paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Hierarchical MoE for Multi-Modal ILD Diagnosis

Alec K. Peltekian, Gorkem Durak, Halil Ertugrul Aktas, Carrie Lynn Richardson, Mary Carns, Kathleen Aren, GR Scott Budinger, Anthony J. Esposito, Alexander Misharin, Alok Nidhi Choudhary, Ankit Agrawal, Ulas Bagci

Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in medical data. We present a hierarchical multimodal MoE for interstitial lung disease (ILD) classification that integrates a frozen, pre-trained imaging expert with structured electronic health records (EHR) via two-stage gating. A modality-level gate assigns patient-specific weights to imaging and EHR predictions, while a sub-gating module decomposes the EHR branch into clinically defined feature groups with learned, group-specific contributions. This design preserves stable imaging representations while enabling input-dependent clinical weighting and explicit EHR specialization. Under strict patient-level cross-validation, the model achieved the highest mean AUC among the evaluated methods (0.8750 +- 0.0443), compared with 0.8646 for imaging-only REN and 0.7685 for SwinUNETR. The framework extends interpretability across anatomical regions, imaging--EHR utilization, and clinically defined EHR feature groups.

arXiv

What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift

Ayoub Louaye Bouaziz, Lokmane Chebouba, Yassine Himeur

Medical vision-language models (VLMs) can appear reliable in-domain while failing when acquisition domain, paired supervision, or evaluation protocol changes. We study this failure mode as a representation-level blind spot relevant to epistemic intelligence, without claiming a formal estimator of epistemic uncertainty. Using NIH ChestXray14 and CheXpert, we first isolate source-only cross-dataset visual transfer from unsupervised domain-adaptation diagnostics. Using PadChest and OpenI, we then evaluate multimodal alignment under strict pair-index retrieval and quantify metadata-derived source-proxy information retained in frozen embeddings. Self-supervised visual initialization improves NIH-to-CheXpert transfer over supervised ImageNet initialization in matched ResNet-18 comparisons, whereas adversarial adaptation is useful only in a narrow regime and becomes unstable as adversarial pressure increases. Multimodal exact-pair retrieval remains low under external OpenI stress testing, and source-proxy information remains recoverable from learned representations. Qualitative nearest-neighbor and Grad-CAM analyses show clinically plausible cross-dataset structure and thoracic attention patterns in many cases, while device-heavy and false-positive cases remain ambiguous. Auxiliary architecture checks are task-dependent and do not support a universal backbone ranking. Overall, the study shows that apparent competence under a single protocol can conceal transfer, alignment, and shortcut-related failure modes, motivating stress-tested evaluation of medical VLMs under distribution shift.

arXiv

Platonic Representation Hypothesis on World Models

Wenhow Li, Chengwei MA, Hui Xiong, Ying-Cong Chen, Lei Zhang

World models have demonstrated significant potential for perceiving and simulating complex environments. Despite their strong performance, the fundamental nature of their learned representations remains poorly understood. In this paper, we investigate the Platonic Representation Hypothesis within this domain by proposing the Predictive Consistency Assumption: we posit that the optimization of a shared state transition objective acts as a selective pressure that encourages heterogeneous models to converge toward a shared latent structure. Through systematic experiments with the DINO World Model (DINO-WM), in which we vary visual encoders to create heterogeneous models, we find that capable world models evolve toward geometrically similar internal structures. Moreover, via model stitching, we show that the internal features of one world model can be mapped to another with limited performance degradation, providing evidence of functional compatibility. Our findings suggest that the pursuit of predictive consistency can promote shared, transition-compatible latent structure across world models.

arXiv

Scaling Muon for Diffusion Transformers

Chenghao Li, Xiao Han, Xinxin Huang, Wei Liu, Boyang Li, Bing Xiao, Heran Zhang, Juanma Perez Rua, Ke Xu, Kangning Liu, Linjun Kuang, Na Li, Tan Wang, Tian Xie, Wei Peng, Yang Pei, Yifan Xu, Yuanhao Zhai, Yuwei Lin, Zhe Wang, Zihao He, Daniel Li, Junbiao Tang, Ziyang Jiang, Dake Chen

The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion Transformers (DiTs) remain unclear. We first establish Muon's scaling behavior on DiTs from 1.3B to 15B parameters, showing that its optimization and generative quality advantages over AdamW persist across model scales. However, at scale, the 5-step Newton--Schulz iteration (NS5) performed at every optimization step, together with full-momentum materialization, introduces substantial computation and communication overhead that can offset Muon's step-efficiency advantage. We introduce \emph{Periodic Row-wise Muon}, which performs a full NS5 spectral update once every \(K\) steps and applies a low compute and communication cost row-wise constrained update based on the current momentum at the remaining steps. We further co-design a distributed implementation that operates directly on sharded momentum during non-refresh steps and accelerates spectral refreshes through bucketed all-gather and communication--computation overlap. Across all scales, Muon improves the best observed generative quality over AdamW by 12.9--19.1\%. Compared with vanilla Muon, Periodic Row-wise Muon remains within 0.5\% in best generative quality on the 1.3B--4B models and improves it by 4.5\% at 9B. It reduces optimizer time by 46.9--54.3\%, end-to-end step time by 15.7--24.3\%, and logical communication volume by 66.7\%, while reaching its respective best generative quality with 33.7--64.8\% less active training time. These results show that Periodic Row-wise Muon preserves Muon's generative quality advantage while translating it into end-to-end training efficiency for large DiTs.

arXiv

SPARK-SAM: Learning How to Prompt and Respond for Infrared Small Target Segmentation

Aji Mao, Zhenming Peng, Bailin Mu, Tian Pu

Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a mismatch between spatial prompts and target-domain mask responses. In a diagnostic using target-covering loose-box prompts deterministically derived from test reference masks, the best official SAM2.1 results are only 4.69%, 1.64%, and 2.28% IoU on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K. We introduce SPARK-SAM (Self-Prompt Adaptation with Response Knowledge for SAM), which learns target-domain response knowledge and conditions the decoder through an image-conditioned joint self-prompt state. Training combines benchmark-mask supervision with reliability-aware response guidance. SPARK-SAM achieves 75.78%, 86.49%, and 68.34% IoU with 0.726M additional parameters, ranking first on two benchmarks among 14 retrained SAM variants and adaptations evaluated as automatic image-to-mask methods. The staged IRSTD-1K diagnostic shows that response adaptation reaches most of the final IoU before the predicted points acquire reliable target grounding. Prompt supervision aligns the predicted prompt candidates with target locations, and frozen-weight interventions measure output sensitivity to the joint self-prompt state. Matched ablations show consistent accuracy gains from response guidance and high-resolution prompt refinement across all three datasets. Code is available at https://github.com/Sakauma/SPARK-SAM.

arXiv

HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion

Muhammad Asad Ali, Nadia Robertini, Didier Stricker

In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images. Unlike previous monocular approaches, which suffer from scale-depth ambiguities, our method ensures consistent and accurate absolute hand poses and shapes. This is achieved through a multi-view attention-fusion mechanism that effectively integrates features from multiple viewpoints. In contrast to previous multi-view methods, our approach eliminates the need for camera parameters as input to learn 3D geometry. HandMvNet also achieves a substantial reduction in inference time while delivering competitive results compared to the state-of-the-art methods, making it suitable for real-time applications. Evaluated on publicly available datasets, HandMvNet qualitatively and quantitatively outperforms previous methods under identical settings. Code is available at github.com/pyxploiter/handmvnet.

arXiv

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Xuan He, Cong Wei, Yuhao Cheng, Linrui Ma, Yuxuan Zhang, Zuojun Li, Yuhao Wen, Jize Jiang, Zeyi Liu, Yuren Hao, Songcheng Cai, Keming Wu, Penghui Du, Kai Zou, Rui Yang, Chenkai Sun, Ke Yang, Ping Nie, Kelsey R. Allen, Chenglong Wang, Michel Galley, Jianfeng Gao, ChengXiang Zhai

Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: benchmarks should adopt inputs aligned with the visual priors of current video models, require valid evolving processes rather than only plausible final states, and calibrate task difficulty to remain challenging yet partly feasible. To this end, we introduce VGI-bench, containing 27 tasks and 810 instances, organized by a two-level taxonomy of task domains and skill tags for fine-grained evaluation of visual reasoning capabilities of video generation models. Our evaluations show that current generative systems can solve a subset of visually grounded reasoning tasks, but remain far from reliable, with even the strongest model, Seedance 2.0, achieving only 51.0% under our evaluation criteria. Our analysis further explore the output failure modes, input condition sensitivity, performance transfer boundary from synthetic fine-tuning, and internal denoising perspective revealing limited self-correction, where later steps mainly refine early hypotheses rather than correct reasoning errors. We hope VGI-bench will help stimulate the development of next-generation video generation models. Website: https://hexuan21.github.io/VGI-Bench/

arXiv

Training-Free Agentic Computer Vision for Structural Component Detection in 2D Structural Framing Plans

Mohammad Talebi-Kalaleh, Qipei Mei

Converting structural framing plans into editable finite-element model drafts is labor-intensive and susceptible to transcription errors. Existing building-component recognition systems generally depend on task-specific neural detectors, whereas language-model agents in structural engineering typically operate on text or model data rather than on drawings. To the authors' knowledge, this work is the first to apply an agentic vision-language layer to structural-component detection and model drafting from framing-plan PDFs without task-specific detector training or fine-tuning. A deterministic stage extracts geometric primitives, estimates scale by dimension-ratio consensus, recognizes five entity classes using an explicit drafting grammar, and assembles an editable layout. The agentic stage constrains typed corrections through deterministic candidates, operation-specific admission tests, change-level review, and fail-closed transactions. Evaluation used an author-generated benchmark of 100 plans, divided equally between a development half used for all rule revisions and a seed-disjoint held-out half generated after the rules were frozen and evaluated once. All scores are end-to-end results for the complete framework on the held-out half. Scale estimates were within 0.1% of the generator reference for every drawing. Recall and precision were 0.922/0.997 for columns, 0.886/0.990 for beams, 1.000/1.000 for walls, 1.000/1.000 for braces, and 1.000/0.964 for openings. A controlled study repeated two corruptions three times on three development drawings. Calibration passed all nine trials, whereas member repair satisfied every strict end-state criterion in five of nine trials. Because both benchmark halves share a generator, the evaluation does not address independently drafted plans, raster input, analytical connectivity, or solver validation.

arXiv

FLEET: Token-Based Feature Extraction for Event Camera-based Reinforcement Learning

Tristan Gottwald, Maximilian Schier, Melanie Schaller, Bodo Rosenhahn

Event cameras generate asynchronous, high-frequency data streams offering spatially sparse information at lower latency than traditional cameras. In principle, these properties should be ideal for the design of control policies. However, reinforcement learning research in this field remains limited as existing approaches fail to fully exploit the sensor's properties. CNN-based methods negate the sensors benefits by aggregating events into sparse grids. This couples compute cost to sensor resolution and blurs the temporal information. Meanwhile, existing generative baselines rely on the availability of trajectory data to pretrain the model. We propose FLEET (Feature Learning from Events via Efficient Tokenization), a feature extractor that processes event sequences directly. Leveraging random Fourier features and cross-attention, our architecture compresses variable streams into fixed-size latent representations. This decouples inference cost of the feature extractor's backbone from the sensor's resolution, enabling end-to-end learning without auxiliary losses. We validate FLEET on a new, high-throughput benchmark. The results demonstrate that our sequence-based approach surpasses SOTA performance and exhibits superior robustness to variations in observation frequencies.

arXiv

Reliability analysis for BraTS-GoAT segmentation: a controlled robustness study of deep-ensemble uncertainty

Riya Deepak Shet, Chenxi Liang, Le Zhang

Deep networks segment brain tumours accurately in-distribution, but can fail silently when the input differs from their training data. That risk is central to clinical deployment and is the premise of the BraTS-GoAT generalizability task. We ask not only how well a model segments, but whether its uncertainty knows when it is wrong. On BraTS-GoAT (Task 3) we train a 5-fold cross-validated nnU-Net baseline (one held-out prediction per case) and a 3-seed deep ensemble. Both are evaluated for calibration and error detection on a per-region relevant mask, aggregated per case. In-distribution the 3-seed ensemble improves modestly over the already strong single model on the same held-out split, with the clearest gain in calibration. The separation appears under shift. In a controlled robustness study using graded synthetic corruptions as a proxy for acquisition shift, the single model's confidence stays flat while its accuracy and calibration degrade. Inter-member disagreement instead rises steeply, about a quarter to a third above the clean condition, several times the single model's response. On the official validation leaderboard the 5-fold ensemble of those folds attains whole-tumour Dice 0.87. The generalization gap is concentrated on the harder regions, with a characteristic failure of missing small, satellite lesions on unseen cohorts. In the synthetic study, disagreement among the 3-seed members is a more sensitive case-level indicator of acquisition shift than single-model confidence. Its per-voxel error localisation weakens as severity grows. The contribution is a rigorous, honest reliability comparison rather than a claim that any one uncertainty method dominates.

arXiv

HEDGE: A Calibrated Ensemble for A/H Recognition

Josep Cabacas-Maso, Ismael Benito-Altamirano, Carles Ventura

Ambivalence and hesitancy (A/H) undermine digital behaviour-change interventions, and recognizing them automatically from video is the goal of the ABAW A/H challenge on the BAH dataset. We describe HEDGE (Hesitancy/Ambivalence Estimation via Distribution-aware, Generalized Ensembling), our system for the 11th edition of the challenge: a calibrated, equal-weight ensemble of three fusion models over frozen face, audio, text, and pose embeddings, which reaches 0.7358 macro-F1 on the public test set. We also submitted four variants of this system to this year's private test (30 new participants): a fixed-threshold version, a single individual model, and an ensemble with cache-personalization test-time adaptation (TTA). The plain calibrated ensemble scored 0.7361 macro-F1 on the private test, closely matching our public-test estimate, and the TTA variant scored highest of all five at 0.7367 macro-F1, our official challenge result (team AIWELL, rank 5 of 12), even though TTA showed no benefit on the public test. The single individual model dropped to 0.6759, far more than any ensemble variant. We explain both results: TTA only has distribution shift to correct on the private test, which the public test lacks, and a text-only linear probe reaches 0.716 macro-F1 (within noise of the full system, correlated at 0.91 in its errors), so the ensemble's robustness to new participants comes from the same modality redundancy that makes single, less-diversified models comparatively brittle. We additionally report a systematic study of more than 60 further controlled experiments (modality, backbone, loss, and adaptation ablations) that did not improve on this system, and an explainability analysis showing the transcript's delivery style dominates the signal while the extractable non-verbal ceiling saturates near 0.60 macro-F1.

arXiv

S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval

Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez, Devendra Singh Sachan, Barlas Oguz, Seungwhan Moon, Shang-Wen Li, Gargi Ghosh, Xin Dong, Wen-tau Yih

As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capability known as episodic memory. Current benchmarks often rely on offline evaluation with access to entire video files, failing to simulate the streaming reality of wearable intelligence. We introduce S-EMBER (Streaming Egocentric Memory Benchmark for Episodic Retrieval), a large-scale benchmark comprising 3,141 videos totaling 388 hours of organic activity captured via Ray-Ban Meta smart glasses. S-EMBER formalizes grounded streaming episodic retrieval, a paradigm shift from global offline search to causal, active recall triggered by visual events in a continuous stream. We provide 9,448 QA pairs requiring manual visual proof through precise temporal localization and supporting flexible response lengths to simulate natural human-AI interaction. Our extensive benchmarking of frontier models reveals a grounded recall gap: models answer and localize with moderate competence in isolation, yet fall furthest short of human performance when both must hold for the same query, the strongest reaching less than half the human rate. S-EMBER establishes a hardware-authentic foundation for developing grounded, reliable episodic memory in the next generation of wearable AI agents.

arXiv

Diffusion-Based Multi-Class Normality for OOD Detection: An Application to CDP Authentication

Bolutife Atoki, Iuliia Tkachenko, Bertrand Kerautret, Carlos Crispim-Junior

Reconstruction-based generative models offer a natural framework for unsupervised out-of-distribution (OOD) detection, but multi-class normality modelling requires a single detector to capture multiple in-distribution manifolds and produce comparable anomaly scores across classes. We study this problem in copy detection pattern (CDP) authentication, where authentic and counterfeit samples are visually similar but differ in subtle printing-and-digitisation (P&D) signatures. We propose a diffusion-based multi-class normality framework in which a single class-conditional ControlNet is trained exclusively on authentic CDPs from multiple P&D classes and detects counterfeits through reconstruction error under authentic-class conditioning. We further introduce dual template masking, which hides complementary regions of the input template and scores only withheld pixels, reducing reliance on visible binary structure. On the Indigo 1 x 1 Base dataset, the proposed method outperforms traditional and adapted generative baselines under multi-class authentic-versus-counterfeit evaluation, without using counterfeit samples for training or threshold calibration.

arXiv

SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions

Siyuan Yao, Ziqi Wang, Ruiqi Yu, Junqi Huang, Wenqi Ren, Xiaochun Cao

Domain adaptive visual object tracking under adverse weather conditions has garnered significant attention in recent years. Despite the impressive performance, existing methods heavily rely on the large-scale video frames from both source and target domains, which is impractical under rigid resource constraints where source data is unavailable. To overcome this limitation, we propose SFDATrack, a generalized source-free domain adaptive tracker that merely leverages adverse weather samples from the target domain for robust state estimation. Specifically, SFDATrack first employs a mean-teacher backbone with Dual Interactive Mamba (DIM) blocks to distill the candidate target tokens that are resilient to weather variations from classified, augmented samples. Afterwards, we introduce a hyperspherical prototype projection (HPP) module to project these tokens onto multi-domain prototypes within a latent hyperspherical space. By enforcing both domain-specific and domain-invariant properties of the multi-domain prototypes, SFDATrack can be seamlessly adapted to diverse weather conditions with powerful generalizability. Extensive experiments evaluated on various benchmarks demonstrate that SFDATrack achieves superior performance compared to state-of-the-art approaches. The code is available at https://github.com/watcherBR0/sfdatrack.

arXiv

DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection

Hun Im, Jungi Lee, Subeen Cha, Pilsung Kang

In industrial environments, new product categories arrive sequentially, requiring continual anomaly detection without access to past data. Normalizing Flows (NFs) provide exact density estimation but suffer from catastrophic forgetting as parameter updates across tasks distort the density manifold. While parameter isolation can prevent interference, it must preserve the strict invertibility and Jacobian validity of NFs. To satisfy these requirements, we exploit the inherent property that affine coupling layers maintain transformation validity regardless of subnet parameterization. Based on this, we propose DeCoFlow, which decomposes subnets into a frozen universal base and task-specific low-rank adapters to isolate updates. We further introduce Task-Specific Alignment, Auxiliary Coupling Layers, and Tail-Aware Loss to compensate for frozen-base rigidity. DeCoFlow achieves state-of-the-art image-level AUROCs of 98.40% on MVTec-AD and 93.00% on VisA, while maintaining parameter-level zero forgetting (0.00% FM under correct routing) with only 2.27M parameters per task.

arXiv

Rendering Novel Views of MRI Using 3D Gaussian Splatting

Robin Y. Park, Mark C. Eid, Rhydian Windsor, Amir Jamaludin, Ana I. L. Namburete, João F. Henriques, Andrew Zisserman

The objective of this paper is to improve radiological gradings measured on MRIs of spines, by resampling scans so that the new view planes are better aligned with the target anatomy than the original sparse images. To this end, we adapt 3D Gaussian Splatting to form a volumetric reconstruction starting from non-aligned MRIs to render imaging planes aligned with the anatomy relevant for clinical evaluation. The novel view plane is optimal for diagnostic radiological grading of the target anatomy, whereas the original MRI is not. The resampled scans are then used to predict ordinal severity grades of localised stenosis conditions in spinal MRIs. We compare our method against (1) Voxel Interpolation, which takes the average of inverse-distance weighted nearest neighbour intensities for each target coordinate, and (2) Cubic B-spline resampling, which estimates target points using a smooth piecewise-cubic function built from the source points. Experiments show that across all stenosis conditions, resampled scans using Gaussian Splatting produce more accurate stenosis gradings compared to the raw scans which do not include the complete anatomy in-plane, as well as images resampled using Voxel Interpolation or Cubic B-spline resampling.

arXiv

Context-Guided Semantic Alignment for Feature Fusion Networks

Hyungseop Lee, Jiho Lee, Woochul Kang

Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes. However, directly fusing features from different pyramid levels often introduces semantic inconsistency, causing information conflicts that distort the fused representation and degrade detection accuracy. In this paper, we propose Feature Interaction NEtwork (FINE), a lightweight semantic alignment module that refines low-level features via high-level contextual guidance using cross-level attention prior to fusion. To bridge the structural gap and ensure computational efficiency, we introduce an Alignment-Aware Token Sampling that aligns corresponding spatial regions across scales, reducing the attention complexity by an order of magnitude. % The resulting attention weights generate a spatial-channel modulation map that is upsampled and applied to the low-level features via residual element-wise modulation. The resulting attention weights generate a spatial-channel modulation map that is applied to the low-level features via residual modulation. This mechanism ensures that the network selectively enhances semantically relevant pixels while preserving the sub-pixel localization accuracy necessary for dense prediction tasks. FINE is generally applicable to various detectors and consistently improves detection accuracy with minimal computational overhead. Our code is publicly available at https://github.com/HyungseopLee/FINE.

arXiv

OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs

Yifei Li, Pengyiang Liu, Yuhang Zang, Zhongyue Shi, Qi Fu, Hongye Hao, Jiwen Lu

Multimodal agents in robotics, AR, and autonomous driving must reason about places and layouts from continuous egocentric streams, often using evidence outside the current view. Existing benchmarks either evaluate offline over full videos or target events rather than spatial structure. We introduce OVO-S-Bench, a fully human-annotated benchmark for streaming spatial intelligence, comprising 1,680 questions over 348 source videos. Annotation involves 12 trained annotators (each also serving as a blind cross-reviewer) across roughly 804 person-hours of multi-round quality assurance. Each question carries a query timestamp and an evidence interval, and at evaluation, the model sees only the prefix preceding the query. Questions span four levels of increasing abstraction: instantaneous egocentric perception, spatiotemporal context tracking, generative spatial reasoning, and allocentric spatial mapping. Across 38 proprietary and open-source MLLMs, Gemini-3.1-Pro trails human experts evaluated under the same prefix-access protocol by 33 points (59.2 vs. 92.2), with allocentric spatial mapping as the dominant bottleneck. Notably, streaming and spatially fine-tuned MLLMs underperform their own backbones. We further find that chain-of-thought reasoning amplifies spatial errors when ungrounded in the stream. By exposing these limitations, OVO-S-Bench establishes a demanding testbed for next-generation streaming spatial MLLMs.

arXiv

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

Jiawei Guo, Yu Chen, Xiang Wang, Shuai Li, Xinpei Zhao, Huaxing Liu, Shuai Dong, Feifei Zhai, Yu Zhou

Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains are commonly attributed to the tokens encoding visual evidence; recent analyses, however, reveal a paradox: the tokens are loosely tied to the image and contribute little to the answer. Critically, these analyses treat latent tokens as a single unit, obscuring the source of the gains. We therefore decompose latent tokens into three testable components: latent slots, boundary markers, and format, and develop a state-of-the-art method as a probe under favorable conditions. Across six method-stage settings and four perception-heavy benchmarks, latent slots fail every prediction of the visual-memory account. Strikingly, retaining only the boundary markers preserves 78 to 100% of the gain in several settings, while the model attends to the image more narrowly at latent positions than at answer positions. These results do not support slot contents as recoverable visual memory; much of the benefit is instead associated with marker and format control, together with visual-attention routing. At matched accuracy, methods can still rely on markedly different mechanisms shaped by training supervision. Latent visual reasoning thus needs evaluation not only by accuracy but by what the model actually relies on.

arXiv

Minimalist Visual Inertial Odometry

Francesco Pasti, Jeremy Klotz, Nicola Bellotto, Shree K. Nayar

Visual-Inertial Odometry (VIO), which is critical to mobile robot navigation, uses cameras with a large number of pixels. Capturing and processing camera images requires significant resources. This work presents a minimalist approach to planar odometry, showing that just four visual sensors (pixels) and an IMU provide robust motion estimation for differential-drive robots. Our key insight is that four downward-facing photodiodes that sense the world through optical Gabor masks produce signals that encode speed. Based on this, we jointly optimize the mask parameters alongside a Temporal Convolutional Network (TCN) using a physically-grounded simulator. The resulting model decodes speed from the four photodiode measurements. Pairing these estimates with an IMU's angular speed yields a continuous planar trajectory. We validate our approach with a prototype sensor mounted on a differential drive robot. Across diverse indoor and outdoor terrains, our system closely tracks the reference trajectories without any real-world fine-tuning. Our work shows that minimalist sensing enables efficient and accurate planar odometry.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →