Guohui Zhang

Chen Yang, Guanxin Lin, Youquan He et al.

Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a single image may admit multiple plausible 3D interpretations. We introduce SSI-Bench, a VQA benchmark for Structure-Centric Spatial Reasoning (SCSR) in constraint-governed spaces. Built from complex real-world 3D structures, it uses structural constraints from geometry, topology, and physical feasibility to make component relations more determinate from visual evidence. The benchmark contains 1,000 ranking questions spanning geometric and topological reasoning, where correct ordering requires resolving all candidate-wise 3D relations, imposing stronger demands on spatial understanding. It is created through a fully human-centered pipeline with over 400 researcher-hours of image curation, component annotation, and question design. Evaluating 31 VLMs reveals a large gap to humans: the best open-source model achieves 22.2% accuracy and the strongest closed-source model reaches 33.6%, while humans score 91.6%. Further results show that chain-of-thought reasoning brings only marginal gains, and error analysis reveals fundamental limitations in current models' spatial understanding within constraint-governed spaces. Project page: https://ssi-bench.github.io.

Haicheng Liao, Yongkang Li, Chengyue Wang et al.

The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art (SOTA) 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. {We rigorously evaluate the performance of our framework on three benchmark datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset--demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA).

Lin Song, Wenbo Li, Guoqing Ma et al.

We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.

Yaning Pan, Zekun Wang, Qianqian Xie et al.

The recent development of Multimodal Large Language Models (MLLMs) has significantly advanced AI's ability to understand visual modalities. However, existing evaluation benchmarks remain limited to single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios. To bridge this gap, we introduce MT-Video-Bench, a holistic video understanding benchmark for evaluating MLLMs in multi-turn dialogues. Specifically, our MT-Video-Bench mainly assesses six core competencies that focus on perceptivity and interactivity, encompassing 987 meticulously curated multi-turn dialogues from diverse domains. These capabilities are rigorously aligned with real-world applications, such as interactive sports analysis and multi-turn video-based intelligent tutoring. With MT-Video-Bench, we extensively evaluate various state-of-the-art open-source and closed-source MLLMs, revealing their significant performance discrepancies and limitations in handling multi-turn video dialogues. The benchmark will be publicly available to foster future research.

Guohui Zhang, XiaoXiao Ma, Jie Huang et al.

Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synchronization. Reinforcement Learning (RL) offers a promising paradigm, but its extension to multi-objective and multi-modal joint audio-video generation remains unexplored. Notably, our in-depth analysis first reveals that the primary obstacles to applying RL in this stem from: (i) multi-objective advantages inconsistency, where the advantages of multimodal outputs are not always consistent within a group; (ii) multi-modal gradients imbalance, where video-branch gradients leak into shallow audio layers responsible for intra-modal generation; (iii) uniform credit assignment, where fine-grained cross-modal alignment regions fail to get efficient exploration. These shortcomings suggest that vanilla RL fine-tuning strategy with a single global advantage often leads to suboptimal results. To address these challenges, we propose OmniNFT, a novel modality-aware online diffusion RL framework with three key innovations: (1) Modality-wise advantage routing, which routes independent per-reward advantages to their respective modality generation branches. (2) Layer-wise gradient surgery, which selectively detaches video-branch gradients on shallow audio layers while retaining those for cross-modal interaction layers. (3) Region-wise loss reweighting, which modulates policy optimization toward critical regions related to audio-video synchronization and fine-grained alignment. Extensive experiments on JavisBench and VBench with the LTX-2 backbone demonstrate that OmniNFT achieves comprehensive improvements in audio and video perceptual quality, cross-modal alignment, and audio-video synchronization.

Yanchen Guan, Haicheng Liao, Zhenning Li et al.

In the rapidly evolving landscape of autonomous driving, the capability to accurately predict future events and assess their implications is paramount for both safety and efficiency, critically aiding the decision-making process. World models have emerged as a transformative approach, enabling autonomous driving systems to synthesize and interpret vast amounts of sensor data, thereby predicting potential future scenarios and compensating for information gaps. This paper provides an initial review of the current state and prospective advancements of world models in autonomous driving, spanning their theoretical underpinnings, practical applications, and the ongoing research efforts aimed at overcoming existing limitations. Highlighting the significant role of world models in advancing autonomous driving technologies, this survey aspires to serve as a foundational reference for the research community, facilitating swift access to and comprehension of this burgeoning field, and inspiring continued innovation and exploration.

Tianfei Ren, Zhipeng Yan, Yiming Zhao et al.

While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to these requirements as semantic commitments and formalize their lifecycle discontinuity as the Conceptual Rift, where commitments may be locally resolved or checked but fail to remain identifiable as the same operational units throughout the generation lifecycle. To address this, we propose SCOPE, a specification-guided skill orchestration framework that maintains semantic commitments in an evolving structured specification and conditionally invokes retrieval, reasoning, and repair skills around unresolved or violated commitments. To evaluate commitment-level intent realization, we introduce Gen-Arena, a human-annotated benchmark with entity- and constraint-level specifications, together with Entity-Gated Intent Pass Rate (EGIP), a strict entity-first pass criterion. SCOPE substantially outperforms all evaluated baselines on Gen-Arena, achieving 0.60 EGIP, and further achieves strong results on WISE-V (0.907) and MindBench (0.61), demonstrating the effectiveness of persistent commitment tracking for complex image generation.

Guohui Zhang, Hu Yu, Xiaoxiao Ma et al.

Reinforcement learning (RL) has demonstrated significant potential for post-training language models and autoregressive visual generative models, but adapting RL to masked generative models remains challenging. The core factor is that policy optimization requires accounting for the probability likelihood of each step due to its multi-step and iterative refinement process. This reliance on entire sampling trajectories introduces high computational cost, whereas natively optimizing random steps often yields suboptimal results. In this paper, we present MaskFocus, a novel RL framework that achieves effective policy optimization for masked generative models by focusing on critical steps. Specifically, we determine the step-level information gain by measuring the similarity between the intermediate images at each sampling step and the final generated image. Crucially, we leverage this to identify the most critical and valuable steps and execute focused policy optimization on them. Furthermore, we design a dynamic routing sampling mechanism based on entropy to encourage the model to explore more valuable masking strategies for samples with low entropy. Extensive experiments on multiple Text-to-Image benchmarks validate the effectiveness of our method.

Haicheng Liao, Bonan Wang, Junxian Yang et al.

Accurate and reliable motion forecasting is essential for the safe deployment of autonomous vehicles (AVs), particularly in rare but safety-critical scenarios known as corner cases. Existing models often underperform in these situations due to an over-representation of common scenes in training data and limited generalization capabilities. To address this limitation, we present WM-MoE, the first world model-based motion forecasting framework that unifies perception, temporal memory, and decision making to address the challenges of high-risk corner-case scenarios. The model constructs a compact scene representation that explains current observations, anticipates future dynamics, and evaluates the outcomes of potential actions. To enhance long-horizon reasoning, we leverage large language models (LLMs) and introduce a lightweight temporal tokenizer that maps agent trajectories and contextual cues into the LLM's feature space without additional training, enriching temporal context and commonsense priors. Furthermore, a mixture-of-experts (MoE) is introduced to decompose complex corner cases into subproblems and allocate capacity across scenario types, and a router assigns scenes to specialized experts that infer agent intent and perform counterfactual rollouts. In addition, we introduce nuScenes-corner, a new benchmark that comprises four real-world corner-case scenarios for rigorous evaluation. Extensive experiments on four benchmark datasets (nuScenes, NGSIM, HighD, and MoCAD) showcase that WM-MoE consistently outperforms state-of-the-art (SOTA) baselines and remains robust under corner-case and data-missing conditions, indicating the promise of world model-based architectures for robust and generalizable motion forecasting in fully AVs.

Xiaoxiao Ma, Haibo Qiu, Guohui Zhang et al.

Reinforcement learning has recently been explored to improve text-to-image generation, yet applying existing GRPO algorithms to autoregressive (AR) image models remains challenging. The instability of the training process easily disrupts the pretrained model capability during long runs, resulting in marginal gains, degraded image quality, and poor generalization. In this work, we revisit GRPO for AR image generation and identify two key issues: contradictory gradients from unnecessary tokens and unstable policy entropy dynamics. To address these, we introduce STAGE, a stable and generalizable framework that leverages two targeted solutions: 1) Advantage/KL reweighting. Similarity-aware reweighting to alleviate conflicting updates; and 2) Entropy reward. An entropy-based reward corresponding to reference model to stabilize learning. With the help of alleviating conflicts between tokens and an entropy reward for stabilizing training, we reduce disruption of the pretrained distribution and mitigate reward hacking, which in turn improves generalization and transfer better to other benchmarks. Experiments across multiple benchmarks show that STAGE consistently improves visual quality, stability, and cross-task generalization compared to baseline GRPO.

Guohui Zhang, Hu Yu, Xiaoxiao Ma et al.

Recent studies have extended Reinforcement Learning with Verifiable Rewards (RLVR) to autoregressive (AR) visual generation and achieved promising progress. However, existing methods typically apply uniform optimization across all image tokens, while the varying contributions of different image tokens for RLVR's training remain unexplored. In fact, the key obstacle lies in how to identify more critical image tokens during AR generation and implement effective token-wise optimization for them. To tackle this challenge, we propose $\textbf{G}$roup $\textbf{C}$ritical-token $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{GCPO}$), which facilitates effective policy optimization on critical tokens. We identify the critical tokens in RLVR-based AR generation from three perspectives, specifically: $\textbf{(1)}$ Causal dependency: early tokens fundamentally determine the later tokens and final image effect due to unidirectional dependency; $\textbf{(2)}$ Entropy-induced spatial structure: tokens with high entropy gradients correspond to image structure and bridges distinct visual regions; $\textbf{(3)}$ RLVR-focused token diversity: tokens with low visual similarity across a group of sampled images contribute to richer token-level diversity. For these identified critical tokens, we further introduce a dynamic token-wise advantage weight to encourage exploration, based on confidence divergence between the policy model and reference model. By leveraging 30\% of the image tokens, GCPO achieves better performance than GRPO with full tokens. Extensive experiments on multiple text-to-image benchmarks for both AR models and unified multimodal models demonstrate the effectiveness of GCPO for AR visual generation.

Guohui Zhang, Jiangtong Tan, Linjiang Huang et al.

Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher. In fact, the key challenge in generating variable-scale images lies in the differing amounts of information across resolutions, which requires information conversion procedures to be varied for generating variable-scaled images. In this paper, we investigate the issues of three critical aspects in DMs for a unified analysis in variable-scaled generation: dilated convolution, attention mechanisms, and initial noise. Specifically, 1) dilated convolution in DMs for the higher-resolution generation loses high-frequency information. 2) Attention for variable-scaled image generation struggles to adjust the information aggregation adaptively. 3) The spatial distribution of information in the initial noise is misaligned with variable-scaled image. To solve the above problems, we propose \textbf{InfoScale}, an information-centric framework for variable-scaled image generation by effectively utilizing information from three aspects correspondingly. For information loss in 1), we introduce Progressive Frequency Compensation module to compensate for high-frequency information lost by dilated convolution in higher-resolution generation. For information aggregation inflexibility in 2), we introduce Adaptive Information Aggregation module to adaptively aggregate information in lower-resolution generation and achieve an effective balance between local and global information in higher-resolution generation. For information distribution misalignment in 3), we design Noise Adaptation module to re-distribute information in initial noise for variable-scaled generation. Our method is plug-and-play for DMs and extensive experiments demonstrate the effectiveness in variable-scaled image generation.

Haicheng Liao, Zhenning Li, Guohui Zhang et al.

Predicting the trajectories of vehicles is crucial for the development of autonomous driving (AD) systems, particularly in complex and dynamic traffic environments. In this study, we introduce HiT (Human-like Trajectory Prediction), a novel model designed to enhance trajectory prediction by incorporating behavior-aware modules and dynamic centrality measures. Unlike traditional methods that primarily rely on static graph structures, HiT leverages a dynamic framework that accounts for both direct and indirect interactions among traffic participants. This allows the model to capture the subtle yet significant influences of surrounding vehicles, enabling more accurate and human-like predictions. To evaluate HiT's performance, we conducted extensive experiments using diverse and challenging real-world datasets, including NGSIM, HighD, RounD, ApolloScape, and MoCAD++. The results demonstrate that HiT consistently outperforms other top models across multiple metrics, particularly excelling in scenarios involving aggressive driving behaviors. This research presents a significant step forward in trajectory prediction, offering a more reliable and interpretable approach for enhancing the safety and efficiency of fully autonomous driving systems.

Zhenning Li, Chengzhong Xu, Guohui Zhang

Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy. Reinforcement learning (RL) is a trending data-driven approach for adaptive traffic signal control in complex urban traffic networks. Although the development of deep neural networks (DNN) further enhances its learning capability, there are still some challenges in applying deep RLs to transportation networks with multiple signalized intersections, including non-stationarity environment, exploration-exploitation dilemma, multi-agent training schemes, continuous action spaces, etc. In order to address these issues, this paper first proposes a multi-agent deep deterministic policy gradient (MADDPG) method by extending the actor-critic policy gradient algorithms. MADDPG has a centralized learning and decentralized execution paradigm in which critics use additional information to streamline the training process, while actors act on their own local observations. The model is evaluated via simulation on the Simulation of Urban MObility (SUMO) platform. Model comparison results show the efficiency of the proposed algorithm in controlling traffic lights.

Zhenning Li, Hao Yu, Guohui Zhang et al.

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Deterministic Policy Gradient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden.

Zhihui Su, Ming Ye, Guohui Zhang et al.

Human pose estimation plays an important role in many computer vision tasks and has been studied for many decades. However, due to complex appearance variations from poses, illuminations, occlusions and low resolutions, it still remains a challenging problem. Taking the advantage of high-level semantic information from deep convolutional neural networks is an effective way to improve the accuracy of human pose estimation. In this paper, we propose a novel Cascade Feature Aggregation (CFA) method, which cascades several hourglass networks for robust human pose estimation. Features from different stages are aggregated to obtain abundant contextual information, leading to robustness to poses, partial occlusions and low resolution. Moreover, results from different stages are fused to further improve the localization accuracy. The extensive experiments on MPII datasets and LIP datasets demonstrate that our proposed CFA outperforms the state-of-the-art and achieves the best performance on the state-of-the-art benchmark MPII.

Guohui Zhang, Gaoyuan Liang, Fang Su et al.

In the problem of domain transfer learning, we learn a model for the predic-tion in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has sufficient labels. Besides the instances of the data, recently the attributes of data shared across domains are also explored and proven to be very helpful to leverage the information of different domains. In this paper, we propose a novel learning framework for domain-transfer learning based on both instances and attributes. We proposed to embed the attributes of dif-ferent domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by dif-ferent domains by matching across domains, and a domain-specific CNN model to represent the information of each domain. The concatenation of the three CNN model outputs is used to predict the class label. An iterative algo-rithm based on gradient descent method is developed to learn the parameters of the model. The experiments over benchmark datasets show the advantage of the proposed model.

Yanyan Geng, Guohui Zhang, Weizhi Li et al.

In the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.