CVPR 2026 论文列表

Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify task-relevant interaction cues or track progress within a subtask, leading to critical execution errors such as repeated actions, missed steps, and premature termination. To address these challenges, we introduce PALM, a VLA framework that structures policy learning around interaction-centric affordance reasoning and subtask progress cues. PALM distills complementary affordance representations that capture object relevance, contact geometry, spatial placements, and motion dynamics, and serve as task-relevant anchors for visuomotor control. To further stabilize long-horizon execution, PALM predicts continuous within-subtask progress, enabling seamless subtask transitions. Across extensive simulation and real-world experiments, PALM consistently outperforms baselines, achieving a 91.8% success rate on LIBERO-LONG, a 12.5% improvement in average length on CALVIN ABC->D, and a 2ximprovement over real-world baselines across three long-horizon generalization settings.

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce **HierEdit**, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (**Local-Window MMDiT**) that refines only edited regions within the original high-resolution image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (**Inference Acceleration**) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without requiring any specialized high-resolution training data. Extensive experiments demonstrate that **HierEdit** achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing.

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and answer of VLMs consist of long sequences of visual and text tokens. This paper presents AttentionPack, an adaptive and attention-aware optimization framework tailored for large vision-language models with improving memory-efficiency during decoding, focusing on addressing the challenges due to the increased high number of visual inputs and interactions, particularly in long-context tasks with multiple high-resolution images or videos. AttentionPack is novel in two aspects: (i) We introduce a multi-head attention compaction method for economically storing key and value matrices by exploiting the implicit low-rank structure, and (ii) we develop a token-specific attention-aware decompression mechanism to reduce latency overhead. Experimental results on multiple benchmarks demonstrate that AttentionPack improves memory efficiency by up to 8x, enabling higher batch sizes and faster batch inference while preserving the model output quality or longer context lengths for superior retrieval performance. We also report the effectiveness of AttentionPack combined with eviction, quantization and kernel fusion, showing further efficiency gains for resource-limited environments.

Bird's Eye View (BEV) semantic segmentation is essential for autonomous driving and mobile robotics, yet it still faces significant challenges on accurate segmentation of foreground object and efficient estimating of layout categories obscured by objects. To address these issues, we propose BEV-CAR, a Context-Aware Rasterization method that rasterizes the BEV representation without any coordinate transformations. By optimising each ray and incorporating depth features, BEV-CAR effectively addresses the challenges posed by object occlusions and varying environmental conditions. It ensures robust performance across diverse scenarios, particularly improving the accuracy of foreground object segmentation and layout estimation in occluded areas. And extensive experiments on the nuScenes and Argoverse datasets demonstrate that BEV-CAR achieves state-of-the-art (SOTA) performance. More importantly, the rasterization technique in this paper does not introduce additional computational overhead during the inference process, making it suitable for practical deployment in real-world scenarios. Code is available in https://github.com/BEV-DAR/BEV-DAR.

Video Temporal Grounding (VTG) aims to localize a temporal segment in a video corresponding to a natural language query. However, existing VTG models assume that a relevant segment always exists, causing them to always predict a target segment even when the query is irrelevant to the video. While recent approaches attempt to handle irrelevant queries, they can only reject those that are entirely unrelated to the video and still fail to handle hard-irrelevant queries that are semantically similar but not actually relevant.To address this, we propose Refusal-Aware Reinforcement Fine-Tuning (RA-RFT) to effectively refuse hard-irrelevant queries in VTG.Our method is based on the Group Relative Policy Optimization (GRPO) framework and integrates four reward objectives--format, refuse-IoU, explain, and query correction--to improve both relevance discrimination and fine-grained semantic reasoning.In addition, to effectively support RA-RFT, we construct a Hard-Irrelevant VTG (HI-VTG) dataset, which includes hard-irrelevant queries and their refusal answers.We demonstrate the effectiveness of our method across various relevance-aware VTG scenarios, including hard-irrelevant VTG, simply-shuffled RA-VTG, and human-annotated RA-VTG settings. We also show that the proposed method is scalable by applying it to various LVLM-based VTG 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/.

Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization methods alleviate this issue with additional supervision, but they are mostly computationally expensive and impractical in real-time applications. To address these limitations, we propose MoRe, a feedforward 4D reconstruction network that efficiently recovers dynamic 3D scenes from monocular videos. Built upon a strong static reconstruction backbone, MoRe employs an attention-forcing strategy to disentangle dynamic motion from static structure. To further enhance robustness, we fine-tune the model on large-scale, diverse datasets encompassing both dynamic and static scenes. Moreover, our grouped causal attention captures temporal dependencies and adapts to varying token lengths across frames, ensuring temporally coherent geometry reconstruction. Extensive experiments on multiple benchmarks demonstrate that MoRe achieves high-quality dynamic reconstructions with exceptional efficiency.

Reliable 3D perception from multi-view roadside sensors hinges on the robust fusion of camera and LiDAR data, a task complicated by geometric misalignments and sensor calibration errors. This paper presents GSV2X, a fusion framework that tackles these challenges through two core contributions. First, to achieve robustness against spatial uncertainty, we lift 2D image features into a unified Bird's-Eye-View (BEV) space by representing them as 3D Gaussian distributions. By incorporating learnable perturbations guided by camera geometry, our model explicitly accounts for potential calibration inaccuracies. Second, to maximize the synergy between modalities, we propose a new orthogonal fusion module. This module employs constrained attention to enforce orthogonality between camera and LiDAR features, effectively disentangling redundant information and promoting the learning of complementary representations. Extensive experiments on the challenging RCooper dataset demonstrate that GSV2X sets a new state-of-the-art in multi-view roadside perception and exhibits remarkable robustness in complex, real-world scenarios.

Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments. To address these challenges, we propose SCALE (Self-Cognitive-Aware Learning and Exploration), which leverages three adversarial roles--Selector, Predictor, and Judger to autonomously discover the agent's limitations and expand its cognitive boundaries through environmental exploration. Moreover, we propose SCALE-Hop, a graph exploration strategy that facilitates global planning and helps agents avoid local exploration traps. To further support learning, we construct SCALE-20k, a large-scale dataset collected from 19 real-world websites, containing diverse task types and structured demonstrations generated from SCALE's exploration traces. Experimental results show that our approach significantly improves the performance and generalization of multiple MLLMs in various web environments. Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents.

Diffusion Transformers (DiTs) achieve strong video generation performance but suffer from prohibitive computation cost due to dense spatiotemporal tokenization. Most existing works rely on uniform patchification, tokenizing non-overlapping spatiotemporal with a fixed patch size regardless of the underlying content. This content-agnostic tokenization results in substantial redundant computation, especially in visually simple or static areas. To address this inefficiency while preserving the video generation quality, we propose DynaPatch, a fine-grained dynamic patchification framework that adaptively selects patch sizes for each spatiotemporal region based on content complexity. A lightweight router predicts patch sizes directly from the latents encoded by 3D Variational Autoencoder (VAE), and is jointly optimized with the diffusion model through diffusion loss, an attention-guided saliency alignment loss, and a token-budget regularizer. Learnable patchify/unpatchify layers integrate seamlessly with standard DiT backbones, allowing flexible tokenization without architectural changes. Experiments demonstrate that DynaPatch can effectively reduce redundant computations while preserving fine details, achieving 1.3-1.8x acceleration with minimal quality degradation. On VBench, DynaPatch attains a Total Score of 83.42 at 30% token reduction, significantly outperforming prior patchification and token pruning approaches. These results indicate that content-aware patchification offers an effective direction for efficient and scalable video diffusion. Project page: https://shengli99.github.io/DynaPatch/.

Synthesizing text-driven 3D human motion within realistic scenes requires learning both semantic intent ("walk to the couch") and physical feasibility (e.g., avoiding collisions). Current methods use generative frameworks that simultaneously learn high-level planning and low-level contact reasoning, and rely on computationally expensive 3D scene data such as point clouds or voxel occupancy grids. We propose SceMoS, a scene-aware motion synthesis framework that shows that structured 2D scene representations can serve as a powerful alternative to full 3D supervision in physically grounded motion synthesis. SceMoS disentangles global planning from local execution using lightweight 2D cues and relying on (1) a text-conditioned autoregressive global motion planner that operates on a bird's-eye-view (BEV) image rendered from an elevated corner of the scene, encoded with DINOv2 features, as the scene representation, and (2) a geometry-grounded motion tokenizer trained via a conditional VQ-VAE, that uses 2D local scene heightmap, thus embedding surface physics directly into a discrete vocabulary. This 2D factorization reaches an efficiency-fidelity trade-off: BEV semantics capture spatial layout and affordance for global reasoning, while local heightmaps enforce fine-grained physical adherence without full 3D volumetric reasoning. SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark, reducing the number of trainable parameters for scene encoding by over 50%, showing that 2D scene cues can effectively ground 3D human-scene interaction. Project URL: https://anindita127.github.io/SceMoS.

The pursuit of a universal AI-generated image (AIGI) detector often relies on aggregating data from numerous generators to improve generalization. However, this paper identifies a paradoxical phenomenon we term the "Benefit then Conflict" dilemma, where detector performance stagnates and eventually degrades as source diversity expands. Our systematic analysis, diagnoses this failure by identifying two core issues: severe data-level heterogeneity which causes the feature distributions of real and synthetic images to increasingly overlap, and a critical model-level bottleneck from fixed, pretrained encoders that cannot adapt to the rising complexity. To address these challenges, we propose Generator-Aware Prototype Learning (GAPL) , a framework that constrain representation with a structured learning paradigm. GAPL learns a compact set of canonical forgery prototypes to create a unified, low-variance feature space, effectively countering data heterogeneity. To resolve the model bottleneck, it employs a two-stage training scheme with Low-Rank Adaptation, enhancing its discriminative power while preserving valuable pretrained knowledge. This approach establishes a more robust and generalizable decision boundary. Through extensive experiments, we demonstrate that GAPL achieves state-of-the-art performance, showing superior detection accuracy across a wide variety of GAN and diffusion-based generators. Code is available at https://github.com/UltraCapture/GAPL

Object removal requires eliminating not only the target object but also its associated visual effects such as shadows and reflections. However, diffusion-based inpainting and removal methods often introduce artifacts, hallucinate contents, alter background, and struggle to remove object effects accurately. To address these challenges, we propose ObjectClear, a novel framework that decouples foreground removal from background reconstruction via an adaptive target-aware attention mechanism. This design empowers the model to precisely localize and remove both objects and their effects while maintaining high background fidelity. Moreover, the learned attention maps are leveraged for an attention-guided fusion strategy during inference, further enhancing visual consistency. To facilitate the training and evaluation, we construct OBER, a large-scale dataset for OBject-Effect Removal, which provides paired images with and without object-effects, along with precise masks for both objects and their effects. The dataset comprises high-quality captured and simulated data, covering diverse objects, effects, and complex multi-object scenes. Extensive experiments demonstrate that ObjectClear outperforms prior methods, achieving superior object-effect removal quality and background fidelity, especially in challenging scenarios.

Post-training quantization (PTQ) with computational equivalence for Large Language Models (LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models (MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms.

Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in real-world FL scenarios, clients often hold data from distinct domains, leading to severe domain shift and degraded global model performance. To address this, prototype learning has been emerged as a promising solution, which leverages class-wise feature representations. Yet, existing methods face two key limitations: (1) Existing prototype-based FL methods typically construct a single global prototype per class by aggregating local prototypes from all clients without preserving domain information. (2) Current feature-prototype alignment is domain-agnostic, forcing clients to align with global prototypes regardless of domain origin. To address these challenges, we propose Federated Domain-Aware Prototypes (FedDAP) to construct domain-specific global prototypes by aggregating local client prototypes within the same domain using a similarity-weighted fusion mechanism. These global domain-specific prototypes are then used to guide local training by aligning local features with prototypes from the same domain, while encouraging separation from prototypes of different domains. This dual alignment enhances domain-specific learning at the local level and enables the global model to generalize across diverse domains. Finally, we conduct extensive experiments on three different datasets: DomainNet, Office-10, and PACS to demonstrate the effectiveness of our proposed framework to address the domain shift challenges.

Personalized image generation based on user behavior reflects individual preferences with minimal user intervention. However, existing studies often rely on inaccurate profiling, high resource costs, and model-specific designs, which jointly restrict creativity, diversity, and generality. To address these limitations, we propose FAN, a novel approach that enables preference-aware personalization using only foundation encoders, without additional structures. FAN performs tailored profiling to capture user preferences and reconstructs transformer-based encoders to integrate them while preserving target fidelity. Experiments show that FAN achieves robust personalization across various foundation text-to-image models. It also extends to applications such as CLIP retrieval, unCLIP, and vision-language models, seamlessly integrating into diverse encoders without fine-tuning.

Sparse Upcycling provides an efficient way to initialize a Mixture-of-Experts (MoE) model from pretrained dense weights instead of training from scratch. However, since all experts start from identical weights and the router is randomly initialized, the model suffers from expert symmetry and limited early specialization. We propose Cluster- aware Upcycling, a strategy that incorporates semantic structure into MoE initialization. Our method first partitions the dense model's input activations into semantic clusters. Each expert is then initialized using the subspace representations of its corresponding cluster via truncated SVD, while setting the router's initial weights to the cluster centroids. This cluster-aware initialization breaks expert symmetry and encourages early specialization aligned with the data distribution. Furthermore, we introduce an expert-ensemble self-distillation loss that stabilizes training by providing reliable routing guidance using an ensemble teacher. When evaluated on CLIP ViT-B/32 and ViT-B/16, Cluster-aware Upcycling consistently outperforms existing methods across both zero-shot and few-shot benchmarks. The proposed method also produces more diverse and dis- entangled expert representations, reduces inter-expert similarity, and leads to more confident routing behavior.

Recent advances in chart recognition have been driven by supervised fine-tuning (SFT) of vision-language models (VLMs), which unify multiple related tasks, and by diversifying training corpora. In parallel, research on leveraging large language models (LLMs) for object detection has shown that jointly training phrase grounding alongside SFT enhances a model's generative capabilities. Inspired by this, we hypothesize that chart recognition can also benefit from phrase grounding, which aligns textual phrases with chart regions. However, this setting remains underexplored due to the lack of corresponding datasets. In this work, we introduce phrase-grounding-aware SFT via a Side-Masked Attention Module (SMAM) inserted into each transformer layer of the LLM. SMAM performs masked attention within the annotated region aligned with each phrase to produce an additional logit. This logit is supervised and serves as a reference signal to guide the LLM's output prediction during fine-tuning, alongside the standard SFT objective. To enable this approach, we also develop an automated pipeline for generating phrase-to-region alignments, which augments existing datasets. Experiments show that our method effectively incorporates phrase grounding into VLM fine-tuning for chart recognition.

In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct approaches, which regress the pose in an end-to-end manner, are usually computationally more efficient but less accurate. However, direct pose regression heads rely on globally pooled features, ignoring spatial second-order statistics despite their informativeness in pose prediction. They also predict, in most cases, discontinuous pose representations that lack robustness. Herein, we therefore propose a covariance-pooled representation that encodes convolutional feature distributions as a symmetric positive definite (SPD) matrix. Moreover, we propose a novel pose encoding in the form of an SPD matrix via its Cholesky decomposition. Pose is then regressed in an end-to-end manner with a manifold-aware network head, taking into account the Riemannian geometry of SPD matrices. Experiments and ablations consistently demonstrate the relevance of second-order pooling and continuous representations for direct pose regression, including under partial occlusion.