论文检索

Computer Vision · Classification and Understanding

Zhongao Zhou, Bin Yang, Wenke Huang, Jun Chen, Mang Ye

In object re-identification (ReID) task, both cross-modal and multi-modal retrieval methods have achieved notable progress. However, existing approaches are designed for specific modality and category (person or vehicle) retrieval task, lacking generalizability to others. Acquiring multiple task-specific models would result in wasteful allocation of both training and deployment resources. To address the practical requirements for unified retrieval, we introduce Multi-Modal and Multi-Task object ReID ($\rm {M^3T}$-ReID). The $\rm {M^3T}$-ReID task aims to utilize a unified model to simultaneously achieve retrieval tasks across different modalities and different categories. Specifically, to tackle the challenges of modality distibution divergence and category semantics discrepancy posed in $\rm {M^3T}$-ReID, we design a novel Unbiased Prototype Consistency Learning (UPCL) framework, which consists of two main modules: Unbiased Prototypes-guided Modality Enhancement (UPME) and Cluster Prototype Consistency Regularization (CPCR). UPME leverages modality-unbiased prototypes to simultaneously enhance cross-modal shared features and multi-modal fused features. Additionally, CPCR regulates discriminative semantics learning with category-consistent information through prototypes clustering. Under the collaborative operation of these two modules, our model can simultaneously learn robust cross-modal shared feature and multi-modal fused feature spaces, while also exhibiting strong category-discriminative capabilities. Extensive experiments on multi-modal datasets RGBNT201 and RGBNT100 demonstrates our UPCL framework showcasing exceptional performance for $\rm {M^3T}$-ReID. The code is available at https://github.com/ZhouZhongao/UPCL.

Social Aspects · Trustworthy Machine Learning

Andre Kassis, Urs Hengartner, Yaoliang Yu

Diffusion-based purification (DBP) has become a cornerstone defense against adversarial examples (AEs), regarded as robust due to its use of diffusion models (DMs) that project AEs onto the natural data manifold. We refute this core claim, theoretically proving that gradient-based attacks effectively target the DM rather than the classifier, causing DBP's outputs to align with adversarial distributions. This prompts a reassessment of DBP's robustness, accrediting it two critical factors: inaccurate gradients and improper evaluation protocols that test only a single random purification of the AE. We show that when accounting for stochasticity and resubmission risk, DBP collapses. To support this, we introduce DiffBreak, the first reliable toolkit for differentiation through DBP, eliminating gradient mismatches that previously further inflated robustness estimates. We also analyze the current defense scheme used for DBP where classification relies on a single purification, pinpointing its inherent invalidity. We provide a statistically grounded majority-vote (MV) alternative that aggregates predictions across multiple purified copies, showing partial but meaningful robustness gain. We then propose a novel adaptation of an optimization method against deepfake watermarking, crafting systemic perturbations that defeat DBP even under MV, challenging DBP's viability.

Computer Vision · Classification and Understanding

Ilona Demler, Saumya Chauhan, Georgia Gkioxari

We introduce ITTO, a challenging new benchmark suite for evaluating and diagnosing the capabilities and limitations of point tracking methods. Our videos are sourced from existing datasets and egocentric real-world recordings, with high-quality human annotations collected through a multi-stage pipeline. ITTO captures the motion complexity, occlusion patterns, and object diversity characteristic of real-world scenes -- factors that are largely absent in current benchmarks. We conduct a rigorous analysis of state-of-the-art tracking methods on ITTO, breaking down performance along key axes of motion complexity. Our findings reveal that existing trackers struggle with these challenges, particularly in re-identifying points after occlusion, highlighting critical failure modes. These results point to the need for new modeling approaches tailored to real-world dynamics. We envision ITTO as a foundation testbed for advancing point tracking and guiding the development of more robust tracking algorithms.

Applications · Health

Pragya Singh, Ankush Gupta, Somay Jalan, Mohan Kumar, Pushpendra Singh

Emotion recognition from physiological signals has substantial potential for applications in mental health and emotion-aware systems. However, the lack of standardized, large-scale evaluations across heterogeneous datasets limits progress and model generalization. We introduce FEEL (Framework for Emotion Evaluation), the first large-scale benchmarking study of emotion recognition usingelectrodermal activity (EDA) and photoplethysmography (PPG) signals across 19 publicly available datasets. We evaluate 16 architectures spanning traditional machine learning, deep learning, and self-supervised pretraining approaches, structured into four representative modeling paradigms. Our study includes both within-dataset and cross-dataset evaluations, analyzing generalization across variations in experimental settings, device types, and labeling strategies. Our results showed that fine-tuned contrastive signal-language pretraining (CLSP) models (71/114) achieve the highest F1 across arousal and valence classification tasks, while simpler models like Random Forests, LDA, and MLP remain competitive (36/114). Models leveraging handcrafted features (107/114) consistently outperform those trained on raw signal segments, underscoring the value of domain knowledge in low-resource, noisy settings. Further cross-dataset analyses reveal that models trained on real-life setting data generalize well to lab (F1 = 0.79) and constraint-based settings (F1 = 0.78). Similarly, models trained on expert-annotated data transfer effectively to stimulus-labeled (F1 = 0.72) and self-reported datasets (F1 = 0.76). Moreover, models trained on lab-based devices also demonstrated high transferability to both custom wearable devices (F1 = 0.81) and the Empatica E4 (F1 = 0.73), underscoring the influence of heterogeneity. Overall, FEEL provides a unified framework for benchmarking physiological emotion recognition, delivering insights to guide the development of generalizable emotion-aware technologies. Code implementationis available at https://github.com/alchemy18/FEEL. More information about FEEL can be found on our website https://alchemy18.github.io/FEEL_Benchmark/.

Kai Yan, Zhan Ling, Kang Liu, Yifan Yang, Ting-Han Fan, Lingfeng Shen, Zhengyin Du, Jiecao Chen

The ability to recognize patterns from examples and apply them to new ones is a primal ability for general intelligence, and is widely studied by psychology and AI researchers. Many benchmarks have been proposed to measure such ability for Large Language Models (LLMs); however, they focus on few-shot (usually <10) setting and lack evaluation for aggregating many pieces of information from long contexts. On the other hand, the ever-growing context length of LLMs have brought forth the novel paradigm of many-shot In-Context Learning (ICL), which addresses new tasks with hundreds to thousands of examples without expensive and inefficient fine-tuning. However, many-shot evaluations often focus on classification, and popular long-context LLM tasks such as Needle-In-A-Haystack (NIAH) seldom require complicated intelligence for integrating many pieces of information. To fix the issues from both worlds, we propose MIR-Bench, the first many-shot in-context reasoning benchmark for pattern recognition that asks LLM to predict output via input-output examples from underlying functions with diverse data format. Based on MIR-Bench, we study many novel problems for many-shot in-context reasoning, and acquired many insightful findings including scaling effect, robustness, inductive vs. transductive reasoning, retrieval Augmented Generation (RAG), coding for inductive reasoning, cross-domain generalizability, etc. Our dataset is available at https://huggingface.co/datasets/kaiyan289/MIR-Bench.

Deep Learning · Generative Models and Autoencoders

Sai Niranjan Ramachandran, Manish Krishan Lal, Suvrit Sra

We analyse how the sampling dynamics of distributions evolve in score-based diffusion models using \emph{cross-fluctuations}, a centered-moment statistic from statistical physics. Specifically, we show that starting from an unbiased isotropic normal distribution, samples undergo sharp, discrete transitions, eventually forming distinct events of a desired distribution while progressively revealing finer structure. As this process is reversible, these transitions also occur in reverse, where intermediate states progressively merge, tracing a path back to the initial distribution. We demonstrate that these transitions can be detected as discontinuities in $n^{\text{th}}$-order cross-fluctuations. For variance-preserving SDEs, we derive a closed-form for these cross-fluctuations that is efficiently computable for the reverse trajectory. %, thus tying cross-fluctuation dynamics to event formation within the desired distribution. We find that detecting these transitions directly boosts sampling efficiency, accelerates class-conditional and rare-class generation, and improves two zero-shot tasks--image classification and style transfer--without expensive grid search or retraining. We also show that this viewpoint unifies classical coupling and mixing from finite Markov chains with continuous dynamics while extending to stochastic SDEs and non Markovian samplers. Our framework therefore bridges discrete Markov chain theory, phase analysis, and modern generative modeling.

Computer Vision · Vision Models & Multimodal

Thanh-Dat Truong, Christophe Bobda, Nitin Agarwal, Khoa Luu

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the multimodal model cannot capture the essential features of each modality, making it difficult to comprehend complex structures and correlations of multimodal inputs. This paper introduces a novel Multimodal Attention-based Normalizing Flow (MANGO) approach to developing explicit, interpretable, and tractable multimodal fusion learning. In particular, we propose a new Invertible Cross-Attention (ICA) layer to develop the Normalizing Flow-based Model for multimodal data. To efficiently capture the complex, underlying correlations in multimodal data in our proposed invertible cross-attention layer, we propose three new cross-attention mechanisms: Modality-to-Modality Cross-Attention (MMCA), Inter-Modality Cross-Attention (IMCA), and Learnable Inter-Modality Cross-Attention (LICA). Finally, we introduce a new Multimodal Attention-based Normalizing Flow to enable the scalability of our proposed method to high-dimensional multimodal data. Our experimental results on three different multimodal learning tasks, i.e., semantic segmentation, image-to-image translation, and movie genre classification, have illustrated the state-of-the-art (SoTA) performance of the proposed approach.

Deep Learning · Everything Else

Indrashis Das, Mahmoud Safari, Steven Adriaensen, Frank Hutter

Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuron problem, which has been mitigated by variants such as LeakyReLU, PReLU, and ELU that better handle negative neuron outputs. Recently, self-gated activations like GELU and Swish have emerged as state-of-the-art alternatives, leveraging their smoothness to ensure stable gradient flow and prevent neuron inactivity. In this work, we introduce the Gompertz Linear Unit (GoLU), a novel self-gated activation function defined as $\mathrm{GoLU}(x) = x \\, \mathrm{Gompertz}(x)$, where $\mathrm{Gompertz}(x) = e^{-e^{-x}}$. The GoLU activation leverages the right-skewed asymmetry in the Gompertz function to reduce variance in the latent space more effectively compared to GELU and Swish, while preserving robust gradient flow. Extensive experiments across diverse tasks, including Image Classification, Language Modeling, Semantic Segmentation, Object Detection, Instance Segmentation, and Diffusion, highlight GoLU's superior performance relative to state-of-the-art activation functions, establishing GoLU as a robust alternative to existing activation functions.

Computer Vision · Classification and Understanding

Chiara Cappellino, Gianluca Mancusi, Matteo Mosconi, Angelo Porrello, SIMONE CALDERARA, Rita Cucchiara

Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing their abilities on multiple specialized domains remains essential. While recent methods rely on monolithic adaptation strategies with a single set of weights, we embrace modular deep learning. We introduce DitHub, a framework designed to build and maintain a library of efficient adaptation modules. Inspired by Version Control Systems, DitHub manages expert modules as branches that can be fetched and merged as needed. This modular approach allows us to conduct an in-depth exploration of the compositional properties of adaptation modules, marking the first such study in Object Detection. Our method achieves state-of-the-art performance on the ODinW-13 benchmark and ODinW-O, a newly introduced benchmark designed to assess class reappearance.

Computer Vision · Classification and Understanding

Hao-Ran Yang, Xiaohui Chen, Chuan-Xian Ren

Aiming to generalize the well-trained gaze estimation model to new target domains, Cross-domain Gaze Estimation (CDGE) is developed for real-world application scenarios. Existing CDGE methods typically extract the domain-invariant features to mitigate domain shift in feature space, which is proved insufficient by Generalized Label Shift (GLS) theory. In this paper, we introduce a novel GLS perspective to CDGE and modelize the cross-domain problem by label and conditional shift problem. A GLS correction framework is presented and a feasible realization is proposed, in which a importance reweighting strategy based on truncated Gaussian distribution is introduced to overcome the continuity challenges in label shift correction. To embed the reweighted source distribution to conditional invariant learning, we further derive a probability-aware estimation of conditional operator discrepancy. Extensive experiments on standard CDGE tasks with different backbone models validate the superior generalization capability across domain and applicability on various models of proposed method.

Social Aspects · Accountability, Transparency and Interpretability

Rose Gurung, Ronilo Ragodos, Chiyu Ma, Tong Wang, Chaofan Chen

We present Prototypical Pair Network (ProtoPairNet), a novel interpretable architecture that combines deep learning with case-based reasoning to predict continuous targets. While prototype-based models have primarily addressed image classification with discrete outputs, extending these methods to continuous targets, such as regression, poses significant challenges. Existing architectures which rely heavily on one-to-one comparison with prototypes lack the directional information necessary for continuous predictions. Our method redefines the role of prototypes in such tasks by incorporating prototypical pairs into the reasoning process. Predictions are derived based on the input's relative dissimilarities to these pairs, leveraging an intuitive geometric interpretation. Our method further reduces the complexity of the reasoning process by relying on the single most relevant pair of prototypes, rather than all prototypes in the model as was done in prior works. Our model is versatile enough to be used in both vision-based regression and continuous control in reinforcement learning. Our experiments demonstrate that ProtoPairNet achieves performance on par with its black-box counterparts across these tasks. Comprehensive analyses confirm the meaningfulness of prototypical pairs and the faithfulness of our model’s interpretations, and extensive user studies highlight our model's improved interpretability over existing methods.

Computer Vision · Vision Models & Multimodal

Piyush Nitin Bagad, Andrew Zisserman

Our objective is to develop compact video representations that are sensitive to visual change over time. To measure such time-sensitivity, we introduce a new task: chiral action recognition, where one needs to distinguish between a pair of temporally opposite actions, such as “opening vs. closing a door", “approaching vs. moving away from something", “folding vs. unfolding paper", etc. Such actions (i) occur frequently in everyday life, (ii) require understanding of simple visual change over time (in object state, size, spatial position, count . . . ), and (iii) are known to be poorly represented by many video embeddings. Our goal is to build time aware video representations which offer linear separability between these chiral pairs. To that end, we propose a self-supervised adaptation recipe to inject time-sensitivity into a sequence of frozen image features. Our model is based on an auto-encoder with a latent space with inductive bias inspired by perceptual straightening. We show that this results in a compact but time-sensitive video representation for the proposed task across three datasets: Something-Something, EPIC-Kitchens, and Charade. Our method (i) outperforms much larger video models pre-trained on large-scale video datasets, and (ii) leads to an improvement in classification performance on standard benchmarks when combined with these existing models.

Computer Vision · Classification and Understanding

Zhiwei Yang, Chen Gao, Mike Zheng Shou

Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Previous methods typically rely on domain-specific training data and manual adjustments when applying to new scenarios and unseen anomaly types, suffering from high labor costs and limited generalization. Therefore, we aim to achieve generalist VAD, \ie, automatically handle any scene and any anomaly types without training data or human involvement. In this work, we propose PANDA, an agentic AI engineer based on MLLMs. Specifically, we achieve PANDA by comprehensively devising four key capabilities: (1) self-adaptive scene-aware strategy planning, (2) goal-driven heuristic reasoning, (3) tool-augmented self-reflection, and (4) self-improving chain-of-memory. Concretely, we develop a self-adaptive scene-aware RAG mechanism, enabling PANDA to retrieve anomaly-specific knowledge for anomaly detection strategy planning. Next, we introduce a latent anomaly-guided heuristic prompt strategy to enhance reasoning precision. Furthermore, PANDA employs a progressive reflection mechanism alongside a suite of context-aware tools to iteratively refine decision-making in complex scenarios. Finally, a chain-of-memory mechanism enables PANDA to leverage historical experiences for continual performance improvement. Extensive experiments demonstrate that PANDA achieves state-of-the-art performance in multi-scenario, open-set, and complex scenario settings without training and manual involvement, validating its generalizable and robust anomaly detection capability. Code is released at https://github.com/showlab/PANDA.

Theory · Domain Adaptation and Transfer Learning

Yuyao Wang, Yu-Hung Cheng, Debarghya Mukherjee, Huimin Cheng

Graphon models provide a flexible nonparametric framework for estimating latent connectivity probabilities in networks, enabling a range of downstream applications such as link prediction and data augmentation. However, accurate graphon estimation typically requires a large graph, whereas in practice, one often only observes a small-sized network. One approach to addressing this issue is to adopt a transfer learning framework, which aims to improve estimation in a small target graph by leveraging structural information from a larger, related source graph. In this paper, we propose a novel method, namely GTRANS, a transfer learning framework that integrates neighborhood smoothing and Gromov-Wasserstein optimal transport to align and transfer structural patterns between graphs. To prevent negative transfer, GTRANS includes an adaptive debiasing mechanism that identifies and corrects for target-specific deviations via residual smoothing. We provide theoretical guarantees on the stability of the estimated alignment matrix and demonstrate the effectiveness of GTRANS in improving the accuracy of target graph estimation through extensive synthetic and real data experiments. These improvements translate directly to enhanced performance in downstream applications, such as the graph classification task and the link prediction task.

Computer Vision · Classification and Understanding

Zhao Jin, Rong-Cheng Tu, Jingyi Liao, Wenhao Sun, Xiao Luo, Shunyu Liu, Dacheng Tao

3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER — a VLM-driven agent that combines both modalities in a progressive reasoning framework. It first holistically analyzes the scene and produces a 3D rendering from the optimal viewpoint. Based on this, anchor-guided candidate screening is conducted to perform a coarse-level localization of potential objects. Furthermore, leveraging retrieved relevant 2D camera images, 3D-2D joint decision-making is efficiently performed to determine the best-matching object. By bridging spatial and semantic reasoning neural streams, SPAZER achieves robust zero-shot grounding without training on 3D-labeled data. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate that SPAZER significantly outperforms previous state-of-the-art zero-shot methods, achieving notable gains of $\mathbf{9.0\}$% and $\mathbf{10.9\}$% in accuracy.

Deep Learning · Graph Neural Networks

Adarsh Jamadandi, Jing Xu, Adam Dziedzic, Franziska Boenisch

Deep neural networks (DNNs) have been shown to memorize their training data, but similar analyses for graph neural networks (GNNs) remain under-explored. We introduce NCMemo (Node Classification Memorization), the first framework to quantify label memorization in semi-supervised node classification. We establish an inverse relationship between memorization and graph homophily, i.e the tendency of connected nodes to share labels or features. Lower homophily significantly increases memorization, indicating that GNNs rely on label memorization when learning less homophilic graphs. We then analyze GNN training dynamics and find that increased memorization in low-homophily graphs is tightly coupled to GNNs' implicit bias toward using graph structure. When structure is less informative, models instead memorize node labels to minimize training loss. Finally, we show that nodes with higher label inconsistency in their feature-space neighborhood are more prone to memorization. Based on these insights, we investigate graph rewiring as a mitigation strategy. Our results show that rewiring reduces memorization without harming model performance, while also lowering the privacy risk for previously memorized data points. Thus, our work advances understanding of GNN learning and supports more privacy-preserving GNN deployment.

Deep Learning · Graph Neural Networks

Antonin Joly, Nicolas Keriven, Aline Roumy

Graph coarsening aims to diminish the size of a graph to lighten its memory footprint, and has numerous applications in graph signal processing and machine learning. It is usually defined using a reduction matrix and a lifting matrix, which, respectively, allows to project a graph signal from the original graph to the coarsened one and back. This results in a loss of information measured by the so-called Restricted Spectral Approximation (RSA). Most coarsening frameworks impose a fixed relationship between the reduction and lifting matrices, generally as pseudo-inverses of each other, and seek to define a coarsening that minimizes the RSA. In this paper, we remark that the roles of these two matrices are not entirely symmetric: indeed, putting constraints on the *lifting matrix alone* ensures the existence of important objects such as the coarsened graph's adjacency matrix or Laplacian. In light of this, in this paper, we introduce a more general notion of reduction matrix, that is *not* necessarily the pseudo-inverse of the lifting matrix. We establish a taxonomy of ``admissible'' families of reduction matrices, discuss the different properties that they must satisfy and whether they admit a closed-form description or not. We show that, for a *fixed* coarsening represented by a fixed lifting matrix, the RSA can be *further* reduced simply by modifying the reduction matrix. We explore different examples, including some based on a constrained optimization process of the RSA. Since this criterion has also been linked to the performance of Graph Neural Networks, we also illustrate the impact of this choices on different node classification tasks on coarsened graphs.

Deep Learning · Algorithms

Erel Naor, Ofir Lindenbaum

Deep neural networks often under-perform on tabular data due to their sensitivity to irrelevant features and a spectral bias toward smooth, low-frequency functions. These limitations hinder their ability to capture the sharp, high-frequency signals that often define tabular structure, especially under limited labeled samples. While self-supervised learning (SSL) offers promise in such settings, it remains challenging in tabular domains due to the lack of effective data augmentations. We propose a hybrid autoencoder that combines a neural encoder with an oblivious soft decision tree (OSDT) encoder, each guided by its own stochastic gating network that performs sample-specific feature selection. Together, these structurally different encoders and model-specific gating networks implement model-based augmentation, producing complementary input views tailored to each architecture. The two encoders, trained with a shared decoder and cross-reconstruction loss, learn distinct yet aligned representations that reflect their respective inductive biases. During training, the OSDT encoder (robust to noise and effective at modeling localized, high-frequency structure) guides the neural encoder toward representations more aligned with tabular data. At inference, only the neural encoder is used, preserving flexibility and SSL compatibility. Spectral analysis highlights the distinct inductive biases of each encoder. Our method achieves consistent gains in low-label classification and regression across diverse tabular datasets, outperforming deep and tree-based supervised baselines.

Computer Vision · 3D Rendering & Reconstruction

Wuyang Li, Zhu Yu, Alexandre Alahi

Semantic Scene Completion (SSC) aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate SSC as a *dense segmentation task*, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a "free lunch" of SSC labels: the voxel-level class label has implicitly told the instance-level insight, which is ever-overlooked by the community. Motivated by this observation, we first introduce a training-free **Voxel-to-Instance (VoxNT) trick**: a simple yet effective method that freely converts voxel-level class labels into instance-level offset labels. Building on this, we further propose **VoxDet**, an instance-centric framework that reformulates the voxel-level SSC as *dense object detection* by decoupling it into two sub-tasks: offset regression and semantic prediction. Specifically, based on the lifted 3D volume, VoxDet first uses (a) Spatially-decoupled Voxel Encoder to generate disentangled feature volumes for the two sub-tasks, which learn task-specific spatial deformation in the densely projected tri-perceptive space. Then, we deploy (b) Task-decoupled Dense Predictor to address SSC via dense detection. Here, we first regress a 4D offset field to estimate distances (6 directions) between voxels and the corresponding object boundaries in the voxel space. The regressed offsets are then used to guide the instance-level aggregation in the classification branch, achieving instance-aware scene completion. VoxDet can be deployed on both camera and LiDAR input and jointly achieves state-of-the-art results on both benchmarks, which gives 63.0 IoU on the SemanticKITTI test set, **ranking 1$^{st}$** on the online leaderboard.

Computer Vision · Vision Models & Multimodal

Dmitry Lvov, Ilya Pershin

Predicting human eye movements during goal-directed visual search is critical for enhancing interactive AI systems. In medical imaging, such prediction can support radiologists in interpreting complex data, such as chest X-rays. Many existing methods rely on generic vision--language models and saliency-based features, which can limit their ability to capture fine-grained clinical semantics and integrate domain knowledge effectively. We present \textbf{LogitGaze-Med}, a state-of-the-art multimodal transformer framework that unifies (1) domain-specific visual encoders (e.g., CheXNet), (2) textual embeddings of diagnostic labels, and (3) semantic priors extracted via the logit-lens from an instruction-tuned medical vision--language model (LLaVA-Med). By directly predicting continuous fixation coordinates and dwell durations, our model generates clinically meaningful scanpaths. Experiments on the GazeSearch dataset and synthetic scanpaths generated from MIMIC-CXR and validated by experts demonstrate that LogitGaze-Med improves scanpath similarity metrics by 20--30\% over competitive baselines and yields over 5\% gains in downstream pathology classification when incorporating predicted fixations as additional training data.