CVPR 2026 论文列表

Vision-language models (VLMs) have demonstrated strong potential for adapting to downstream biomedical tasks with limited training samples. However, their generalization to unseen classes within the same dataset remains limited, as the image-text alignment semantics often rely on spurious cues present in seen classes that do not transfer. To tackle this, we propose BiomedCCPL (Causal Conditional Prompt Learning), a framework that uses VGAP (Visual Grounder with Adaptive Prototype) to generate image-conditional prompts from multi-scale adaptive prototypes and employs SCD (Synergistic Causal Disentanglement) to regularize the generation of image-conditional prompts. Guided by insights from a causal analysis of generalization to unseen classes, SCD leverages multiple synergistic learning objectives to perform front-door adjustment, ensuring that the dynamically generated image-conditional prompts focus on underlying diagnostic image features shared across seen and unseen classes. Experiments on 11 datasets across 9 modalities demonstrate that BiomedCCPL effectively enhances the model's data efficiency and generalization ability. In particular, on the Base-to-Novel task, BiomedCCPL achieves an average HM of 79.98%, surpassing the previous state-of-the-art by 6.45%. Code is available at https://github.com/burgers0708/BiomedCCPL.

Multi-model routing has evolved from an engineering technique into essential infrastructure, yet existing work lacks a systematic, reproducible benchmark for evaluating vision-language models (VLMs). We present VL-RouterBench to assess the overall capability of VLM routing systems systematically. The benchmark is grounded in raw inference and scoring logs from VLMs and constructs quality and cost matrices over sample-model pairs. In scale, VL-RouterBench covers 14 datasets across 3 task groups, totaling 30,540 samples, and includes 15 open-source models and 2 API models, yielding 519,180 sample-model pairs and a total input-output token volume of 34,494,977. The evaluation protocol jointly measures average accuracy, average cost, and throughput, and builds a ranking score from the harmonic mean of normalized cost and accuracy to enable comparison across router configurations and cost budgets. On this benchmark, we evaluate 10 routing methods and baselines and observe a significant routability gain, while the best current routers still show a clear gap to the ideal Oracle, indicating considerable room for improvement in router architecture through finer visual cues and modeling of textual structure. We open-source the complete data construction and evaluation toolchain to promote comparability, reproducibility, and practical deployment in multimodal routing research.

Vision-language models (VLMs) with dynamic resolution vision encoders achieve strong performance, but face significant efficiency challenges due to long input sequences. A common approach is to assess the importance of tokens and prune those that are less informative. Recent methods utilizing a small VLM to provide the importance map of visual tokens have outperformed existing rule-based and similarity-driven pruning approaches, particularly under high pruning ratios. However, directly using the small VLM remains unreliable, as it utilizes the aggregated visual attention weights as importance score, which can lead to noisy guidance if the generated tokens are incorrect.To address this, we invert the approach by having it detect non-informative visual tokens according to the user's input query. By adding a variational information bottleneck in the small VLM, we can approximate the entropy of each visual token as pruning guidance. Such a posteriori-guided pruning method allows the large VLM to retain its reasoning capacity with improved efficiency. Extensive experiments on eight benchmarks demonstrate the effectiveness of our approach. With only 5% of visual tokens retained, the large VLM preserves 95% of its original performance, outperforming the state of the art by 8%.

Effective medical image analysis requires representations that capture both global anatomical structure and fine-grained tissue texture. Current self-supervised approaches exhibit limited capacity to address both requirements simultaneously. Invariance-based methods learn through augmentation consistency but face challenges in medical imaging where common augmentations may discard diagnostically relevant intensity patterns. Masked image modeling approaches employ high masking ratios to enforce holistic reasoning, yet inherently limit exposure to fine-grained texture. Recent work in general-domain vision demonstrates that generative and semantic objectives can mutually benefit each other, yet this paradigm remains unexplored for 3D medical imaging. We introduce Masked-Diffusion Autoencoders (MDAE), a self-supervised framework that imposes concurrent spatial masking and diffusion corruption, encouraging the model to learn complementary objectives: masked region reconstruction for structural coherence and visible region denoising for textural characteristics. This dual corruption enables the network to learn structure-texture representations within a unified time-conditioned objective. Evaluated on brain MRI across tumor classification, molecular marker detection, and dense segmentation benchmarks, MDAE consistently outperforms state-of-the-art baselines, with improvements most pronounced in cross-modal generalization tasks.

Bayesian deep learning (BDL) integrates Bayesian inference with deep learning, improving predictive performance while enabling principled uncertainty quantification. However, existing BDLs often rely on non-informative random priors, limiting the benefits of Bayesian inference. In contrast, knowledge-augmented deep learning explicitly injects domain knowledge during training, yet lacks a probabilistic foundation. In this paper, we propose a knowledge-augmented BDL framework that integrates domain knowledge both as an informative prior and as an adaptive likelihood under a unified two-stage hybrid formulation. In the first stage, we learn a knowledge-informed prior p(\theta \mid \mathcal K ) by pre-training a model to satisfy domain-specific constraints. In the second stage, we perform Bayesian inference on task data with an adaptive knowledge likelihood p(\mathcal K \mid \theta, \mathcal D ), which dynamically enforces these constraints during optimization. This unified framework enables knowledge to guide both initialization and training, significantly improving prediction accuracy, robustness, adaptation and uncertainty estimation. Experiments on various computer vision tasks, including semi-synthetic and real-knowledge scenarios, demonstrate that our two-stage framework consistently outperforms state-of-the-art Bayesian and knowledge-augmented baselines.

Robotic manipulation in complex 3D environments requires unifying spatial reasoning with intuitive visual perception, which is a capability that current Vision-Language-Action paradigms address separately. While 3D VLAs excel in geometric and physical reasoning, they lack intuitive, image-level understanding and dense visual semantics; conversely, 2D VLAs (even with depth image) provide rich visual intuition and semantic continuity but miss explicit spatial global grounding. We introduce DiffRender-VLA, a differentiable rendering-based framework that bridges 3D and 2D Vision-Language-Action models through gradient-consistent visual mediation. It generates differentiable images by localizing the next end-effector target with a world-aligned cube marker, differentiably structuring surrounding geometry whose color encodes spatial relations to the marker, and rendering adaptive viewpoints optimized to reveal the target-environment spatial relationships. These differentiable images serve as visual bridges, embedding spatial semantics while allowing gradients from 2D VLAs to backpropagate into 3D representations, thereby coupling geometric reasoning with visual perception. This closed differentiable loop unifies reasoning and perception, substantially improving performance under occlusion, clutter, and complex spatial manipulation tasks, achieving average improvements of +12.1% over state-of-the-art methods. Codes are available at https://github.com/zyl123456aB/DIFFVLA.

Humans commonly reason about object affordance through observed interactions in images or videos, and once formed, such knowledge can be generically generalized to novel objects. Inspired by this principle, we advocate for a novel framework that leverages emerging multimodal large language models (MLLMs) for interaction intention-driven 3D affordance grounding, namely HAMMER. Instead of generating explicit object attribute descriptions or relying on off-the-shelf 2D segmenters, we alternatively aggregate the interaction intention depicted in the reference image into a contact-aware embedding and guide the model to infer textual affordance labels, ensuring it thoroughly excavates object semantics and contextual cues. We further devise a hierarchical cross-modal integration mechanism to fully exploit the complementary information from the MLLM for 3D representation refinement and introduce a multi-granular geometry lifting module that infuses spatial characteristics into the extracted intention embedding, thus facilitating accurate 3D affordance localization. Extensive experiments on public datasets and our newly constructed corrupted benchmark reveal the superiority and robustness of our method in seen and unseen scenarios compared to existing approaches. The code and models will be made publicly available.

Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve representation quality and cross-modal alignment under tight compute and memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the loss level, it matches joint distributions on the unit hypersphere using a geometry-aware matching objective that exploits the joint features in the cross-modal alignment and discrepancy directions along with symmetric contrastive learning. Across image-text retrieval benchmarks with cross-architecture evaluation, MDM yields compact synthetic sets that preserve multimodal semantics, substantially reduce distillation cost, and remain robust across architectures.

Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral coverage, making RGB-only inference highly desirable for scalable deployment, the adoption of VLFMs for satellite imagery remains hindered by two factors: (1) multi-spectral inputs are informative but difficult to exploit consistently due to band redundancy and misalignment; and (2) CLIP-style text encoders limit semantic expressiveness and weaken fine-grained alignment. We present SATtxt, a VLFM that operates with RGB inputs at inference while retaining spectral cues learned during training and producing rich cross-modal representations. Our framework comprises two stages. First, Spectral Representation Distillation transfers spectral priors from a frozen multi-spectral teacher to an RGB student via a lightweight projector. Second, Spectrally Grounded Alignment with Instruction-Augmented LLMs bridges the distilled visual space and an expressive LLM embedding space. Across satellite benchmarks, SATtxt improves zero-shot classification on average by 4.2%, retrieval by 5.9%, linear probing by 2.7%, and open-vocabulary segmentation by 2.8% over baselines, showing an efficient path toward spectrum-aware vision-language learning for Earth observation. Project page: https://ikhado.github.io/sattxt/

We introduce the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization based on perceptual indistinguishability, rather than identity replication. A model passes the VPTT if its output (image, video, 3D asset, etc.) is indistinguishable to a human or calibrated VLM judge from content a given person might plausibly create or share. To operationalize VPTT, we present the VPTT Framework, integrating a 10k-persona benchmark (VPTT-Bench), a visual retrieval-augmented generator (VPRAG), and the VPTT Score, a text-only metric calibrated against human and VLM judgments. We show high correlation across human, VLM, and VPTT evaluations, validating the VPTT Score as a reliable perceptual proxy. Experiments demonstrate that VPRAG achieves the best alignment-originality balance, offering a scalable and privacy-safe foundation for personalized generative AI.

Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, the "linearity problem" causing recent CBMs to bypass the concept bottleneck entirely, an accuracy gap compared to opaque models, and finally the lack of systematic study on the impact of different visual backbones and VLMs. We introduce CBM-Suite, a methodological framework to systematically addresses these challenges. First, we propose an entropy-based metric to quantify the intrinsic suitability of a concept set for a given dataset. Second, we resolve the linearity problem by inserting a non-linear layer between concept activations and the classifier, which ensures that model accuracy faithfully reflects concept relevance. Third, we narrow the accuracy gap by leveraging a distillation loss guided by a linear teacher probe. Finally, we provide comprehensive analyses on how different vision encoders, vision-language models, and concept sets interact to influence accuracy and interpretability in CBMs. Extensive evaluations show that CBM-Suite yields more accurate models and provides insights for improving concept-based interpretability.

Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets, which fundamentally erodes PEFT's efficiency promise. In this work, we introduce SEATrack, a Simple, Efficient, and Adaptive two-stream multimodal tracker that tackles this performance-efficiency dilemma from two complementary perspectives. We first prioritize cross-modal alignment of matching responses, an underexplored yet pivotal factor that we argue is essential for breaking the trade-off. Specifically, we observe that modality-specific biases in existing two-stream methods generate conflicting matching attention maps, thereby hindering effective joint representation learning. To mitigate this, we propose AMG-LoRA, which seamlessly integrates Low-Rank Adaptation (LoRA) for domain adaptation with Adaptive Mutual Guidance (AMG) to dynamically refine and align attention maps across modalities. We then depart from conventional local fusion approaches by introducing a Hierarchical Mixture of Experts (HMoE) that enables efficient global relation modeling, effectively balancing expressiveness and computational efficiency in cross-modal fusion. Equipped with these innovations, SEATrack advances notable progress over state-of-the-art methods in balancing performance with efficiency across RGB-T, RGB-D, and RGB-E tracking tasks. Code is available.

We aim to learn a joint representation between inertial measurement unit (IMU) signals and 2D pose sequences extracted from video, enabling accurate cross-modal retrieval, temporal synchronization, subject and body-part localization, and action recognition. To this end, we introduce MoBind, a hierarchical contrastive learning framework designed to address three challenges: (1) filtering out irrelevant visual background, (2) modeling structured multi-sensor IMU configurations, and (3) achieving fine-grained, sub-second temporal alignment. To isolate motion-relevant cues, MoBind aligns IMU signals with skeletal motion sequences rather than raw pixels. We further decompose full-body motion into local body-part trajectories, pairing each with its corresponding IMU to enable semantically grounded multi-sensor alignment. To capture detailed temporal correspondence, MoBind employs a hierarchical contrastive strategy that first aligns token-level temporal segments, then fuses local (body-part) alignment with global (body-wide) motion aggregation. Evaluated on mRi, TotalCapture, and EgoHumans, MoBind consistently outperforms strong baselines across all four tasks, demonstrating robust fine-grained temporal alignment while preserving coarse semantic consistency across modalities.

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors remains unclear. To address this, we introduce VisRes Bench, a benchmark designed to study visual reasoning in naturalistic settings without contextual language supervision. Analyzing model behavior across three levels of complexity, we uncover clear limitations in perceptual and relational visual reasoning capacities. VisRes isolates distinct reasoning abilities across its levels. Level 1 probes perceptual completion and global image matching under perturbations such as blur, texture changes, occlusion, and rotation; Level 2 tests rule-based inference over a single attribute (e.g., color, count, orientation); and Level 3 targets compositional reasoning that requires integrating multiple visual attributes. Across more than 19,000 controlled task images, we find that state-of-the-art VLMs perform near random under subtle perceptual perturbations, revealing limited abstraction beyond pattern recognition. We conclude by discussing how VisRes provides a unified framework for advancing abstract visual reasoning in multimodal research (https://visres-bench.github.io).

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decisionmaking. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies noisy, high-entropy signals and is especially harmful under large teacher-student capacity gaps. We introduce SelecTKD, a plug-and-play Selective Token-Weighted distillation framework that shifts the focus from "how to measure divergence" to "where to apply learning". At each step, the student proposes tokens that are verified by the teacher through a robust propose-and-verify procedure with two variants: greedy Top-k and non-greedy Spec-k. Accepted tokens receive full loss, while rejected tokens are masked or down-weighted. This objective-agnostic design works with on- and off-policy data, induces an implicit curriculum quantified by Token Acceptance Rate (TAR), and stabilizes optimization. Across instruction following, mathematical reasoning, code generation, and a VLM setting, SelecTKD consistently improves strong baselines and achieves state-of-the-art results for small models without architectural changes or extra reference models.

Accurate focus quality assessment (FQA) in fluorescence microscopy is challenging due to stain-dependent optical variations that induce heterogeneous focus behavior across images. Existing methods, however, treat focus quality as a stain-agnostic problem, assuming a shared global ordering. We formulate stain-aware FQA for fluorescence microscopy, showing that focus-rank relationships vary substantially across stains due to stain-dependent imaging characteristics and invalidate this assumption. To support this formulation, we introduce FluoMix, the first dataset for stain-aware FQA spanning multiple tissues, fluorescent stains, and focus levels. We further propose FluoCLIP, a two-stage vision-language framework that grounds stain semantics and enables stain-conditioned ordinal reasoning for focus prediction, effectively decoupling stain representation from ordinal structure. By explicitly modeling stain-dependent focus behavior, FluoCLIP consistently outperforms both conventional FQA methods and recent vision-language baselines, demonstrating strong generalization across diverse fluorescence microscopy conditions. Code and dataset are publicly available at https://fluoclip.github.io/.

Recent Vision-Language-Action (VLA) models map visual-textual inputs to robotic actions via end-to-end architectures, yet this approach entangles visual understanding with task-specific actions. This leads to an exhaustive collection of full operational sequences and parameter redundancy across tasks, while generic third-person camera setups require fine-tuning for different hardware due to implicit hand-eye assumptions. We argue that decoupling how robots see from how robots act is a missing primitive in VLA systems. We present EgoRoC, a plug-and-play egocentric alignment head that precedes any task policy and exposes only a thin 6-DoF pose interface. EgoRoC establishes task-agnostic viewpoint consistency from a wrist-mounted (first-person) camera and then alternates alignment with manipulation, while a diffusion-based online hand-eye module corrects the action in the end-effector frame for hardware-agnostic deployment. Trained once from static wrist-target image pairs with relative poses, rather than full manipulation trajectories, EgoRoC leaves downstream VLAs unchanged. By turning egocentric alignment into a reusable capability, EgoRoC reduces training redundancy, strengthens zero-shot cross-scene transfer, and scales across VLA backbones without manual calibration. Across simulation and real settings, attaching EgoRoC consistently boosts success rates, especially on long-horizon and out-of-distribution tasks, and improves data efficiency during fine-tuning.

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.