arXiv subjects

Xinggang Wang

Publications and source records attributed to Xinggang Wang.

At least 19 recordsLinked to original sources

arXiv2026

Cross-Encoder Anchor Refinement for Zero-Shot Anomaly Detection

Zero-shot anomaly detection aims to transfer anomaly discrimination from auxiliary training domains to unseen categories while localizing subtle defects. A key challenge is to construct discriminative references that combine contextual representations with complementary local evidence. We present Cross-Encoder Anchor Refinement (CEAR), which connects two visual encoding paths for the same image at the anchor stage, before normal and anomalous prototypes are constructed. An independent convolutional encoder pretrained for industrial product recognition builds an image-specific memory shared across selected vision transformer (ViT) layers. Spatial anchors read from ViT patch features query this memory through cross-attention and undergo residual refinement. Image-conditioned normal and anomalous queries then gate anchor aggregation to construct prototypes for anomaly scoring. Across 13 industrial and medical datasets, CEAR achieves the best performance in 57 of 68 evaluations spanning image-level detection and pixel-level localization. Notably, CEAR surpasses all other state-of-the-art methods in 41 of 44 pixel-level comparisons. Across 11 localization datasets, mean gains in pixel-level maximum F1 score and average precision are 4.45 and 3.79 percentage points, respectively. This study shows how cross-encoder interaction at the anchor stage can integrate complementary visual representations for fine-grained anomaly localization across domains.

cs.CV↗

arXiv2026

Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?

Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective. However, quantization error is widely assumed to cause unavoidable semantic loss, fundamentally limiting the semantic fidelity of discrete visual tokens and positioning continuous visual representations as an intrinsic upper bound. Using multimodal understanding as a proxy for semantic fidelity, we revisit this assumption and find quantization error unreliable, as discrete representations with substantially larger errors can achieve better understanding. Instead, the effective bit budget of discrete indices emerges as a key determinant of downstream performance. However, existing quantizers eventually saturate as additional codebooks contribute progressively less semantic information. As one approach to alleviating this saturation, we introduce Factorized Vector Quantization, which quantizes complementary, fixed-dimensional views of the visual feature with symmetric parallel codebooks. It continues to improve at larger bit budgets, ultimately matching continuous visual representations in multimodal understanding. Trained on industrial-scale multimodal data, our model achieves state-of-the-art performance among discrete-representation models, outperforming UniAR and Emu3-Chat by 22.8% and 59.2%, respectively, on a nine-metric average. To our knowledge, it is also the first discrete-representation model competitive with strong continuous-representation models such as Qwen3-VL, including on fine-grained OCR tasks. We further identify the key principles and a practical recipe enabling this competitiveness. These results and insights support the potential of discrete visual representations to underpin large-scale native multimodal foundation models. Code and models are available at https://github.com/hustvl/FVQ

cs.CV↗

arXiv2026

Latent Bridge: From Video Latents to 3D Geometry via Feature Alignment

Video generation and feed-forward 3D reconstruction typically use separate representations, requiring RGB decoding and visual re-encoding to recover geometry from generated latents. We propose Latent Bridge, which connects video generative latent spaces with geometric feature spaces to directly predict 3D geometry from video latents. We develop representation-specific bridges for Wan2.1 and V-RAE, enabling feed-forward prediction of cameras, depth, and 3D point clouds without the intermediate RGB pathway. Each bridge is trained on RGB videos through feature distillation, while the video encoder and geometry model remain frozen. Training requires neither ground-truth geometry nor execution of the downstream geometric aggregator or prediction heads. At inference, the same video latents support both RGB decoding and geometry prediction. The same trained bridge can be reused for image-to-video and text-to-video generation within the same video latent space, without bridge retraining. Experiments on Co3Dv2 and WildRGB-D demonstrate competitive geometric reconstruction quality, efficient end-to-end generation and reconstruction, and faster latent-to-geometry decoding, highlighting latent alignment as a practical and reusable interface between video generation and 3D reconstruction. Our code is available at: https://github.com/hustvl/Latent-Bridge.

cs.CV↗

arXiv2026

LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction

Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstruction methods rapidly predict 3D scenes from a small set of images, but extending them to longer sequences presents two bottlenecks: jointly processing all views increases GPU memory requirements, while accumulating pixel-aligned predictions redundantly represents the same surfaces and increases storage and rendering costs. We present LonGaussian, a streaming feed-forward framework that reconstructs compact, globally renderable Gaussian scenes from long image sequences with known intrinsics and unknown camera poses. Built on a pretrained streaming 3D reconstruction backbone, LonGaussian decodes long-context geometric features into dense Gaussians. Within each chunk, multi-frame point tracks link repeated observations of the same surface and guide a learned merger to consolidate the corresponding Gaussian predictions. Rendered-depth consistency filtering further suppresses Gaussians from other chunks that incorrectly occlude locally reconstructed surfaces. On DL3DV and RealEstate10K benchmarks, LonGaussian improves novel-view rendering quality while using substantially fewer Gaussians than the evaluated feed-forward baselines.

cs.CV↗

arXiv2026

DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving

Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous driving. However, effectively integrating both capabilities for trajectory generation remains challenging. In this work, we propose DriveWLA, a unified World-Language-Action model based on Mixture-of-Transformers (MoT) that jointly models semantic understanding, future scene dynamics, and trajectory generation. DriveWLA consists of three experts: a World Expert for future prediction, a Language Expert for semantic understanding, and an Action Expert for trajectory generation. We further introduce Cross-Expert Attention, which enables controlled information flow across experts while aligning semantic and dynamic representations. To improve trajectory generation beyond imitation learning, we apply Flow-GRPO reinforcement learning post-training to refine the Action Expert. Extensive experiments show that DriveWLA achieves superior performance in both open-loop and closed-loop evaluation. DriveWLA achieves 92.3 PDMS on NAVSIM v1 and 90.1 EPDMS on NAVSIM v2, demonstrating strong performance among VLM-based and world-model-based planners. Without specific fine-tuning, DriveWLA further demonstrates strong zero-shot generalization to HUGSIM, nuScenes, and Bench2Drive. These results validate the effectiveness of our unified World-Language-Action modeling, establishing DriveWLA as a generalizable framework for autonomous driving.

cs.CV↗

arXiv2026

ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving

End-to-end driving requires rich spatiotemporal representations to support scene understanding and trajectory planning under strict latency constraints. However, most systems initialize their visual encoders from generic image pretraining and densely process all patch tokens for each camera view and input frame, limiting both representation quality and inference efficiency. To address these challenges, we present ConDenseDrive, a knowledge-dense and token-sparse visual encoder for end-to-end autonomous driving. Our three-stage framework first makes the encoder knowledge-dense by distilling complementary visual, semantic, and geometric knowledge from three vision foundation models. It then adapts the distilled encoder to multi-frame end-to-end driving and integrates spatiotemporal context into register tokens for planning. Finally, it makes the encoder token-sparse by applying register-guided token compression, reducing redundant patch computation and yielding a 2.0$\times$ speedup while improving planning performance. ConDenseDrive achieves 94.5 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2, and reaches 37.4 HD-Score in zero-shot evaluation on HUGSIM. Extensive experiments and qualitative analyses demonstrate that visual encoder design provides an effective route to reliable and efficient end-to-end driving.

cs.CV↗

arXiv2026

XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos

Small object detection and tracking in videos remain critical yet underexplored challenges in computer vision, particularly for applications such as public safety, aerial surveillance, and autonomous driving. Existing benchmarks offer limited support due to limited numbers of small objects, constrained category diversity, and narrow scene coverage. To address these limitations, we introduce XS-VID, a large-scale video benchmark comprising 223K frames and 1.4M annotated bounding boxes across 374 video sequences spanning diverse scene types. XS-VID provides extensive coverage of small-object scales, particularly for extremely small ($0\sim12^2$ pixels) and small ($12^2\sim20^2$ pixels) objects, which collectively constitute over 55% of all annotations. For systematic evaluation, we establish three dedicated tracks: Detection, multiple object tracking (MOT), and single object tracking (SOT), and extensively test the existing state-of-the-art methods on each. The experimental results indicate that existing methods face significant challenges with XS-VID, mainly stemming from insufficient modeling of spatiotemporal features at small scales. To tackle these challenges, we propose a lightweight, high-precision detection framework dubbed YOLOFT. It enhances small-object feature representation and spatiotemporal integration while preserving high detection speed, thereby achieving improved accuracy and robustness on both the XS-VID and VisDrone benchmarks. Our dataset and code are publicly available at https://gjhhust.github.io/XS-VID/, providing a solid foundation for future research on small-object detection and tracking in videos.

cs.CV↗

arXiv2026

Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis

This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands. Unlike existing VLG methods that tightly couple foundation models with end-to-end grasp policies, AdaRoboVLG learns an efficient generalizable base policy that generates and evaluates physically feasible grasp candidates through explicit kinematic mapping and force-closure-based stability estimation, while offloading task-dependent understanding to specialized foundation-model modules. These modules provide composable priors that are integrated into the grasp synthesis process, enabling contextually adaptive grasp synthesis without retraining the underlying grasp policy. Through extensive simulation and real-world experiments, we demonstrate that (i) the base policy exhibits efficient learning and strong cross-hand generalization, (ii) the framework effectively incorporates spatial, cognitive, and temporal priors to address three representative grasping challenges without compromising grasp synthesis performance compared to state-of-the-art methods, and (iii) these priors can operate jointly to enable functional grasping in cluttered and dynamic environments. These results indicate that decoupling physical grasp synthesis from task-dependent understanding provides a scalable paradigm for robotic grasping, allowing future advances in foundation models to be directly translated into improved grasp capabilities without redesigning or retraining the underlying grasp policy. Supplementary videos are available at https://adarobovlg.github.io/

cs.RO↗

arXiv2026

Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces

We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and quantized images as discrete tokens or combine discrete language prediction with continuous image generation. The former introduces a visual quantization bottleneck. The latter requires modality-dependent objectives and sampling procedures. Fully continuous modeling avoids these trade-offs and enables a shared generative process, but remains underexplored for multimodal pretraining. Multimodal Flow introduces a unified continuous architecture that integrates multimodal continuous representations with a shared chunk-causal flow backbone. It organizes text blocks and images as ordered continuous hyperchunks, preserving textual token order and visual spatial structure. The backbone learns a single vector field over these hyperchunks through Flow Matching. Joint attention enables cross-modal interaction, while modality-specific feed-forward networks process each modality. The model predicts multiple target chunks in parallel during training and generates hyperchunks sequentially at inference. We instantiate MF-1 and pretrain it on multimodal data. Across 0.6B, 1.2B, and 1.6B scales, continued pretraining consistently improves multimodal modeling. With only 150B pretraining tokens, MF-1 achieves an average score of 82.8 across GenEval and DPG-Bench and 75.3 across VQAv2, MMBench, and POPE, remaining competitive with unified models trained on substantially more data. Under matched data, optimization, and parameter budgets, Multimodal Flow further outperforms representative hybrid and discrete models. These results establish continuous chunk-based embedding flow modeling as a new fully continuous paradigm for unified multimodal modeling. The related code and model are publicly released at https://github.com/hustvl/Multimodal-Flow.

cs.CV↗

arXiv2026

Rethinking Representations for World-Action Modeling

World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning. These findings motivate ReWAM, a representation-centric world-action model built on pre-trained DINO features. Feature Calibration and a Temporal Representation Bottleneck organize these features into compact world states suited to dynamics modeling. Action-Grounded Representation Shaping routes only action-loss gradients to the bottleneck, thereby letting the policy shape what the representation encodes while the world model learns how it evolves. Without generative video pre-training, ReWAM achieves 93.6% success on RoboTwin 2.0. On RoboDojo, it achieves an average score of 12.29 and a success rate of 8.28% using approximately 600 hours of embodied pre-training data.

cs.CV↗

arXiv2026

ReDrive: Shaping Representations with World Modeling for End-to-End Driving

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by the transferability of general-purpose visual representations, we argue that combining sufficiently strong visual representations with representation world modeling can support effective planning without relying on complex inference-time auxiliary modules. Based on this insight, we present ReDrive, an end-to-end driving framework that strengthens planning-oriented visual features via future representation prediction. To achieve this, ReDrive adopts a three-stage training pipeline consisting of driving video pretraining, joint world-modeling and planning training, and planner adaptation. This yields a strong planning-oriented representation and a high-performance planner, while requiring neither auxiliary perception modules nor future prediction at inference time. Experiments on NAVSIM demonstrate strong performance, achieving 91.0 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. These results show that shaping representations with world modeling is sufficient to enable high-performance end-to-end planning while retaining a simple encoder-planner inference pipeline.

cs.CV↗

arXiv2026

ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model

Existing latent world models are typically optimized for future predictability, yet the resulting representations are not necessarily useful for planning in autonomous driving. Predictions are commonly used for pretraining or auxiliary supervision rather than as direct conditioning signals for trajectory generation. We propose ForeDrive, which learns a planning-relevant latent representation and couples it asymmetrically to a Diffusion Transformer (DiT) planner. The planner consumes multi-horizon latent future representations learned with a JEPA-style world model; planning gradients update the shared online encoder, while stop-gradient routing trains the latent predictor with forecasting losses only. Because predicted futures have varying reliability across horizons and BEV trajectories are misaligned with image tokens, we use gated visual fusion, future-status injection, and Trajectory-Adaptive Bias (TAB) to inject future latents as guidance without overriding the current observation. Trained with pure imitation learning and using only the current front-view image as visual input at inference, ForeDrive attains 89.9 PDMS on NAVSIM v1 and 90.0 one-stage EPDMS on NAVSIM v2, without reinforcement learning or an external trajectory scorer.

cs.CV↗

arXiv2026

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Vector Quantization (VQ) is fundamental to discrete visual tokenizers that power modern autoregressive and masked image generation models. While recent shared-projection codebook methods have substantially advanced codebook utilization, training stability remains a critical and underexplored challenge. We argue that the root cause lies in the entanglement of the Encoder--Decoder and Codebook training: because neither module can reliably fulfill its own responsibility in isolation, the system can only function when the two subsystems happen to cooperate---a fragile condition that breaks down precisely when training is most stressed. We propose StableVQ, which revisits the proper learning objective of each module and resolves the problems that arise when each is trained to fulfill its own role independently. Concretely, (1) Dynamic STE corrects the instability in the Encoder's learning objective, enabling it to robustly optimize the reconstruction space under discrete regularization even when codebook utilization is low. (2) Region VQ Loss reconceives the Codebook's learning objective so that it can independently guarantee full tracking of the encoder output distribution, without relying on encoder oscillations to drive activation. (3) Decoupled Schedule recognizes that the distinct responsibilities of the Encoder--Decoder and the Codebook demand distinct optimization dynamics, and assigns each an independent learning rate schedule to ensure robust system-level behavior. Built on top of shared-projection codebooks, StableVQ is lightweight and introduces no learnable parameters. Experiments on ImageNet demonstrate consistent improvements in training stability, codebook utilization, and reconstruction quality across diverse codebook sizes and initialization settings.

cs.CV↗

arXiv2026

Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D

Vision-Language-Action (VLA) models have demonstrated remarkable generalization in robotic manipulation via large-scale multimodal pretraining. However, VLA models are mainly trained on 2D-centric observations, which inherently constrains their capacity for precise spatial manipulation. Previous methods enhance 3D awareness by introducing implicit spatial priors, but still lack explicit geometry guidance. In this paper, we propose Bridge3D that integrates both implicit and explicit 3D geometry guidance into pre-trained 2D VLA models, enabling them to ''see'' and ''act'' in 3D. Bridge3D introduces two strategies: 1) Implicit Fusion, which enriches visual tokens with features from 3D foundation models to improve ''seeing'' in 3D; 2) Explicit Conditioning, which integrates action denoising with an explicit 3D semantic field to achieve ''acting'' in 3D. Furthermore, we utilize the proposed layer-wise linear probing to improve learning efficiency. Experiments show that Bridge3D achieves superior performance against state-of-the-art methods. On the RoboTwin 2.0 benchmark, Bridge3D exceeds $π_0$ by 14.0 percentage points, while in real-world experiments, it outperforms Spatial Forcing by 11.7 percentage points. These results demonstrate Bridge3D's strong capabilities in high-precision and spatial-sensitive manipulation tasks.

cs.RO↗

arXiv2026

ReWorld: Representation Learning for World Action Models

World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only the final outputs, leaving intermediate representations as incidental byproducts. We present ReWorld, the first representation learning framework specifically designed for autonomous-driving WAMs. ReWorld explicitly optimizes the latent world-to-action pathway through three complementary mechanisms. First, it imposes future-predictive supervision on intermediate Video DiT states to encode temporal scene dynamics, enabling self-guided sampling and a roughly twofold convergence speedup. Second, it aligns Action DiT states with their attended video readouts so that the retrieved world information is retained in the representations used for planning. Third, it shapes the action space using geometrically close yet low-scoring hard negatives to separate the expert trajectory from nearby unsafe alternatives. ReWorld constructs supervision entirely from the WAM's own generation targets and attended features, requiring no external encoders or teacher models and introducing only 0.3% additional per-step training cost. Experiments show that ReWorld reduces FVD from 81.3 to 61.9 on nuScenes, improves closed-loop PDMS from 89.1 to 90.4 on NAVSIM without reinforcement learning or test-time scoring, and increases frozen linear-probe accuracy from 68.3% to 80.2% on UCF-101 action recognition. These results indicate that explicitly optimized representations are central to translating world knowledge into planning capability in WAMs.

cs.CV↗

arXiv2026

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalability, or inject partial, view-conditioned geometric priors and leave the language model to recover global scene structure from sparse cues. We introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation from unposed multi-view RGB images. Its Predictive Spatial Field Modeling objective compresses context views into a compact latent representation and predicts aligned geometric and semantic feature fields at novel viewpoints, thereby encouraging coherent encoding of scene geometry and layout. We integrate the pre-trained Spa3R Encoder into a vision-language model through a lightweight residual cross-attention adapter, yielding Spa3-VLM and grounding language reasoning in global spatial context. Spa3-VLM achieves an average score of 58.6% on VSI-Bench and delivers leading or competitive performance across three additional spatial reasoning benchmarks. These results demonstrate that predictive spatial representation learning provides an effective visual foundation for 3D reasoning.

cs.CV↗

arXiv2026

Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation

Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming video diffusion models introduce a fundamental train-inference mismatch: inference follows a specialized denoising order, whereas advanced training strategies typically require diverse noise-level configurations. To address this trade-off between train-inference consistency and training coverage, we reformulate the video diffusion sampling as a frame-indexed stochastic process over noise levels. Within this stochastic process space, we construct a continuous training trajectory along which the sampling schedule progressively evolves from independent sampling to inference-consistent sampling. We further introduce a joint calibration algorithm and a temporal correlative sampling algorithm to ensure trajectory smoothness and cross-frame correlation. Building on these designs, we propose Stream Forcing, a unified training framework for streaming video generation that balances training sufficiency and inference efficiency. Extensive experiments demonstrate that Stream Forcing significantly improves generation quality with a 36.6% FVD improvement on the UCF-101 benchmark. Furthermore, our method facilitates robust zero-shot extrapolation to long-horizon video generation with a 27.9% FVD improvement on the UCF-101 benchmark.

cs.CV↗

arXiv2026

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

World Action Models (WAMs) improve robot manipulation by learning how the environment evolves beyond the current observation. However, existing approaches face a fundamental dilemma: Joint-WAMs preserve future-aware representations during inference but incur prohibitive computation costs, while efficient alternatives remove future modeling at inference time and may lose the robustness benefits of temporal reasoning. In this work, we revisit the role of future representations in WAMs and show that inference-time future conditioning is critical for generalization under distribution shifts. This observation motivates Faster-WAM, an efficient future-conditioning WAM that preserves future representations while avoiding expensive video-action interaction. Faster-WAM introduces a sparse future-conditioning framework that computes future representations once and selectively reuses them throughout action denoising. Specifically, we propose SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fusion to aggregate multi-depth future representations without increasing attention complexity. Experiments demonstrate that Faster-WAM achieves a substantially better performance-efficiency trade-off than existing WAMs. On the out-of-distribution LIBERO-Plus benchmark, Faster-WAM improves success rate from 49.14% to 73.57% compared with Fast-WAM, while running 2.21$\times$ faster than Joint-WAM. It further achieves state-of-the-art performance on LIBERO and RoboTwin 2.0, while demonstrating strong robustness in real-world manipulation.

cs.CV↗