang↗Zhe Li↗Shiming Xiang↗…

arXiv:2606.15231v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex, open-world scenarios. While recent multimodal deep search agents attempt to address this issue by utilizing external tools, the visual-native search paradigm remains underexplored. Existing methods primarily rely on simple images with explicit semantics and text-only evidence trajectories, limiting the agent's ability to perform multi-hop, cross-modal reasoning and search. To address these limitations, we propose Visual-Seeker, a visual-native multimodal deep search agent via active visual reasoning. Rather than treating vision as a static input, our agent actively attends to fine-grained visual details, dynamically harvests visual evidence throughout the search process. To unlock its visual-native potential, we design an active visual reasoning data pipeline and synthesize 5K high-quality multimodal trajectories for model training. Extensive experiments demonstrate the state-of-the-art performance across five challenging multimodal search benchmarks, even surpassing several proprietary models, validating robust visual-native reasoning and search in real-world web environments. The code and data can be accessed at: https://github.com/ZhengboZhang/Visual-Seeker.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11766

Fast Speech Foundation Model Distillation Using Interleaved Stacking

作者:

Eungbeom Kim↗Kyogu Lee↗

Distilling a large speech foundation model (SFM) into an efficient student model has been successfully applied to low-resource environments. Although distillation reduces inference latency, it requires an additional student model training. However, the training efficiency of SFM distillation remains underexplored. In this work, we explore training acceleration of SFM distillation to speed up model deployment. We examine the potential of stacking, in which the model depth is progressively increased through training until the target model depth is reached. While existing stacking methods improve training speed, they suffer from performance degradation. To handle this limitation, we propose interleaved stacking, a novel stacking method that consistently preserves layer position throughout the stacking process. This property is particularly critical in SFMs, in which each layer encodes distinct layer-specific knowledge. We validate the effectiveness of the proposed method on SUPERB.

阅读与讨论 → 访问原文 →

19.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2508.10076

TensorKit.jl: A Julia package for large-scale tensor computations, with a hint of category theory

作者:

Lukas Devos↗Jutho Haegeman↗

arXiv:2508.10076v2 Announce Type: replace-cross Abstract: TensorKit$.$jl is a Julia-based software package for tensor computations, especially focusing on tensors with internal symmetries. This paper introduces the design philosophy, core functionalities, and distinctive features, including how to handle abelian, non-abelian, and anyonic symmetries through the ``TensorMap'' type. We highlight the software's flexibility, performance, and its capability to extend to new tensor types and symmetries, illustrating its practical applications through select case studies.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17013

Exploding and vanishing gradients in deep neural networks: the effect of residual connections

作者:

Vivek S Borkar↗

arXiv:2606.17013v1 Announce Type: cross Abstract: The well known phenomenon of exploding and vanishing gradients in deep neural networks is analyzed using multiplicative ergodic theory. The effect of adding a residual connection is explained in this context. Specifically, a characterization of Liapunov exponents due to Furstenberg and Kifer is exploited in order to make a precise statement about the Liapunov spectrum and the effect of residual connections on it.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.08402

SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

作者:

Jeonghwan Kim↗Yushi Lan↗Yongwei Chen↗Hieu Trung Nguyen↗Chuanyu Pan↗Xingang Pan↗

Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly decomposed pipelines that entangle many factors at once and demand extensive scene-level supervision, limiting their generalization to complex real-world environments. We propose a multi-agent orchestration framework that decomposes single-image 3D scene generation into three structured stages: scene initialization, environment construction, and multi-agent refinement. The initialization stage extracts image-derived object masks, builds object-level 3D representations, and predicts an initial spatial layout to form a coarse 3D scene. The environment-construction stage then leverages this initialization together with point-map geometry to build an environmental scaffold of supporting surfaces, room boundaries, materials, and illumination. Finally, in the refinement stage, a planner agent identifies structural and visual inconsistencies, applies simple corrections directly, and dispatches specialist agents for complex localized revisions that are reintegrated into the global scene. To provide reliable structural initialization while reducing reliance on scene-level annotations, we further introduce a geometry-aware layout predictor supervised by sparse geometric priors derived from point maps. Unlike fully supervised layout generators, the predictor can be trained from segmentation-level data and generalizes robustly to diverse real-world scenes. Extensive experiments on benchmark datasets show that our method consistently outperforms prior approaches in geometric accuracy, spatial consistency, and perceptual realism.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12590

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs

作者:

Shayan Mohammadizadehsamakosh↗Pritam Sarkar↗Leonid Sigal↗Ali Etemad↗Elham Dolatabadi↗

Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback. Existing post-training alignment approaches, including Direct Preference Optimization (DPO) and its variants, face three critical limitations in the medical domain: (1) sequence-level reward signals treat clinically critical tokens identically to generic filler text; (2) reliance on static supervised fine-tuning references as preferred responses introduces an off-policy distribution shift, steering optimization toward stylistic artifacts over clinical correctness; and (3) alignment objectives lack explicit visual grounding constraints, leaving models insensitive to subtle yet diagnostically decisive pathological features. Our method leverages a bidirectional token-wise KL regularizer alongside a visual-contrastive grounding objective that pairs clean and lesion-corrupted images to penalize responses generated without adequate visual evidence. Together, these components form a fine-grained, on-policy alignment framework that constructs preference pairs by minimally editing model-generated outputs, correcting only clinically erroneous spans while preserving the original linguistic style. Extensive experiments across medical imaging tasks and clinical text generation benchmarks validate the effectiveness of our approach.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2506.16738

LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization

作者:

Daejin Jo↗Jeeyoung Yun↗Byungseok Roh↗Sungwoong Kim↗

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate semantic information from low-level acoustics to better align with language models (LMs). In particular, previous methods use self-supervised learning (SSL) teachers such as HuBERT to extract semantic representations, which are then distilled into a semantic quantizer to suppress acoustic redundancy as well as capture content-related latent structures. However, these tokenizers often operate at relatively high frame rates, producing token sequences significantly longer than their textual counterparts and hindering seamless integration with pretrained LMs. Although recent methods attempt to reduce the token rate by applying uniform average pooling to SSL features, this can over-smooth content-bearing regions and dilute the structural information, thereby potentially limiting the LM alignment. To address this, we propose LM-SPT, an LM-aligned speech tokenization method based on semantic speech-resynthesis distillation. Instead of directly matching teacher and student features via pooling, LM-SPT resynthesizes speech from semantic tokens only and minimizes the discrepancy between representations extracted from the original and resynthesized waveforms using a frozen, LM-aligned speech encoder. This indirect supervision avoids rigid temporal alignment and encourages dedicated semantic units that are more semantically aligned with LMs under reduced frame rates. Experimental results show that the proposed LM-SPT consistently outperforms previous semantic-enhanced speech tokenizers when applied to SLMs for the tasks of automatic speech recognition and text-to-speech, even without compromising the speech reconstruction fidelity at the codec level.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14783

The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models

作者:

Chenyu Zhou↗Qiliang Jiang↗Shuning Wu↗Xu Zhou↗

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail required for exact text recovery. Encoder-free vision-language models (VLMs) remove this boundary by routing image patches directly into the language-model token stream, thereby exposing an architectural privacy attack surface: intermediate visual tokens become a pre-output side channel. Under a token-access adversary, decoders invert visual-token streams from two encoder-free VLMs, Gemma4 and Fuyu, recovering recognizable image structure and readable held-out access codes, whereas matched encoder-based controls localize target regions but recover no exact strings. Within-model ablations show that the operative factor is spatial sampling fidelity of the visual-token grid, especially character-direction sampling density, rather than token or value count. The leakage is not limited to exported tokens: Gemma4 layer-0 key-value cache tensors are directly invertible, placing the side channel within KV caches commonly persisted by production serving stacks for decoding efficiency. The attack survives clutter, realistic document degradation, and zero-shot transfer to public document images, and it resists value-level defenses such as additive noise and quantization. Effective mitigation must therefore reduce spatial sampling, making removal of the vision encoder a first-class privacy decision in VLM deployment.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.13714

TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation

作者:

Duc Nguyen↗Sieu Tran↗Hao Vo↗Khoa Vo↗Duy Minh Ho Nguyen↗Nghi D. Q. Bui↗Anh Nguyen↗Long Mai↗Ngan Le↗

Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propagate a fixed set of slots across frames, but typically assume unconditional slot propagation: every slot is updated and decoded at every frame, regardless of whether its corresponding object is visible. We show that this design violates a basic lifecycle requirement for persistent slots: when an object is absent or fully occluded, its slot should preserve its previous state and avoid explaining unrelated visible content. Instead, unconditional propagation creates two failure pathways: update-induced state drift, where current-frame evidence overwrites the absent object's representation, and decoder-induced reconstruction interference, where the inactive slot remains coupled to reconstruction through decoder attention. We propose Temporal Slot Activation (TSA), a mechanism that learns a per-slot, per-frame activation score $\alpha_{k,t} \in (0, 1)$ without visibility supervision. TSA uses this activation as a shared latent control variable for slot lifecycle modeling. When a slot is inactive, TSA anchors its state to the previous slot via activation-gated updating and suppresses its decoder participation through an activation-dependent additive bias on attention logits before softmax normalization. This jointly reduces state drift and reconstruction-driven interference. To improve decisions under partial occlusion and gradual reappearance, TSA further conditions activation prediction on a per-slot temporal memory produced by a Temporal Context Encoder. We evaluate TSA on MOVi-C/E, YT-VIS, and OVIS benchmarks using both standard and tracking-based metrics (FG-ARI, mBO, IDF1, HOTA). TSA consistently improves object decomposition and temporal identity preservation, with large gains on long, heavily occluded videos.

阅读与讨论 → 访问原文 →