Searcharxiv⌕ Search

arXiv subjects

Zhiguang Liu

Publications and source records attributed to Zhiguang Liu.

9 recordsLinked to original sources

Role-Separated Diffusion Transformers: Global Rule Isolation and Deterministic Sampling Manifold Compression

We present Role-Separated Diffusion Transformers (RoSeDiT), a new diffusion transformer architecture that isolates the global rule from the image tokens. RoSeViT showed in visual reasoning that a vanilla ViT spreads a shared rule over all $L$ tokens at an entropy of order $Ld$, whereas an enforced controller route reduces it to order $d$. In class-conditional DiT and SiT, the class and the noise level are explicitly conditioned by adaLN, so a RoSeViT-style controller channel on the ViT side is insufficient to establish the full role separation. By introducing the adaLN listening mechanism, which makes adaLN compute under the controller's command, RoSeDiT brings the entropy theorem and role separation into the latent diffusion domain. Under the same SiT training and evaluation protocol at the same level of parameter count, RoSeDiT surpasses SiT at all four model scales at 400K steps, and RoSeDiT-L/2 even surpasses SiT-XL/2's 17.2 FID with 15.34 and 32% fewer parameters. RoSeDiT-XL/2 surpasses SiT-XL/2's 7M-step FID of 8.3 at 1.4M steps with 7.98, using one-fifth as many training steps. We further observe that models with the same denoising loss can have a large FID gap, which indicates a misalignment between the denoising objective and the image manifold. We formalize this phenomenon into Deterministic Sampling Manifold Compression (DSMC), a two-stage training schedule with which RoSeDiT-XL/2 surpasses SiT + REPA's 4M-step FID of 5.9 at 2.4M steps with 5.84.

cs.CV↗

RoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning

ARC tasks can be formulated as visual transformation problems, where a model must infer a high-level transformation rule from a small set of demonstrations and apply it consistently across a grid. While dense Vision Transformers (ViTs) perform well in this setting, they entangle local visual state and global transformation logic within a shared token representation, which can hinder consistent reasoning. In this paper, we introduce RoSeViT, a role-separated Vision Transformer that explicitly decouples high-level instruction inference from visual workspace computation. RoSeViT uses controller tokens to aggregate transformation-level information and workspace tokens to represent the visual grid, with a structured attention pass in which nonlocal workspace interactions are routed through the controller. This design is motivated by our formal analysis showing that enforcing a shared instruction representation can reduce the effective complexity of visual transformation modeling. RoSeViT outperforms dense ViT baselines under the standard VARC training and evaluation protocol for ARC. In a controlled backbone replacement setting, it improves ARC-1 accuracy from 54.5 to 56.6, and with recurrent refinement reaches 58.8. When integrated into the full system, RoSeViT-Ensemble improves performance from 60.4 to 62.6 on ARC-1. These results demonstrate that explicitly separating instruction and workspace representations leads to more effective visual reasoning on ARC tasks. GitHub repository: https://github.com/lz7fd/RoSeViT.

cs.AI↗

Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher

Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation. Under standard training, however, they often yield lower generation quality than bidirectional models of the same size. Many existing approaches address this gap by initializing from or distilling a pretrained bidirectional teacher. We instead train a causal model from an image-model initialization, with no bidirectional video model at any stage. Because this path requires neither a large bidirectional teacher nor a complex distillation pipeline, it is simpler and more scalable. On this path, we find that a causal model trained on ground-truth history becomes strongly dependent on it, so that at inference errors in its own generated history propagate forward. We hypothesize that much of this dependence is unnecessary, because the current input already determines much of what the history provides. We propose Conditional Residual Prediction (CRP), a simple recipe for reducing a model's reliance on a condition: the model first predicts the target without the condition, and the condition may only add a residual on top of this prediction. Applied to history, CRP makes the model predict each chunk from the present as far as it can and use the past only for what the present cannot supply. In controlled experiments, CRP nearly closes the 6.14-point gap to a bidirectional model trained under the same setup. Scaling this recipe, we train Optica, a 2B-parameter causal video model that autoregressively generates 5-second 480p videos and reaches 82.78 on VBench with only about 15M training videos.

cs.CV↗

4DStreamCtrl: Interactive Video Generation with Online 4D Control

Generative video models now synthesize footage nearly indistinguishable from reality. Their promise as interactive tools hinges on fine-grained control of how objects and the camera move over time, yet each existing approach captures only part of this: camera-parameter methods steer the viewpoint but cannot move objects, 2D-trajectory methods act in the image plane and ignore depth and occlusion, and recent 3D methods add geometry but run only offline at a fixed length. In particular, none combines 3D-consistent control of both camera and objects with real-time, streaming generation. Here we show that camera motion, object trajectories, and depth can be unified into a single 3D point-track representation, from which one model performs joint camera and object control, depth editing, and motion transfer in a single forward pass. To learn this interface at scale, we mine in-the-wild video for 3D motion supervision, yielding OpenVidHD-Motion3D, and encode it with a lightweight Geometric Motion Head that plugs into a pretrained video diffusion model. Because this encoder is temporally separable, we distill the model into a causal streaming student that generates arbitrarily long video in four denoising steps at memory independent of length. This unified design surpasses prior camera-only, 2D, and offline-3D methods in motion-control precision while covering modalities they address only in isolation. 4DStreamCtrl runs at 20 FPS on a single high-end GPU for 480p video and stays temporally coherent over hundreds of frames, enabling, to our knowledge, interactive 4D-controllable streaming generation for the first time. More broadly, grounding generation in explicit 3D geometry with efficient causal inference points toward interactive world models with closed-loop spatiotemporal control, from controllable simulators to real-time visual imagination for embodied agents.

cs.CV↗

HunyuanVideo 1.5 Technical Report

We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.

cs.CV↗

Inverse design of artificial skins

Mimicking the perceptual functions of human cutaneous mechanoreceptors, artificial skins or flexible pressure sensors can transduce tactile stimuli to quantitative electrical signals. Conventional methods to design such devices follow a forward structure-to-property routine based on trial-and-error experiments/simulations, which take months or longer to determine one solution valid for one specific material. Target-oriented inverse design that shows far higher output efficiency has proven effective in other fields, but is still absent for artificial skins because of the difficulties in acquiring big data. Here, we report a property-to-structure inverse design of artificial skins based on small dataset machine learning, exhibiting a comprehensive efficiency at least four orders of magnitude higher than the conventional routine. The inverse routine can predict hundreds of solutions that overcome the intrinsic signal saturation problem for linear response in hours, and the solutions are valid to a variety of materials. Our results demonstrate that the inverse design allowed by small dataset is an efficient and powerful tool to target multifarious applications of artificial skins, which can potentially advance the fields of intelligent robots, advanced healthcare, and human-machine interfaces.

cond-mat.soft↗

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding

Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document textlines. We introduce textline-region contrastive learning to achieve fine-grained alignment between the visual regions and texts of document textlines. Furthermore, masked region modeling and textline-grid matching are also designed to enhance the visual and layout representations of textlines. Experiments show that our Wukong-Reader has superior performance on various VDU tasks such as information extraction. The fine-grained alignment over textlines also empowers Wukong-Reader with promising localization ability.

cs.CL↗

Noise-resilient approach for deep tomographic imaging

We propose a noise-resilient deep reconstruction algorithm for X-ray tomography. Our approach shows strong noise resilience without obtaining noisy training examples. The advantages of our framework may further enable low-photon tomographic imaging.

eess.IV↗

One-shot Key Information Extraction from Document with Deep Partial Graph Matching

Automating the Key Information Extraction (KIE) from documents improves efficiency, productivity, and security in many industrial scenarios such as rapid indexing and archiving. Many existing supervised learning methods for the KIE task need to feed a large number of labeled samples and learn separate models for different types of documents. However, collecting and labeling a large dataset is time-consuming and is not a user-friendly requirement for many cloud platforms. To overcome these challenges, we propose a deep end-to-end trainable network for one-shot KIE using partial graph matching. Contrary to previous methods that the learning of similarity and solving are optimized separately, our method enables the learning of the two processes in an end-to-end framework. Existing one-shot KIE methods are either template or simple attention-based learning approach that struggle to handle texts that are shifted beyond their desired positions caused by printers, as illustrated in Fig.1. To solve this problem, we add one-to-(at most)-one constraint such that we will find the globally optimized solution even if some texts are drifted. Further, we design a multimodal context ensemble block to boost the performance through fusing features of spatial, textual, and aspect representations. To promote research of KIE, we collected and annotated a one-shot document KIE dataset named DKIE with diverse types of images. The DKIE dataset consists of 2.5K document images captured by mobile phones in natural scenes, and it is the largest available one-shot KIE dataset up to now. The results of experiments on DKIE show that our method achieved state-of-the-art performance compared with recent one-shot and supervised learning approaches. The dataset and proposed one-shot KIE model will be released soo

cs.CV↗