arXiv subjects

Tianshui Chen

Publications and source records attributed to Tianshui Chen.

At least 19 recordsLinked to original sources

arXiv2026

Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning

Training deep learning models with freely available web images can reduce their dependence on costly manual annotations. Although webly supervised learning has been widely studied for single-label recognition, its multi-label counterpart remains underexplored, partly due to the lack of unified benchmarks and fair comparison protocols. To address this gap, we construct a benchmark for webly supervised multi-label recognition (WS-MLR), including Web-COCO and Web-Pascal, and re-implement representative baselines under a unified setting. The two datasets cover the same 80 and 20 categories as MS-COCO and Pascal VOC, respectively, and contain about 300 thousand images retrieved from the Internet using category-word combinations as search keywords. We further propose a Dual-Branch Multi-Label Contrastive Learning (DBMLCL) framework, which learns category-specific instance-level and category-level representations together with their similarities to identify and correct noisy labels. Extensive experiments on the benchmark demonstrate that DBMLCL achieves superior performance compared to representative baselines.

cs.CV↗

arXiv2026

Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation

Generating realistic interior furniture layouts that strictly adhere to architectural constraints (e.g., walls, doors, and windows) remains a fundamental challenge in automated spatial design. Existing approaches, primarily based on one-shot generation using diffusion models or Large Language Models (LLMs), lack explicit mechanisms for intermediate geometric constraint verification, often resulting in structural collisions and functionally infeasible arrangements under complex room constraints. To address these challenges, we propose Agentic Designer, a progressive, multi-agent framework that formulates structure-aware interior layout generation as an iterative and constraint-verified decision process. By decomposing layout synthesis into modular stages of proposal, verification, and adjustment, the framework coordinates three specialized agents, a Generator, an Evaluator, and a Refiner, through a Progressive Consensus Mechanism. This mechanism enforces stepwise geometric validation and correction before each placement is committed, thereby preventing error accumulation. To facilitate this structure-aware paradigm and standardize evaluation, we establish InStruct, a comprehensive benchmark that integrates a dataset comprising over 18,000 high-quality, parametrically annotated samples with a novel suite of structure-centric metrics. Extensive quantitative evaluations, qualitative analyses, and user studies show that Agentic Designer significantly outperforms state-of-the-art methods, demonstrating substantial improvements in strict structural adherence and functional design coherence.

cs.CV↗

arXiv2026

Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation

Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely aligned frames of the same individual with identical speech but different expressions, which impedes direct supervision for emotional manipulation. While current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision, their direct application is limited. To this end, we propose a Personalized Cross-Modal Emotional Correlation Learning (PCMECL) algorithm that refines VLM-based supervision through two major improvements. First, standard VLMs rely on a single generic prompt for each emotion, failing to capture expressive variations among individuals. PCMECL addresses this limitation by conditioning on individual visual information to learn personalized prompts, thereby establishing more fine-grained visual-semantic correlations. Second, even with personalization, inherent discrepancies persist between the visual and semantic feature distributions. To bridge this modality gap, PCMECL employs feature differencing to correlate the modalities, providing more precisely aligned supervision by matching the change in visual features to the change in semantic features. As a plug-and-play module, PCMECL can be seamlessly integrated into existing SPFEM models. Extensive experiments across various datasets demonstrate the superior efficacy of our algorithm.

cs.CV↗

arXiv2026

Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation

Speech-preserving facial expression manipulation (SPFEM) aims to modify facial emotions while meticulously maintaining the mouth animation associated with spoken content. Current works depend on inaccessible paired training samples for the person, where two aligned frames exhibit the same speech content yet differ in emotional expression, limiting the SPFEM applications in real-world scenarios. In this work, we discover that speakers who convey the same content with different emotions exhibit highly correlated local facial animations in both spatial and temporal spaces, providing valuable supervision for SPFEM. To capitalize on this insight, we propose a novel spatial-temporal coherent correlation learning (STCCL) algorithm, which models the aforementioned correlations as explicit metrics and integrates the metrics to supervise manipulating facial expression and meanwhile better preserving the facial animation of spoken content. To this end, it first learns a spatial coherent correlation metric, ensuring that the visual correlations of adjacent local regions within an image linked to a specific emotion closely resemble those of corresponding regions in an image linked to a different emotion. Simultaneously, it develops a temporal coherent correlation metric, ensuring that the visual correlations of specific regions across adjacent image frames associated with one emotion are similar to those in the corresponding regions of frames associated with another emotion. Recognizing that visual correlations are not uniform across all regions, we have also crafted a correlation-aware adaptive strategy that prioritizes regions that present greater challenges. During SPFEM model training, we construct the spatial-temporal coherent correlation metric between corresponding local regions of the input and output image frames as an additional loss to supervise the generation process.

cs.CV↗

arXiv2026

Robotic Manipulation is Vision-to-Geometry Mapping: Vision-Geometry Backbones over Language and Video Models

At its core, robotic manipulation is a problem of vision-to-geometry mapping ($f(v) \rightarrow G$). Physical actions are fundamentally defined by geometric properties like 3D positions and spatial relationships. Consequently, we argue that the foundation for generalizable robotic control should be a vision-geometry backbone, rather than the widely adopted vision-language or video models. Conventional VLA and video-predictive models rely on backbones pretrained on large-scale 2D image-text or temporal pixel data. While effective, their representations are largely shaped by semantic concepts or 2D priors, which do not intrinsically align with the precise 3D geometric nature required for physical manipulation. Driven by this insight, we propose the Vision-Geometry-Action (VGA) model, which directly conditions action generation on pretrained 3D representations. Specifically, VGA replaces conventional language or video backbones with a pretrained 3D world model, establishing a seamless vision-to-geometry mapping that translates visual inputs directly into physical actions. To further enhance geometric consistency, we introduce Progressive Volumetric Modulation and jointly train action and 3D property prediction to preserve geometric representations. Extensive experiments validate the effectiveness of our approach. Across simulation benchmarks, VGA outperforms leading VLA, 3D-VLA, and WAM baselines, including $\pi_{0.5}$, OpenVLA-OFT, GeoVLA, and Motus. In real-world deployments, VGA surpasses $\pi_{0.5}$ under unseen viewpoints and accurately follows language instructions for target grasping. These results highlight that operating on native 3D representations, rather than relying primarily on language or video priors, offers a promising direction toward generalizable physical intelligence. Project page: https://hcplab-sysu.github.io/VisionGeometryActionModel.

cs.RO↗

arXiv2026

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly modeling assembly hierarchy or geometric constraints, which enlarges the search space, accumulates local errors, and often causes cascading failures in complex assemblies. To address this issue, we propose a hierarchical and geometry-aware graph as an intermediate representation. The graph models multi-level parts and components as nodes and encodes explicit geometric constraints as edges. Instead of mapping text directly to code, our framework first predicts structure and constraints, then conditions action sequencing and code generation, thereby improving geometric fidelity and constraint satisfaction. We further introduce a structure-aware progressive curriculum learning strategy that constructs graded tasks through controlled structural edits, explores the model's capability boundary, and synthesizes boundary examples for iterative training. In addition, we build a 12K dataset with instructions, decomposition graphs, action sequences, and bpy code, together with graph- and constraint-oriented evaluation metrics. Extensive experiments show that our method consistently outperforms existing approaches in both geometric fidelity and accurate satisfaction of geometric constraints.

cs.AI↗

arXiv2026

Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation

The scarcity of large-scale robotic data has motivated the repurposing of foundation models from other modalities for policy learning. In this work, we introduce PhysGen (Learning Physics from Pretrained Video Generation Models), a scalable continuous and sequential world interaction framework that leverages autoregressive video generation to solve robotic manipulation tasks. By treating the pretrained video model as a proxy for a physics simulator, PhysGen models the dynamic interplay between the external environment and robot actions. We introduce a multimodal continuous representation that unifies video and action into shared physical tokens, bridging the gap between discrete video generation and continuous robotic control. This approach enables the seamless transfer of implicit physical knowledge-such as object permanence and dynamics-from video pretraining to downstream manipulation.To ensure efficient convergence, we incorporate causal masking, inverse kinematics, Lookahead Multi-Token Prediction (L-MTP), and key-value (KV) caching. Experimental results on the Libero and ManiSkill benchmarks demonstrate that PhysGen consistently outperforms robust baselines, surpassing OpenVLA and WorldVLA by margins of 13.8% and 8.8%, respectively. Notably, in real-world scenarios, PhysGen matches the performance of large-scale action-pretrained models like $\pi_0$ without requiring prior action-specific pretraining, demonstrating superior capability in physically complex tasks such as grasping transparent objects. These findings validate the potential of extracting physical intuition from pretrained video generators to facilitate generalizable robotic manipulation.

cs.RO↗

arXiv2026

RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation

VLA models have achieved remarkable progress in embodied intelligence; however, their evaluation remains largely confined to simulations or highly constrained real-world settings. This mismatch creates a substantial reality gap, where strong benchmark performance often masks poor generalization in diverse physical environments. We identify three systemic shortcomings in current benchmarking practices that hinder fair and reliable model comparison. (1) Existing benchmarks fail to model real-world dynamics, overlooking critical factors such as dynamic object configurations, robot initial states, lighting changes, and sensor noise. (2) Current protocols neglect spatial--physical intelligence, reducing evaluation to rote manipulation tasks that do not probe geometric reasoning. (3) The field lacks scalable fully autonomous evaluation, instead relying on simplistic 2D metrics that miss 3D spatial structure or on human-in-the-loop systems that are costly, biased, and unscalable. To address these limitations, we introduce RADAR (Real-world Autonomous Dynamics And Reasoning), a benchmark designed to systematically evaluate VLA generalization under realistic conditions. RADAR integrates three core components: (1) a principled suite of physical dynamics; (2) dedicated tasks that explicitly test spatial reasoning and physical understanding; and (3) a fully autonomous evaluation pipeline based on 3D metrics, eliminating the need for human supervision. We apply RADAR to audit multiple state-of-the-art VLA models and uncover severe fragility beneath their apparent competence. Performance drops precipitously under modest physical dynamics, with the expectation of 3D IoU declining from 0.261 to 0.068 under sensor noise. Moreover, models exhibit limited spatial reasoning capability. These findings position RADAR as a necessary bench toward reliable and generalizable real-world evaluation of VLA models.

cs.RO↗

arXiv2026

Neural Clothing Tryer: Customized Virtual Try-On via Semantic Enhancement and Controlling Diffusion Model

This work aims to address a novel Customized Virtual Try-ON (Cu-VTON) task, enabling the superimposition of a specified garment onto a model that can be customized in terms of appearance, posture, and additional attributes. Compared with traditional VTON task, it enables users to tailor digital avatars to their individual preferences, thereby enhancing the virtual fitting experience with greater flexibility and engagement. To address this task, we introduce a Neural Clothing Tryer (NCT) framework, which exploits the advanced diffusion models equipped with semantic enhancement and controlling modules to better preserve semantic characterization and textural details of the garment and meanwhile facilitating the flexible editing of the model's postures and appearances. Specifically, NCT introduces a semantic-enhanced module to take semantic descriptions of garments and utilizes a visual-language encoder to learn aligned features across modalities. The aligned features are served as condition input to the diffusion model to enhance the preservation of the garment's semantics. Then, a semantic controlling module is designed to take the garment image, tailored posture image, and semantic description as input to maintain garment details while simultaneously editing model postures, expressions, and various attributes. Extensive experiments on the open available benchmark demonstrate the superior performance of the proposed NCT framework.

cs.CV↗

arXiv2026

Exploring Talking Head Models With Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation

Speech-Preserving Facial Expression Manipulation (SPFEM) is an innovative technique aimed at altering facial expressions in images and videos while retaining the original mouth movements. Despite advancements, SPFEM still struggles with accurate lip synchronization due to the complex interplay between facial expressions and mouth shapes. Capitalizing on the advanced capabilities of audio-driven talking head generation (AD-THG) models in synthesizing precise lip movements, our research introduces a novel integration of these models with SPFEM. We present a new framework, Talking Head Facial Expression Manipulation (THFEM), which utilizes AD-THG models to generate frames with accurately synchronized lip movements from audio inputs and SPFEM-altered images. However, increasing the number of frames generated by AD-THG models tends to compromise the realism and expression fidelity of the images. To counter this, we develop an adjacent frame learning strategy that finetunes AD-THG models to predict sequences of consecutive frames. This strategy enables the models to incorporate information from neighboring frames, significantly improving image quality during testing. Our extensive experimental evaluations demonstrate that this framework effectively preserves mouth shapes during expression manipulations, highlighting the substantial benefits of integrating AD-THG with SPFEM.

cs.CV↗

arXiv2025

E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We argue that these limitations are closely tied to the structural properties of actions in VLA settings, including the inherent multi-peaked nature of action distributions, the token-based symbolic reasoning of pretrained VLM/VLA backbones, and the effective finite resolution imposed by real-world robotic control. Motivated by these properties, we introduce E0, a tweedie discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. By operating in a discrete action space with a principled diffusion process, E0 naturally aligns with token-based reasoning, supports fine-grained yet executable action control, and avoids the distributional mismatch of masking-based discrete diffusion. We further introduce a spherical viewpoint perturbation augmentation to enhance robustness to camera shifts without additional data. Experiments on LIBERO, VLABench, ManiSkill, and a real-world Franka arm demonstrate that E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.

cs.RO↗

arXiv2025

In-Situ Tweedie Discrete Diffusion Models

While diffusion models excel at generating continuous data such as images, adapting them to discrete tasks has relied on indirect approaches that either operate in continuous embedding spaces or use token masking mechanisms, both of which deviate from modeling the true discrete data distribution that can be theoretically guaranteed by Tweedie's formula. We propose in-situ Tweedie Discrete Diffusion (TDD), a framework that performs diffusion guaranteed by Tweedie's formula directly within the discrete one-hot space, hence "in-situ." Unlike prior methods that diffuse continuous embeddings or mask tokens, TDD directly corrupts one-hot vectors with Gaussian noise and performs iterative denoising through a timestep-conditioned cross-entropy objective rather than mean-squared-error reconstruction. At each denoising step, the model predicts class probabilities, applies argmax to obtain discrete predictions, converts them to one-hot vectors, and feeds them into the next iteration with progressively reduced noise. This process naturally unifies discriminative classification and generative modeling under a single framework. Experiments demonstrate that TDD achieves strong performance on both image classification and text generation tasks, with extensive ablation studies confirming the effectiveness of each design component. Our work establishes a principled approach to discrete diffusion that preserves the core characteristics of diffusion models while operating natively in discrete space.

cs.CV↗

arXiv2025

Neural Scene Designer: Self-Styled Semantic Image Manipulation

Maintaining stylistic consistency is crucial for the cohesion and aesthetic appeal of images, a fundamental requirement in effective image editing and inpainting. However, existing methods primarily focus on the semantic control of generated content, often neglecting the critical task of preserving this consistency. In this work, we introduce the Neural Scene Designer (NSD), a novel framework that enables photo-realistic manipulation of user-specified scene regions while ensuring both semantic alignment with user intent and stylistic consistency with the surrounding environment. NSD leverages an advanced diffusion model, incorporating two parallel cross-attention mechanisms that separately process text and style information to achieve the dual objectives of semantic control and style consistency. To capture fine-grained style representations, we propose the Progressive Self-style Representational Learning (PSRL) module. This module is predicated on the intuitive premise that different regions within a single image share a consistent style, whereas regions from different images exhibit distinct styles. The PSRL module employs a style contrastive loss that encourages high similarity between representations from the same image while enforcing dissimilarity between those from different images. Furthermore, to address the lack of standardized evaluation protocols for this task, we establish a comprehensive benchmark. This benchmark includes competing algorithms, dedicated style-related metrics, and diverse datasets and settings to facilitate fair comparisons. Extensive experiments conducted on our benchmark demonstrate the effectiveness of the proposed framework.

cs.CV↗

arXiv2025

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like complexity and sub-optimal performance due to the lack of end-to-end training. In this paper, we propose Video-MTR, a reinforced multi-turn reasoning framework designed to enable iterative key video segment selection and question comprehension. Unlike traditional video reasoning pipeline, which generate predictions in a single turn, Video-MTR performs reasoning in multiple turns, selecting video segments progressively based on the evolving understanding of previously processed segments and the current question. This iterative process allows for a more refined and contextually aware analysis of the video. To ensure intermediate reasoning process, we introduce a novel gated bi-level reward system, combining trajectory-level rewards based on answer correctness and turn-level rewards emphasizing frame-query relevance. This system optimizes both video segment selection and question comprehension, eliminating the need for external VLMs and allowing end-to-end training. Extensive experiments on benchmarks like VideoMME, MLVU, and EgoSchema demonstrate that Video-MTR outperforms existing methods in both accuracy and efficiency, advancing the state-of-the-art in long video understanding.

cs.CV↗

arXiv2025

Physical Autoregressive Model for Robotic Manipulation without Action Pretraining

The scarcity of manipulation data has motivated the use of pretrained large models from other modalities in robotics. In this work, we build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR), where physical tokens combine frames and actions to represent the joint evolution of the robot and its environment. PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining, enabling accurate video prediction and consistent action trajectories. It also adopts a DiT-based de-tokenizer to model frames and actions as continuous tokens, mitigating quantization errors and facilitating mutual enhancement. Furthermore, we incorporate a causal mask with inverse kinematics, parallel training, and the KV-cache mechanism to further improve performance and efficiency. Experiments on the ManiSkill benchmark show that PAR achieves a 100\% success rate on the PushCube task, matches the performance of action-pretrained baselines on other tasks, and accurately predicts future videos with tightly aligned action trajectories. These findings underscore a promising direction for robotic manipulation by transferring world knowledge from autoregressive video pretraining. The project page is here: https://hcplab-sysu.github.io/PhysicalAutoregressiveModel/

cs.CV↗

arXiv2025

Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels

Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels using pre-set thresholds. This approach often overlooks the varying score distributions across categories, resulting in inaccurate and incomplete pseudo-labels, thereby affecting performance. In our study, we introduce the Semantic-Aware Threshold Learning (SATL) algorithm. This innovative approach calculates the score distribution for both positive and negative samples within each category and determines category-specific thresholds based on these distributions. These distributions and thresholds are dynamically updated throughout the learning process. Additionally, we implement a differential ranking loss to establish a significant gap between the score distributions of positive and negative samples, enhancing the discrimination of the thresholds. Comprehensive experiments and analysis on large-scale multi-label datasets, such as Microsoft COCO and VG-200, demonstrate that our method significantly improves performance in scenarios with limited labels.

cs.CV↗

arXiv2025

Geometry-Editable and Appearance-Preserving Object Compositon

General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simultaneously preserving its fine-grained appearance details. Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation. However, these highly compact embeddings encode only high-level semantic cues and inevitably discard fine-grained appearance details. We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion (DGAD) model that first leverages semantic embeddings to implicitly capture the desired geometric transformations and then employs a cross-attention retrieval mechanism to align fine-grained appearance features with the geometry-edited representation, facilitating both precise geometry editing and faithful appearance preservation in object composition. Specifically, DGAD builds on CLIP/DINO-derived and reference networks to extract semantic embeddings and appearance-preserving representations, which are then seamlessly integrated into the encoding and decoding pipelines in a disentangled manner. We first integrate the semantic embeddings into pre-trained diffusion models that exhibit strong spatial reasoning capabilities to implicitly capture object geometry, thereby facilitating flexible object manipulation and ensuring effective editability. Then, we design a dense cross-attention mechanism that leverages the implicitly learned object geometry to retrieve and spatially align appearance features with their corresponding regions, ensuring faithful appearance consistency. Extensive experiments on public benchmarks demonstrate the effectiveness of the proposed DGAD framework.

cs.CV↗

arXiv2025

ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detection

Continual Anomaly Detection (CAD) enables anomaly detection models in learning new classes while preserving knowledge of historical classes. CAD faces two key challenges: catastrophic forgetting and segmentation of small anomalous regions. Existing CAD methods store image distributions or patch features to mitigate catastrophic forgetting, but they fail to preserve pixel-level detailed features for accurate segmentation. To overcome this limitation, we propose ReplayCAD, a novel diffusion-driven generative replay framework that replay high-quality historical data, thus effectively preserving pixel-level detailed features. Specifically, we compress historical data by searching for a class semantic embedding in the conditional space of the pre-trained diffusion model, which can guide the model to replay data with fine-grained pixel details, thus improving the segmentation performance. However, relying solely on semantic features results in limited spatial diversity. Hence, we further use spatial features to guide data compression, achieving precise control of sample space, thereby generating more diverse data. Our method achieves state-of-the-art performance in both classification and segmentation, with notable improvements in segmentation: 11.5% on VisA and 8.1% on MVTec. Our source code is available at https://github.com/HULEI7/ReplayCAD.

cs.CV↗