Matching
-
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
2026-04-16 17:59:58Ninghui Xu, Fabio Tosi, Lihui Wang, Jiawei Han, Luca Bartolomei, Zhiting Yao, Matteo Poggi, Stefano MattocciaAbstract
Conventional frame-based cameras capture rich contextual information but suffer from limited temporal resolution and motion blur in dynamic scenes. Event cameras offer an alternative visual representation with higher dynamic range free from such limitations. The complementary characteristics of the two modalities make event-frame asymmetric stereo promising for reliable 3D perception under fast motion and challenging illumination. However, the modality gap often leads to marginalization of domain-specific cues essential for cross-modal stereo matching. In this paper, we introduce Bi-CMPStereo, a novel bidirectional cross-modal prompting framework that fully exploits semantic and structural features from both domains for robust matching. Our approach learns finely aligned stereo representations within a target canonical space and integrates complementary representations by projecting each modality into both event and frame domains. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in accuracy and generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15312
PDF
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
2026-04-16 17:59:56Zhanhao Liang, Tao Yang, Jie Wu, Chengjian Feng, Liang ZhengAbstract
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memory costs and gradient explosion. Therefore, direct-gradient methods struggle to update early generation steps, which are crucial for determining the global structure of the final image. To address this issue, we introduce LeapAlign, a fine-tuning method that reduces computational cost and enables direct gradient propagation from reward to early generation steps. Specifically, we shorten the long trajectory into only two steps by designing two consecutive leaps, each skipping multiple ODE sampling steps and predicting future latents in a single step. By randomizing the start and end timesteps of the leaps, LeapAlign leads to efficient and stable model updates at any generation step. To better use such shortened trajectories, we assign higher training weights to those that are more consistent with the long generation path. To further enhance gradient stability, we reduce the weights of gradient terms with large magnitude, instead of completely removing them as done in previous works. When fine-tuning the Flux model, LeapAlign consistently outperforms state-of-the-art GRPO-based and direct-gradient methods across various metrics, achieving superior image quality and image-text alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15311
PDF
-
AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving
2026-04-16 17:54:53Fabrizio Genilotti, Arianna Stropeni, Gionata Grotto, Francesco Borsatti, Manuel Barusco, Davide Dalle Pezze, Gian Antonio SustoAbstract
The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significantly different conditions, such as atypical obstacles, its perceptual capabilities can degrade substantially. Unlike many domains where errors carry limited consequences, failures in autonomous driving translate directly into physical risk for passengers, pedestrians, and other road users. To address this challenge, we explore Visual Anomaly Detection (VAD) as a solution. VAD enables the identification of anomalous objects not present during training, allowing the system to alert the driver when an unfamiliar situation is detected. Crucially, VAD models produce pixel-level anomaly maps that can guide driver attention to specific regions of concern without requiring any prior assumptions about the nature or form of the hazard. We benchmark eight state-of-the-art VAD methods on AnoVox, the largest synthetic dataset for anomaly detection in autonomous driving. In particular, we evaluate performance across four backbone architectures spanning from large networks to lightweight ones such as MobileNet and DeiT-Tiny. Our results demonstrate that VAD transfers effectively to road scenes. Notably, Tiny-Dinomaly achieves the best accuracy-efficiency trade-off for edge deployment, matching full-scale localization performance at a fraction of the memory cost. This study represents a concrete step toward safer, more responsible deployment of autonomous vehicles, ultimately improving protection for passengers, pedestrians, and all road users.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15291
PDF
-
An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
2026-04-16 15:48:40Onno Niemann, Gonzalo Mart\'inez Mu\~noz, Alberto Su\'arez GonzalezAbstract
Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often violate the Fokker--Planck (FP) equation that governs the evolution of the true data density. Directly penalizing these deviations in the objective function reduces their magnitude but introduces a significant computational overhead. It is also observed that enforcing strict adherence to the FP equation does not necessarily lead to improvements in the quality of the generated samples, as often the best results are obtained with weaker FP regularization. In this paper, we investigate whether simpler penalty terms can provide similar benefits. We empirically analyze several lightweight regularizers, study their effect on FP residuals and generation quality, and show that the benefits of FP regularization are available at substantially lower computational cost. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15171
PDF
-
RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
2026-04-16 12:47:09Gabriele Mattioli, Evelyn Turri, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita CucchiaraAbstract
Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to solve complex tasks beyond the reach of standalone language generation. While recent advances in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have expanded their reasoning and perception capabilities, existing tool-use methods are predominantly limited to text-only inputs and closed-world settings. Consequently, they struggle to interpret multimodal user instructions and cannot generalize to tools unseen during training. In this work, we introduce RaTA-Tool, a novel framework for open-world multimodal tool selection. Rather than learning direct mappings from user queries to fixed tool identifiers, our approach enables an MLLM to convert a multimodal query into a structured task description and subsequently retrieve the most appropriate tool by matching this representation against semantically rich, machine-readable tool descriptions. This retrieval-based formulation naturally supports extensibility to new tools without retraining. To further improve alignment between task descriptions and tool selection, we incorporate a preference-based optimization stage using Direct Preference Optimization (DPO). To support research in this setting, we also introduce the first dataset for open-world multimodal tool use, featuring standardized tool descriptions derived from Hugging Face model cards. Extensive experiments demonstrate that our approach significantly improves tool-selection performance, particularly in open-world, multimodal scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14951
PDF
-
Reward-Aware Trajectory Shaping for Few-step Visual Generation
2026-04-16 11:52:11Rui Li, Bingyu Li, Yuanzhi Liang, HuangHai Bin, Chi Zhang, XueLong LiAbstract
Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frameworks to compress the original multi-step denoising process into a few-step generator. However, such methods inherently constrain the student to imitate a stronger multi-step teacher, imposing the teacher as an upper bound on student performance. We argue that introducing \textbf{preference alignment awareness} enables the student to optimize toward reward-preferred generation quality, potentially surpassing the teacher instead of being restricted to rigid teacher imitation. To this end, we propose \textbf{Reward-Aware Trajectory Shaping (RATS)}, a lightweight framework for preference-aligned few-step generation. Specifically, teacher and student latent trajectories are aligned at key denoising stages through horizon matching, while a \textbf{reward-aware gate} is introduced to adaptively regulate teacher guidance based on their relative reward performance. Trajectory shaping is strengthened when the teacher achieves higher rewards, and relaxed when the student matches or surpasses the teacher, thereby enabling continued reward-driven improvement. By seamlessly integrating trajectory distillation, reward-aware gating, and preference alignment, RATS effectively transfers preference-relevant knowledge from high-step generators without incurring additional test-time computational overhead. Experimental results demonstrate that RATS substantially improves the efficiency--quality trade-off in few-step visual generation, significantly narrowing the gap between few-step students and stronger multi-step generators.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14910
PDF
-
Open-Set Vein Biometric Recognition with Deep Metric Learning
2026-04-16 11:03:11Pawe{\l} Pilarek, Marcel Musia{\l}ek, Anna G\'orskaAbstract
Most state-of-the-art vein recognition methods rely on closed-set classification, which inherently limits their scalability and prevents the adaptive enrollment of new users without complete model retraining. We rigorously evaluate the computational boundaries of Deep Metric Learning (DML) under strict open-set constraints. Unlike standard closed-set approaches, we analyze the impact of data scarcity and domain shift on recognition performance. Our approach learns discriminative L2-normalised embeddings and employs prototype-based matching with a calibrated similarity threshold to effectively distinguish between enrolled users and unseen impostors. We evaluate the framework under a strict subject-disjoint protocol across four diverse datasets covering finger, wrist, and dorsal hand veins (MMCBNU 6000, UTFVP, FYO, and a dorsal hand-vein dataset). On the large-scale MMCBNU 6000 benchmark, our best model (ResNet50-CBAM) achieves an OSCR of 0.9945, AUROC of 0.9974, and EER of 1.57%, maintaining high identification accuracy (99.6% Rank-1) while robustly rejecting unknown subjects. Cross-dataset experiments evaluate the framework's generalisation across different acquisition setups, confirming that while the model handles large-scale data robustly, performance remains sensitive to domain shifts in low-data regimes. Ablation studies demonstrate that triplet-based objectives combined with a simple 1-NN classifier offer an optimal trade-off between accuracy and efficiency, enabling real-time deployment on commodity hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14874
PDF
-
Generative Modeling of Complex-Valued Brain MRI Data
2026-04-16 09:24:26Marco Schlimbach, Moritz Rempe, Jessica Mnischek, Lukas T. Rotkopf, Jens Weingarten, Jens Kleesiek, Kevin Kr\"oningerAbstract
Objective. Standard Magnetic Resonance Imaging (MRI) reconstruction pipelines discard phase information captured during acquisition, despite evidence that it encodes tissue properties relevant to tumor diagnosis. Current machine learning approaches inherit this limitation by operating exclusively on reconstructed magnitude images. The aim of this study is to build a generative framework which is capable of jointly modeling magnitude and phase information of complex-valued MRI scans. Approach. The proposed generative framework combines a conditional variational autoencoder, which compresses complex-valued MRI scans into compact latent representations while preserving phase coherence, with a flow-matching-based generative model. Synthetic sample quality is assessed via a real-versus-synthetic classifier and by training downstream classifiers on synthetic data for abnormal tissue detection. Main results. The autoencoder preserves phase coherence above 0.997. Real-versus-synthetic classification yields low AUROC values between 0.50 and 0.66 across all acquisition sequences, indicating generated samples are nearly indistinguishable from real data. In downstream normal-versus-abnormal classification, classifiers trained entirely on synthetic data achieve an AUROC of 0.880, surpassing the real-data baseline of 0.842 on a publicly available dataset (fastMRI). This advantage persists on an independent external test set from a different institution with biopsy-confirmed labels. Significance. The proposed framework demonstrates the feasibility of jointly modeling magnitude and phase information for normal and abnormal complex-valued brain MRI data. Beyond synthetic data generation, it establishes a foundation for the usage of complete brain MRI information in future diagnostic applications and enables systematic investigation of how magnitude and phase jointly encode pathology-specific features.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14800
PDF
-
MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models
2026-04-16 03:20:30Ruiqi Wang, Qi Yu, Jie Ma, Hanlin WuAbstract
High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typically use them to retrain dense predictors with substantial computational cost. We propose MapSR, a prompt-driven framework that decouples supervision from model training. MapSR uses LR labels once to extract class prompts from frozen vision foundation model features through a lightweight linear probe, after which HR mapping proceeds via training-free metric inference and graph-based prediction refinement. Specifically, class prompts are estimated by aggregating high-confidence HR features identified by the linear probe, and HR predictions are obtained by cosine-similarity matching followed by graph-based propagation for spatial refinement. Experiments on the Chesapeake Bay dataset show that MapSR achieves 59.64% mIoU without any HR labels, remaining competitive with the strongest weakly supervised baseline and surpassing a fully supervised baseline. Notably, MapSR reduces trainable parameters by four orders of magnitude and shortens training time from hours to minutes, enabling scalable HR mapping under limited annotation and compute budgets. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14582
PDF
-
TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
2026-04-16 03:19:29Xiangyu Liu, Feng Gao, Xiaomei Zhang, Yong Zhang, Xiaoming Wei, Zhen Lei, Xiangyu ZhuAbstract
Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propose TurboTalk, a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator. We first adopt Distribution Matching Distillation to obtain a strong and stable 4-step student, and then progressively reduce the denoising steps from 4 to 1 through adversarial distillation. To ensure stable training under extreme step reduction, we introduce a progressive timestep sampling strategy and a self-compare adversarial objective that provides an intermediate adversarial reference that stabilizes progressive distillation. Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14580
PDF
-
H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection
2026-04-16 00:47:45Jianghong Huang, Luping Ji, Weiwei Duan, Mao YeAbstract
As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is attracting increasing attention. In recent years, beyond traditional visual paradigm, Vision-Language Model (VLM) has been extensively explored to boost this field. However, in currently-existing VLM-based FSAD schemes, almost all perform anomaly inference only by pairwise feature matching, ignoring structural dependencies and global consistency. To further redound to FSAD via VLM, we propose a Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR) framework. It reformulates the FSAD as a high-order inference problem of visual-semantic relations, by jointly modeling visual regions and semantic concepts in a unified hypergraph. Experimental comparisons verify the effectiveness and advantages of H2VLR. It could often achieve state-of-the-art (SOTA) performance on representative industrial and medical benchmarks. Our code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14507
PDF
-
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
2026-04-15 17:50:07Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, Ping LuoAbstract
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14125
PDF
-
SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation
2026-04-15 14:52:10Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao, Xiaobo Lu, Takeshi IkenagaAbstract
Local feature matching plays a critical role in understanding the correspondence between cross-view images. However, traditional methods are constrained by the inherent local nature of feature descriptors, limiting their ability to capture non-local scene information that is essential for accurate cross-view correspondence. In this paper, we introduce SceneGlue, a scene-aware feature matching framework designed to overcome these limitations. SceneGlue leverages a hybridizable matching paradigm that integrates implicit parallel attention and explicit cross-view visibility estimation. The parallel attention mechanism simultaneously exchanges information among local descriptors within and across images, enhancing the scene's global context. To further enrich the scene awareness, we propose the Visibility Transformer, which explicitly categorizes features into visible and invisible regions, providing an understanding of cross-view scene visibility. By combining explicit and implicit scene-level awareness, SceneGlue effectively compensates for the local descriptor constraints. Notably, SceneGlue is trained using only local feature matches, without requiring scene-level groundtruth annotations. This scene-aware approach not only improves accuracy and robustness but also enhances interpretability compared to traditional methods. Extensive experiments on applications such as homography estimation, pose estimation, image matching, and visual localization validate SceneGlue's superior performance. The source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13941
PDF
-
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
2026-04-15 13:55:34Bo Yu, Cheng Yang, Dongyang Hou, Chengfu Liu, Jiayao Liu, Chi Wang, Zhiming Zhang, Haifeng Li, Wentao YangAbstract
The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-based agents remains challenging due to the complex, multi-step nature of geospatial workflows. Existing benchmarks primarily rely on static text or code matching, neglecting dynamic runtime feedback and the multimodal nature of spatial outputs. To address this gap, we introduce GeoAgentBench (GABench), a dynamic and interactive evaluation benchmark tailored for tool-augmented GIS agents. GABench provides a realistic execution sandbox integrating 117 atomic GIS tools, encompassing 53 typical spatial analysis tasks across 6 core GIS domains. Recognizing that precise parameter configuration is the primary determinant of execution success in dynamic GIS environments, we designed the Parameter Execution Accuracy (PEA) metric, which utilizes a "Last-Attempt Alignment" strategy to quantify the fidelity of implicit parameter inference. Complementing this, a Vision-Language Model (VLM) based verification is proposed to assess data-spatial accuracy and cartographic style adherence. Furthermore, to address the frequent task failures caused by parameter misalignments and runtime anomalies, we developed a novel agent architecture, Plan-and-React, that mimics expert cognitive workflows by decoupling global orchestration from step-wise reactive execution. Extensive experiments with seven representative LLMs demonstrate that the Plan-and-React paradigm significantly outperforms traditional frameworks, achieving the optimal balance between logical rigor and execution robustness, particularly in multi-step reasoning and error recovery. Our findings highlight current capability boundaries and establish a robust standard for assessing and advancing the next generation of autonomous GeoAI.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13888
PDF
-
Failure Identification in Imitation Learning Via Statistical and Semantic Filtering
2026-04-15 12:27:32Quentin Rolland, Fabrice Mayran de Chamisso, Jean-Baptiste MouretAbstract
Imitation learning (IL) policies in robotics deliver strong performance in controlled settings but remain brittle in real-world deployments: rare events such as hardware faults, defective parts, unexpected human actions, or any state that lies outside the training distribution can lead to failed executions. Vision-based Anomaly Detection (AD) methods emerged as an appropriate solution to detect these anomalous failure states but do not distinguish failures from benign deviations. We introduce FIDeL (Failure Identification in Demonstration Learning), a policy-independent failure detection module. Leveraging recent AD methods, FIDeL builds a compact representation of nominal demonstrations and aligns incoming observations via optimal transport matching to produce anomaly scores and heatmaps. Spatio-temporal thresholds are derived with an extension of conformal prediction, and a Vision-Language Model (VLM) performs semantic filtering to discriminate benign anomalies from genuine failures. We also introduce BotFails, a multimodal dataset of real-world tasks for failure detection in robotics. FIDeL consistently outperforms state-of-the-art baselines, yielding +5.30% percent AUROC in anomaly detection and +17.38% percent failure-detection accuracy on BotFails compared to existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13788
PDF
-
SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
2026-04-15 10:39:42Haoran Lou, Ziyan Liu, Chunxiao Fan, Yuexin Wu, Yue MingAbstract
Multimodal Large Language Models (MLLMs) exhibit strong reasoning and world knowledge, yet adapting them for retrieval remains challenging. Existing approaches rely on invasive parameter updates, such as full fine-tuning and LoRA, which may disrupt the pre-trained semantic space and impair the structured knowledge essential for reasoning. In this work, we argue that adapting MLLMs for retrieval should focus on eliciting pre-trained representations rather than overwriting them. To this end, we propose SLQ, an effective and efficient framework that adapts a frozen MLLM into a retriever through a small set of Shared Latent Queries. Appended to the end of both text and image token sequences, these queries leverage the model's native causal attention to serve as global aggregation interfaces, producing compact embeddings in a unified space while keeping the backbone unchanged. Furthermore, to better evaluate retrieval beyond superficial pattern matching, we construct KARR-Bench, a benchmark designed for knowledge-aware reasoning retrieval. Extensive experiments show that SLQ outperforms full fine-tuning and LoRA on COCO and Flickr30K, while achieving competitive performance on MMEB and yielding substantial gains on KARR-Bench. The results demonstrate that SLQ, which preserves pre-trained representations, provides an effective and efficient framework for adapting MLLMs to retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13710
PDF
-
Med-CAM: Minimal Evidence for Explaining Medical Decision Making
2026-04-15 10:22:45Pirzada Suhail, Aditya Anand, Amit SethiAbstract
Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black boxes, providing little insight into why a particular diagnosis was reached. In this paper, we introduce Med-CAM, a framework for generating minimal and sharp maps as evidence-based explanations for Medical decision making via Classifier Activation Matching. Med-CAM trains a segmentation network from scratch to produce a mask that highlights the minimal evidence critical to model's decision for any seen or unseen image. This ensures that the explanation is both faithful to the network's behaviour and interpretable to clinicians. Experiments show, unlike prior spatial explanation methods, such as Grad-CAM and attention maps, which yield only fuzzy regions of relative importance, Med-CAM with its superior spatial awareness to shapes, textures, and boundaries, delivers conclusive, evidence-based explanations that faithfully replicate the model's prediction for any given image. By explicitly constraining explanations to be compact, consistent with model activations, and diagnostic alignment, Med-CAM advances transparent AI to foster clinician understanding and trust in high-stakes medical applications such as pathology and radiology.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13695
PDF
-
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
2026-04-15 09:01:54Xuwen Zhou, Fangxin Liu, Chao Wang, Xiao Zheng, Hao Zheng, Min He, Li Jiang, Haibing GuanAbstract
Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, particularly when draft models produce semantically correct but lexically divergent outputs. In this paper, we present Calibrated Speculative Decoding (CSD), a training-free framework that recovers valid tokens discarded by standard verification. Guided by the principle of "Frequency-Guided Candidate Selection and Probability-Guarded Acceptance," CSD incorporates two lightweight modules: Online Correction Memory, which aggregates historical rejections to propose recurring divergence patterns as rescue candidates, and Semantic Consistency Gating, which verifies candidate admissibility using probability ratios instead of exact token matching. Our evaluation across diverse large language models demonstrates that CSD outperforms existing methods, achieving a peak throughput speedup of 2.33x. CSD preserves model accuracy across all tasks while further boosting performance on complex reasoning datasets. These results establish CSD as a highly effective, lightweight solution for practical LLM deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13634
PDF
-
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
2026-04-15 08:05:13Yulu Gao, Bohao Zhang, Zongheng Tang, Jitong Liao, Wenjun Wu, Si LiuAbstract
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult due to severe changes in scale, perspective, and occlusion, which destabilize direct pixel-level matching. While recent geometry-aware models like VGGT provide a strong foundation for feature alignment, we find they often fail at dense prediction tasks due to significant pixel-level projection drift, even when their internal object-level textntion remains consistent. To bridge this gap, we introduce VGGT-Segmentor (VGGT-S), a framework that unifies robust geometric modeling with pixel-accurate semantic segmentation. VGGT-S leverages VGGT's powerful cross-view feature representation and introduces a novel Union Segmentation Head. This head operates in three stages: mask prompt fusion, point-guided prediction, and iterative mask refinement, effectively translating high-level feature alignment into a precise segmentation mask. Furthermore, we propose a single-image self-supervised training strategy that eliminates the need for paired annotations and enables strong generalization. On the Ego-Exo4D benchmark, VGGT-S sets a new state-of-the-art, achieving 67.7% and 68.0% average IoU for Ego to Exo and Exo to Ego tasks, respectively, significantly outperforming prior methods. Notably, our correspondence-free pretrained model surpasses most fully-supervised baselines, demonstrating the effectiveness and scalability of our approach.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13596
PDF
-
Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis
2026-04-15 07:52:53Yuchao Chen, Hanqing WangAbstract
We present Dehaze-then-Splat, a two-stage pipeline for multi-view smoke removal and novel view synthesis developed for Track~2 of the NTIRE 2026 3D Restoration and Reconstruction Challenge. In the first stage, we produce pseudo-clean training images via per-frame generative dehazing using Nano Banana Pro, followed by brightness normalization. In the second stage, we train 3D Gaussian Splatting (3DGS) with physics-informed auxiliary losses -- depth supervision via Pearson correlation with pseudo-depth, dark channel prior regularization, and dual-source gradient matching -- that compensate for cross-view inconsistencies inherent in frame-wise generative processing. We identify a fundamental tension in dehaze-then-reconstruct pipelines: per-image restoration quality does not guarantee multi-view consistency, and such inconsistency manifests as blurred renders and structural instability in downstream 3D this http URL analysis shows that MCMC-based densification with early stopping, combined with depth and haze-suppression priors, effectively mitigates these artifacts. On the Akikaze validation scene, our pipeline achieves 20.98\,dB PSNR and 0.683 SSIM for novel view synthesis, a +1.50\,dB improvement over the unregularized baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13589
PDF
