CVPR 2026 论文列表

Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face severe label scarcity. In such regimes, end-to-end grounding detectors need to learn spatial and semantic structure from scratch, wasting precious samples. We ask a simple question: Can explicit reasoning priors help models learn more efficiently when data is scarce? To explore this, we first introduce a Data-efficient Referring Object Detection (De-ROD) task, which is a benchmark protocol for measuring ROD performance in low-data and few-shot settings. We then propose the HeROD (Heuristic-inspired ROD), a lightweight, model-agnostic framework that injects explicit, heuristic-inspired spatial and semantic reasoning priors, which are interpretable signals derived based on the referring phrase, into 3 stages of a modern DETR-style pipeline: proposal ranking, prediction fusion, and Hungarian matching. By biasing both training and inference toward plausible candidates, these priors promise to improve label efficiency and convergence performance. On RefCOCO, RefCOCO+, and RefCOCOg, HeROD consistently outperforms strong grounding baselines in scarce-label regimes. More broadly, our results suggest that integrating simple, interpretable reasoning priors provides a practical and extensible path toward better data-efficient vision-language understanding. Code at: https://github.com/xuzhang1199/HeROD.

We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions of the input video and the target retake. Moreover, we introduce Rotary Camera Encoding (RoCE), a camera-conditioned RoPE phase shift that captures and integrates multi-view relationships within and across the input and target videos. By integrating camera conditions into RoPE, our method generalizes to out-of-distribution camera trajectories and video lengths, yielding improved dynamic object localization and static background preservation. Extensive experiments further demonstrate significant improvements in camera controllability, geometric consistency, and video quality across various trajectories and lengths.

Large-scale pre-trained image-text models exhibit robust multimodal representation, yet applying contrastive language-image pretraining (CLIP) to audio-visual localization remains challenging. Replacing the classification token ([CLS]) with an audio-embedded token ([V_A])struggles to capture semantic cues, and the prompt "a photo of a [V_A]" fails to establish meaningful connections between audio embeddings and context tokens. To address these issues, we propose sound-aware prompt learning (SouPLe), which replaces fixed prompts with learnable context tokens. These tokens incorporate visual features to generate conditional context for a mask decoder, effectively bridging semantic correspondence between audio and visual inputs. Experiments on VGGSound, SoundNet, and AVSBench confirm that SouPLe significantly improves localization and segmentation performance.

Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds. Beyond method limitations, progress is further hampered by the lack of a comprehensive dataset that systematically captures common object effects across varied environments for training and evaluation. To address this, we introduce **VOR** (**V**ideo **O**bject **R**emoval), a large-scale dataset that provides diverse paired videos, each consisting of one video where the target object is present with its effects and a counterpart where the object and effects are absent, with corresponding object masks. VOR contains 60k high-quality video pairs from captured and synthetic sources, covers five effects types, and spans a wide range of object categories as well as complex, dynamic multi-object scenes. Building on VOR, we propose ***EffectErase***, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme. The model includes task-aware region guidance that focuses learning on affected areas and enables flexible task switching. Then, an insertion-removal consistency objective that encourages complementary behaviors and shared localization of effect regions and structural cues. Trained on VOR, EffectErase achieves superior performance in extensive experiments, delivering high-quality video object effect erasing across diverse scenarios.

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of one-step distilled models compromises generative diversity and degrades performance in complex generative tasks, e.g., generating intricate object motions in text-to-video task. Directly extending DMD to multi-step distillation increases memory usage and computational depth, leading to instability and reduced efficiency. While prior works propose stochastic gradient truncation as a potential solution, we observe that it substantially reduces the generative diversity in text-to-image generation and slows motion dynamics in video generation, reducing performance to the level of one-step models. To address these limitations, we propose Phased DMD, a multi-step distillation framework that bridges the idea of phase-wise distillation with Mixture-of-Experts (MoE), reducing learning difficulty while enhancing model capacity. Phased DMD incorporates two key ideas: progressive distribution matching and score matching within subintervals. First, our model divides the SNR range into subintervals, progressively refining the model to higher SNR levels, to better capture complex distributions. Next, to ensure accurate training within each subinterval, we derive rigorous mathematical formulations for the objective. We validate Phased DMD by distilling state-of-the-art image and video generation models, including Qwen-Image-20B and Wan2.2-28B. Experiments demonstrate that Phased DMD enhances motion dynamics, improves visual fidelity in video generation, and increases output diversity in image generation. Our code and models are available at https://x-niper.github.io/projects/Phased-DMD/.

Recent advances in Visual-Language-Action (VLA) models have shown promising potential for robotic manipulation tasks.However, real-world robotic tasks often involve long-horizon, multi-step problem-solving and require generalization for continual skill acquisition, extending beyond single actions or skills. These challenges present significant barriers for existing VLA models, which use monolithic action decoders trained on aggregated data, resulting in poor scalability.To address these challenges, we propose AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions. AtomicVLA constructs a scalable atomic skill library through a Skill-Guided Mixture-of-Experts (SG-MoE), where each expert specializes in mastering generic yet precise atomic skills. Furthermore, we introduce a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning.We validate our approach through extensive experiments. In simulation, AtomicVLA outperforms \pi_ 0 by 2.4% on LIBERO, 10% on LIBERO-LONG, and outperforms \pi_ 0 and \pi_ 0.5 by 0.22 and 0.25 in average task length on CALVIN. Additionally, our AtomicVLA consistently surpasses baselines by 18.3% and 21% in real-world long-horizon tasks and continual learning. These results highlight the effectiveness of atomic skill abstraction and dynamic expert composition for long-horizon and lifelong robotic tasks.

Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon introduces a text-conditioned granularity Controller that dynamically adjusts the visual abstraction level according to the semantic scope of the textual input, and an Adaptive Token Aggregation module that performs granularity-guided pooling and relation-aware clustering to produce compact, semantically rich visual tokens. This design enables unified "pixel-to-fine-to-coarse" reasoning within a single forward pass. Extensive and interpretable experiments demonstrate that Granulon improves accuracy by 30% and reduces hallucination by 20%, outperforming all visual encoders under identical settings. Code is available at the Supplementary.

Single-view 3D human reconstruction has garnered significant attention in recent years. Despite numerous advancements, prior research has concentrated on reconstructing 3D models from clear, close-up images of individual subjects, often yielding subpar results in the more prevalent multi-person scenarios. Reconstructing 3D human crowd models is a highly intricate task, laden with challenges such as: 1) extensive occlusions, 2) low clarity, and 3) numerous and various appearances. To address this task, we propose CrowdGaussian, a unified framework that directly reconstructs multi-person 3D Gaussian Splatting (3DGS) representations from single-image inputs. To handle occlusions, we devise a self-supervised adaptation pipeline that enables the pretrained large human model to reconstruct complete 3D humans with plausible geometry and appearance from heavily occluded inputs. Furthermore, we introduce Self-Calibrated Learning (SCL). This training strategy enables single-step diffusion models to adaptively refine coarse renderings to optimal quality by blending identity-preserving samples with clean/corrupted image pairs. The outputs can be distilled back to enhance the quality of multi-person 3DGS representations. Extensive experiments demonstrate that CrowdGaussian generates photorealistic, geometrically coherent reconstructions of multi-person scenes.

Model reprogramming adapts pretrained models to downstream tasks by modifying their input and output spaces. Visual reprogramming, as a prominent instance, has been explored in pioneer works on CLIP, which introduces learnable input transformations as visual prompts to repurpose its visual-language alignment for downstream visual tasks. Existing VR methods focus on single-level alignment between prompted images and text descriptions, overlooking inherent structural information in data that facilitates alignment: semantic granularity from label hierarchies and visual granularity from multi-scale representations. To address this gap, we propose Dual Granularity Alignment (DGA) with two key components for multi-level fusion. For visual granularity, we generate multi-scale images and introduce Uncertainty-calibrated Prediction Fusion (UPF), which fuses predictions based on uncertainty estimation to capture hierarchical spatial information. For semantic granularity, we construct category hierarchies via Prototype-guided Label Hierarchization and develop Hierarchical Knowledge Propagation (HKP), which transfers superclass knowledge for coherent multi-level visual prompts alignment. Our DGA collaboratively integrates both granularities to enhance alignment effectiveness. Experiments across 12 downstream datasets demonstrate DGA's superiority over baselines on both ViT-based and ResNet-based CLIP architectures. Specifically, DGA achieves a 4.5% improvement over the previous state-of-the-art method on ViT-16-based CLIP. By explicitly modeling structural granularities, DGA establishes a new paradigm for visual reprogramming.

Synthesizing novel spatiotemporal views of dynamic scenes is challenging due to object and camera motion, and sparse observations. While recent Neural Radiance Field (NeRF) and Gaussian Splatting (GS) methods enable 4D dynamic scene reconstruction, they predominantly assume well-lit inputs. Existing low-light reconstruction approaches are limited to static scenes and mainly focus on brightness enhancement while overlooking underlying scene structure. Reconstructing well-lit dynamic scenes from low-light inputs is particularly challenging due to motion-induced shadows, occlusions, and disocclusions, making the problem highly ambiguous. We propose L^ 2 DGS (Low-Light Dynamic Gaussian Splatting), a self-supervised 4D GS framework that directly reconstructs well-lit dynamic scenes from low-light videos. The method decomposes the scene into view- and time-dependent illumination and view-time-invariant reflectance components. We introduce an Occlusion-Disocclusion Network (OCD-Net) to model temporal intensity variations and Brightness Attenuation Features (BAFs) with a BAF Enhancement Network (BAFE-Net) to enable geometry- and photometry-aware transformation between well-lit and low-light observations for self-supervision. L^ 2 DGS operates on standard sRGB inputs without requiring camera metadata. Experiments on simulated and proposed real Low-Light Dynamic Video (L^ 2 DyV) datasets demonstrate superior qualitative and quantitative performance over prior methods. The dataset is available at: \href https://github.com/akumar005/L2DGS https://github.com/akumar005/L2DGS .

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection with Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85% accuracy and +69.62% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All the code and models are availabe at: \href https://github.com/mvrl/SimLBR https://github.com/mvrl/SimLBR .

Forecasting gaze behavior is an important task for understanding user intent and creating AR/VR systems that can anticipate where users will look and interact next. While prior works have addressed predicting scanpaths in static images, forecasting gaze in egocentric videos presents new challenges due to the dynamic nature of the scene and the camera wearer's continuous movement through the 3D environment. To address these challenges, we formulate the novel task of egocentric scanpath prediction as forecasting a sequence of future fixations in 3D Cartesian coordinates relative to the last observed camera pose, producing a 3D scanpath that is grounded in the environment. We propose a transformer architecture that leverages egocentric video frames, head pose, and past 3D gaze observations to predict future 3D fixation sequences. We evaluate our method on the Aria Digital Twin dataset. Our findings establish a baseline for the novel task of 3D scanpath prediction and highlight important architectural elements for our task.

Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the real world's inherent physical ambiguity. We address this by reframing physics prediction as a task of learning a controllable, continuous distribution of material properties. We introduce UNIPIXIE, a framework trained to predict a continuous and parameterized path of physically plausible material properties from a single visual input. By learning a direct mapping along an object's softest-to-stiffest spectrum on our PIXIEMULTIVERSE dataset, UNIPIXIE allows for controllable generation of diverse, physically-valid material fields via a single intuitive parameter. Crucially, UNIPIXIE introduces a novel unified architecture to produce simulation-ready parameters for diverse physics solvers, including continuum-based Material Point Method (MPM), reduced-order deformation based on Linear Blend Skinning (LBS), and anchor-based Spring-Mass systems, addressing a key portability issue in prior work. Experiments show our approach not only generates a rich variety of plausible dynamics but also reduces Young's Modulus prediction error by over 50% against the strongest deterministic baseline, bridging the gap between static point-estimates and the continuous nature of physical reality.

Vision-Language Models (VLMs) are frequently undermined by object hallucination--generating content that contradicts visual reality--due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a training-free inference framework that intervenes directly in the decoding process to enforce visual fidelity. PND is motivated by our key finding of a critical attention deficit in VLMs, where visual features are empirically under-weighted. Our framework corrects this via a dual-path contrast: The positive path amplifies salient visual evidence using multi-layer attention to encourage faithful descriptions, directly counteracting the attention deficit. Simultaneously, the negative path identifies and degrades the core object's features to create a strong counterfactual, which penalizes ungrounded, prior-dominant generation. By contrasting the model's outputs from these two perspectives at each step, PND steers generation towards text that is not just linguistically probable, but visually factual. Extensive experiments on benchmarks like POPE, MME, and CHAIR show that PND achieves state-of-the-art performance with up to 6.5% accuracy improvement, substantially reducing object hallucination while also enhancing descriptive detail--all without requiring any model retraining. The method generalizes effectively across diverse VLM architectures including LLaVA, InstructBLIP, InternVL, and Qwen-VL.

Autonomous driving requires generating safe and reliable trajectories from complex multimodal inputs. Traditional modular pipelines separate perception, prediction, and planning, while recent end-to-end (E2E) systems learn them jointly. Vision-language models (VLMs) further enrich this paradigm by introducing cross-modal priors and commonsense reasoning, yet current VLM-based planners face three key challenges: (i) a mismatch between discrete text reasoning and continuous control, (ii) high latency from autoregressive chain-of-thought decoding, and (iii) inefficient or non-causal planners that limit real-time deployment. We propose ColaVLA, a unified vision-language-action framework that transfers reasoning from text to a unified latent space and couples it with a hierarchical, parallel trajectory decoder. The Cognitive Latent Reasoner compresses scene understanding into compact, decision-oriented meta-action embeddings through ego-adaptive selection and only two VLM forward passes. The Hierarchical Parallel Planner then generates multi-scale, causality-consistent trajectories in a single forward pass. Together, these components preserve the generalization and interpretability of VLMs while enabling efficient, accurate and safe trajectory generation. Experiments on the nuScenes benchmark show that ColaVLA achieves state-of-the-art performance in both open-loop and closed-loop settings with favorable efficiency and robustness.

Large multimodal models (LMMs) have achieved impressive performance on multimodal reasoning, becoming crucial technology for the advancement of intelligent question-answering systems. In real-world educational scenarios, effective teaching extends far beyond providing answers. Experienced teachers analyze students' incorrect answers to trace underlying errors and provide corrective feedback, termed educational diagnostic reasoning, a capability that remains under-explored in existing LMMs. To bridge this research gap, we introduce Edudiag benchmark, requiring LMMs to reconstruct erroneous reasoning chains from incorrect answers and generate corrective feedback. Through an AI-assisted annotation pipeline with rigorous human verification, we create 8K erroneous reasoning chains and corresponding feedback, spanning three representative educational domains: commonsense, science, and mathematics. Extensive evaluation across 28 leading LMMs highlights Edudiag as a challenging testbed, where even leading proprietary LMMs struggle on it and supervised fine-tuning (SFT) on open-source LMMs achieves marginal performance gains. Moreover, we conduct analysis experiments and identify three critical insights for educational diagnostic reasoning: (i) Effective error tracing remains the primary bottleneck, while SFT models still fail to reversely identify errors that commonly occur. (ii) Group relative policy optimization (GRPO) mitigates this bottleneck and boosts performance. (iii) LMMs optimized with GRPO can generate plausible yet challenging distractors for multiple-choice questions based on their self-constructed erroneous reasoning chains. We believe Edudiag provides a new direction for evaluating the advanced LMMs.

Compositional 3D scene generation from a single view requires the simultaneous recovery of scene layout and 3D assets. Existing approaches mainly fall into two categories: feed-forward generation methods and per-instance generation methods. The former directly predict 3D assets with explicit 6DoF poses through efficient network inference, but they generalize poorly to complex scenes. The latter improve generalization through a divide-and-conquer strategy, but suffer from time-consuming pose optimization. To bridge this gap, we introduce 3D-Fixer, a novel in-place completion paradigm. Specifically, 3D-Fixer extends 3D object generative priors to generate complete 3D assets conditioned on the partially visible point cloud at the original locations, which are cropped from the fragmented geometry obtained from the geometry estimation methods. Unlike prior works that require explicit pose alignment, 3D-Fixer uses fragmented geometry as a spatial anchor to preserve layout fidelity. At its core, we propose a coarse-to-fine generation scheme to resolve boundary ambiguity under occlusion, supported by a dual-branch conditioning network and an Occlusion-Robust Feature Alignment (ORFA) strategy for stable training. Furthermore, to address the data scarcity bottleneck, we present ARSG-110K, the largest scene-level dataset to date, comprising over 110K diverse scenes and 3M annotated images with high-fidelity 3D ground truth. Extensive experiments show that 3D-Fixer achieves state-of-the-art geometric accuracy, which significantly outperforms baselines such as MIDI and Gen3DSR, while maintaining the efficiency of the diffusion process. Code and data will be publicly available at https://zx-yin.github.io/3dfixer.

3D Large Vision-Language Models (3D LVLMs) built upon Large Language Models (LLMs) have achieved remarkable progress across various multimodal tasks. However, their inherited position-dependent modeling mechanism, Rotary Position Embedding (RoPE), remains suboptimal for 3D multimodal understanding. The vanilla RoPE formulation fails to preserve essential three-dimensional spatial structures when encoding 3D tokens, and its relative distance computation overlooks angular dependencies hindering the model's ability to capture directional variations in visual representations. To overcome these limitations, we introduce Spherical Coordinate-based Positional Embedding (SoPE). Our method maps point-cloud token indices into a 3D spherical coordinate space, enabling unified modeling of spatial locations and directional angles. This formulation preserves the inherent geometric structure of point-cloud data, enhances spatial awareness, and yields more consistent and expressive geometric representations for multimodal learning. In addition, we introduce a multi-scale frequency mixing strategy to fuse feature information across different frequency domains. Experimental results on multiple 3D scene benchmarks validate the effectiveness of our approach, while real-world deployment experiments further demonstrate its strong generalization capability.

Simulation of cellular morphology change has long been a fundamental task in quantitative biology and high-throughput screening, with the potential to accelerate therapeutic development and elucidate disease mechanisms beyond empirical clinical practice. However, the vast perturbation space poses challenges to the discriminative formulation, and existing generative approaches tend to concentrate on the same trajectory subspace, making their generated paths prone to drift. In this paper, we propose a novel Steered Diffusion Bridge approach, named SimuSDB, to define deterministic probabilistic trajectories between two distinct state domains for cell response generation. We first extend the diffusion bridge paradigm to maintain stochasticity and diversity in interpolation trajectories by introducing Brownian bridges. Then, SimuSDB generates cell morphologies that comply with phenotypic constraints, while allowing the latter to explicitly guide the generative process. For the inference stage, we formalize the rule-guided sample generation task as an optimal control problem within a stochastic dynamical system. This way, the generative model can achieve analytically tractable optimal control strategies and steered generation without collapsing toward the trajectory of the same data subspace. Comprehensive experiments demonstrate the superior performance of SimuSDB across various applications, including chemical perturbation and genetic perturbation.