Haoran Cheng

Junkai Xu, Liang Peng, Haoran Cheng et al.

In the field of monocular 3D detection, it is common practice to utilize scene geometric clues to enhance the detector's performance. However, many existing works adopt these clues explicitly such as estimating a depth map and back-projecting it into 3D space. This explicit methodology induces sparsity in 3D representations due to the increased dimensionality from 2D to 3D, and leads to substantial information loss, especially for distant and occluded objects. To alleviate this issue, we propose MonoNeRD, a novel detection framework that can infer dense 3D geometry and occupancy. Specifically, we model scenes with Signed Distance Functions (SDF), facilitating the production of dense 3D representations. We treat these representations as Neural Radiance Fields (NeRF) and then employ volume rendering to recover RGB images and depth maps. To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception. Extensive experiments conducted on the KITTI-3D benchmark and Waymo Open Dataset demonstrate the effectiveness of MonoNeRD. Codes are available at https://github.com/cskkxjk/MonoNeRD.

Liang Peng, Haoran Cheng, Zheng Yang et al.

Recent one-shot video tuning methods, which fine-tune the network on a specific video based on pre-trained text-to-image models (e.g., Stable Diffusion), are popular in the community because of the flexibility. However, these methods often produce videos marred by incoherence and inconsistency. To address these limitations, this paper introduces a simple yet effective noise constraint across video frames. This constraint aims to regulate noise predictions across their temporal neighbors, resulting in smooth latents. It can be simply included as a loss term during the training phase. By applying the loss to existing one-shot video tuning methods, we significantly improve the overall consistency and smoothness of the generated videos. Furthermore, we argue that current video evaluation metrics inadequately capture smoothness. To address this, we introduce a novel metric that considers detailed features and their temporal dynamics. Experimental results validate the effectiveness of our approach in producing smoother videos on various one-shot video tuning baselines. The source codes and video demos are available at \href{https://github.com/SPengLiang/SmoothVideo}{https://github.com/SPengLiang/SmoothVideo}.

Haoran Cheng, Dixin Luo, Hongteng Xu

Graph matching is one of the most significant graph analytic tasks, which aims to find the node correspondence across different graphs. Most existing graph matching approaches mainly rely on topological information, whose performances are often sub-optimal and sensitive to data noise because of not fully leveraging the multi-modal information hidden in graphs, such as node attributes, subgraph structures, etc. In this study, we propose a novel and robust graph matching method based on an unbalanced hierarchical optimal transport (UHOT) framework, which, to our knowledge, makes the first attempt to exploit cross-modal alignment in graph matching. In principle, applying multi-layer message passing, we represent each graph as layer-wise node embeddings corresponding to different modalities. Given two graphs, we align their node embeddings within the same modality and across different modalities, respectively. Then, we infer the node correspondence by the weighted average of all the alignment results. This method is implemented as computing the UHOT distance between the two graphs -- each alignment is achieved by a node-level optimal transport plan between two sets of node embeddings, and the weights of all alignment results correspond to an unbalanced modality-level optimal transport plan. Experiments on various graph matching tasks demonstrate the superiority and robustness of our method compared to state-of-the-art approaches. Our implementation is available at https://github.com/Dixin-Lab/UHOT-GM.

Junkai Xu, Liang Peng, Haoran Cheng et al.

Multi-camera perception tasks have gained significant attention in the field of autonomous driving. However, existing frameworks based on Lift-Splat-Shoot (LSS) in the multi-camera setting cannot produce suitable dense 3D features due to the projection nature and uncontrollable densification process. To resolve this problem, we propose to regulate intermediate dense 3D features with the help of volume rendering. Specifically, we employ volume rendering to process the dense 3D features to obtain corresponding 2D features (e.g., depth maps, semantic maps), which are supervised by associated labels in the training. This manner regulates the generation of dense 3D features on the feature level, providing appropriate dense and unified features for multiple perception tasks. Therefore, our approach is termed Vampire, stands for "Volume rendering As Multi-camera Perception Intermediate feature REgulator". Experimental results on the Occ3D and nuScenes datasets demonstrate that Vampire facilitates fine-grained and appropriate extraction of dense 3D features, and is competitive with existing SOTA methods across diverse downstream perception tasks like 3D occupancy prediction, LiDAR segmentation and 3D objection detection, while utilizing moderate GPU resources. We provide a video demonstration in the supplementary materials and Codes are available at github.com/cskkxjk/Vampire.

Yunhao Yao, Zhiqiang Wang, Ruiqi Li et al.

As the Internet of Things (IoT) becomes deeply embedded in daily life, users are increasingly concerned about privacy leakage, especially from video data. Since frame-by-frame protection in large-scale video analytics (e.g., smart communities) introduces significant latency, a more efficient solution is to selectively protect frames containing privacy objects (e.g., faces). Existing object detectors require fully decoded videos or per-frame processing in compressed videos, leading to decoding overhead or reduced accuracy. Therefore, we propose ComPrivDet, an efficient method for detecting privacy objects in compressed video by reusing I-frame inference results. By identifying the presence of new objects through compressed-domain cues, ComPrivDet either skips P- and B-frame detections or efficiently refines them with a lightweight detector. ComPrivDet maintains 99.75% accuracy in private face detection and 96.83% in private license plate detection while skipping over 80% of inferences. It averages 9.84% higher accuracy with 75.95% lower latency than existing compressed-domain detection methods.

Jiaye Tan, Haonan Luo, Linfeng Song et al.

Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We propose Attribute-Specialized Key-Value Head Sharing (AS-KVHS), adapted to music's structured symbolic representation, achieving about 30% inference speedup with only a negligible (about 0.4%) quality drop in objective evaluations and slight improvements in subjective listening tests. Our main contributions are (1) the first systematic study of BPE's generalizability in multi-track symbolic music, and (2) the introduction of AS-KVHS for low-latency symbolic music generation. Beyond these, we also release SAGE-Music, an open-source benchmark that matches or surpasses state-of-the-art models in generation quality.

Tao Yang, Ruibin Li, Yangming Shi et al.

Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a model for a specific task, especially, text-to-video (T2V) generation, while many other works focus on finetuning the pretrained T2V model for image-to-video (I2V), video-to-video (V2V), image and video manipulation tasks, etc. However, training a strong T2V foundation model requires a large amount of high-quality annotations, which is very costly. In addition, many existing models can perform only one or several tasks. In this work, we introduce a unified framework, namely many-for-many, which leverages the available training data from many different visual generation and manipulation tasks to train a single model for those different tasks. Specifically, we design a lightweight adapter to unify the different conditions in different tasks, then employ a joint image-video learning strategy to progressively train the model from scratch. Our joint learning leads to a unified visual generation and manipulation model with improved video generation performance. In addition, we introduce depth maps as a condition to help our model better perceive the 3D space in visual generation. Two versions of our model are trained with different model sizes (8B and 2B), each of which can perform more than 10 different tasks. In particular, our 8B model demonstrates highly competitive performance in video generation tasks compared to open-source and even commercial engines. Our models and source codes are available at https://github.com/leeruibin/MfM.git.

Liang Peng, Boxi Wu, Haoran Cheng et al.

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level, neglecting the need for global optimization at the image level, which is crucial for achieving high perceptual quality and structural coherence. In this paper, we introduce Self-sUpervised Direct preference Optimization (SUDO), a novel paradigm that optimizes both fine-grained details at the pixel level and global image quality. By integrating direct preference optimization into the model, SUDO generates preference image pairs in a self-supervised manner, enabling the model to prioritize global-level learning while complementing the pixel-level MSE loss. As an effective alternative to supervised fine-tuning, SUDO can be seamlessly applied to any text-to-image diffusion model. Importantly, it eliminates the need for costly data collection and annotation efforts typically associated with traditional direct preference optimization methods. Through extensive experiments on widely-used models, including Stable Diffusion 1.5 and XL, we demonstrate that SUDO significantly enhances both global and local image quality. The codes are provided at \href{https://github.com/SPengLiang/SUDO}{this link}.

Liang Peng, Junkai Xu, Haoran Cheng et al.

Monocular 3D detection is a challenging task due to the lack of accurate 3D information. Existing approaches typically rely on geometry constraints and dense depth estimates to facilitate the learning, but often fail to fully exploit the benefits of three-dimensional feature extraction in frustum and 3D space. In this paper, we propose \textbf{OccupancyM3D}, a method of learning occupancy for monocular 3D detection. It directly learns occupancy in frustum and 3D space, leading to more discriminative and informative 3D features and representations. Specifically, by using synchronized raw sparse LiDAR point clouds, we define the space status and generate voxel-based occupancy labels. We formulate occupancy prediction as a simple classification problem and design associated occupancy losses. Resulting occupancy estimates are employed to enhance original frustum/3D features. As a result, experiments on KITTI and Waymo open datasets demonstrate that the proposed method achieves a new state of the art and surpasses other methods by a significant margin. Codes and pre-trained models will be available at \url{https://github.com/SPengLiang/OccupancyM3D}.

Guanwen Feng, Haoran Cheng, Yunan Li et al.

Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional states, thereby improving the emotional quality and personalization of generated content. Generating fine-grained facial animations that accurately portray emotional expressions using only a portrait and an audio recording presents a challenge. In order to address this challenge, we propose a visual attribute-guided audio decoupler. This enables the obtention of content vectors solely related to the audio content, enhancing the stability of subsequent lip movement coefficient predictions. To achieve more precise emotional expression, we introduce a fine-grained emotion coefficient prediction module. Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix. Through these, effective control over emotional expression in the generated videos and finer classification of emotion intensity are accomplished. Subsequently, a series of 3DMM coefficient generation networks are designed to predict 3D coefficients, followed by the utilization of a rendering network to generate the final video. Our experimental results demonstrate that our proposed method, EmoSpeaker, outperforms existing emotional talking face generation methods in terms of expression variation and lip synchronization. Project page: https://peterfanfan.github.io/EmoSpeaker/

Zhiqiang Wang, Yichao Gao, Yanting Wang et al.

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due to untrusted external tools. While prior work has focused on attacks injected through external tool outputs, we investigate a more fundamental vulnerability: Tool Poisoning, where malicious instructions are embedded within a tool's metadata without execution. To date, this threat has been primarily demonstrated through isolated cases, lacking a systematic, large-scale evaluation. We introduce MCPTox, the first benchmark to systematically evaluate agent robustness against Tool Poisoning in realistic MCP settings. MCPTox is constructed upon 45 live, real-world MCP servers and 353 authentic tools. To achieve this, we design three distinct attack templates to generate a comprehensive suite of 1312 malicious test cases by few-shot learning, covering 10 categories of potential risks. Our evaluation on 20 prominent LLM agents setting reveals a widespread vulnerability to Tool Poisoning, with o1-mini, achieving an attack success rate of 72.8\%. We find that more capable models are often more susceptible, as the attack exploits their superior instruction-following abilities. Finally, the failure case analysis reveals that agents rarely refuse these attacks, with the highest refused rate (Claude-3.7-Sonnet) less than 3\%, demonstrating that existing safety alignment is ineffective against malicious actions that use legitimate tools for unauthorized operation. Our findings create a crucial empirical baseline for understanding and mitigating this widespread threat, and we release MCPTox for the development of verifiably safer AI agents. Our dataset is available at an anonymized repository: \textit{https://anonymous.4open.science/r/AAAI26-7C02}.

Haoran Cheng, Qide Dong, Liang Peng et al.

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical challenges: (1) Data inefficiency. Generating thousands of videos per DPO iteration incurs prohibitive costs; (2) Evaluation uncertainty. Human annotations suffer from subjective bias, and automated discriminators fail to detect subtle temporal artifacts like flickering or motion incoherence. To address these, we propose a discriminator-free video DPO framework that: (1) Uses original real videos as win cases and their edited versions (e.g., reversed, shuffled, or noise-corrupted clips) as lose cases; (2) Trains video diffusion models to distinguish and avoid artifacts introduced by editing. This approach eliminates the need for costly synthetic video comparisons, provides unambiguous quality signals, and enables unlimited training data expansion through simple editing operations. We theoretically prove the framework's effectiveness even when real videos and model-generated videos follow different distributions. Experiments on CogVideoX demonstrate the efficiency of the proposed method.

Hengjia Li, Yang Liu, Yibo Zhao et al.

Recently, 3D generative domain adaptation has emerged to adapt the pre-trained generator to other domains without collecting massive datasets and camera pose distributions. Typically, they leverage large-scale pre-trained text-to-image diffusion models to synthesize images for the target domain and then fine-tune the 3D model. However, they suffer from the tedious pipeline of data generation, which inevitably introduces pose bias between the source domain and synthetic dataset. Furthermore, they are not generalized to support one-shot image-guided domain adaptation, which is more challenging due to the more severe pose bias and additional identity bias introduced by the single image reference. To address these issues, we propose GCA-3D, a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation. Different from previous pipeline methods, we introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner. This multi-modal loss enables GCA-3D in both text prompt and one-shot image prompt adaptation. Besides, it leverages per-instance depth maps from the volume rendering module to mitigate the overfitting problem and retain the diversity of results. To enhance the pose and identity consistency, we further propose a hierarchical spatial consistency loss to align the spatial structure between the generated images in the source and target domain. Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.

Hongze Mi, Jinyuan Li, Xuying Zhang et al.

Multimodal entity linking (MEL), a task aimed at linking mentions within multimodal contexts to their corresponding entities in a knowledge base (KB), has attracted much attention due to its wide applications in recent years. However, existing MEL methods often rely on mention words as retrieval cues, which limits their ability to effectively utilize information from both images and text. This reliance causes MEL to struggle with accurately retrieving entities in certain scenarios, especially when the focus is on image objects or mention words are missing from the text. To solve these issues, we introduce a Visual Prompts guided Multimodal Entity Linking (VP-MEL) task. Given a text-image pair, VP-MEL aims to link a marked region (i.e., visual prompt) in an image to its corresponding entities in the knowledge base. To facilitate this task, we present a new dataset, VPWiki, specifically designed for VP-MEL. Furthermore, we propose a framework named IIER, which enhances visual feature extraction using visual prompts and leverages the pretrained Detective-VLM model to capture latent information. Experimental results on the VPWiki dataset demonstrate that IIER outperforms baseline methods across multiple benchmarks for the VP-MEL task.

Yunhao Yao, Zhiqiang Wang, Haoran Cheng et al.

The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools. Although this decoupled architecture fosters modularity, it simultaneously shatters the traditional trust boundary. We uncover a novel privacy vector inherent to this paradigm: the Intent Inversion Attack. We show that semi-honest third-party MCP servers can accurately reconstruct users' underlying intents by leveraging only authorized metadata (e.g., function signatures, arguments, and receipts), effectively bypassing the need for raw query access. To quantify this threat, we introduce IntentMiner. Unlike statistical approaches, IntentMiner employs a hierarchical semantic parsing strategy that performs step-level intent reconstruction by analyzing tool functions, parameter entities, and result feedback in an orthogonal manner. Experiments on the ToolACE benchmark reveal that IntentMiner achieves a semantic alignment of over 85% with original queries, substantially surpassing LLM baselines. This work exposes a critical endogenous vulnerability: without semantic obfuscation, executing functions requires the transparency of intent, thereby challenging the privacy foundations of next-generation AI agents.

Yang Bai, Haoran Cheng, Yang Zhou et al.

Despite the promise of foundation models in medical AI, current systems remain limited - they are modality-specific and lack transparent reasoning processes, hindering clinical adoption. To address this gap, we present EVLF-FM, a multimodal vision-language foundation model (VLM) designed to unify broad diagnostic capability with fine-grain explainability. The development and testing of EVLF-FM encompassed over 1.3 million total samples from 23 global datasets across eleven imaging modalities related to six clinical specialties: dermatology, hepatology, ophthalmology, pathology, pulmonology, and radiology. External validation employed 8,884 independent test samples from 10 additional datasets across five imaging modalities. Technically, EVLF-FM is developed to assist with multiple disease diagnosis and visual question answering with pixel-level visual grounding and reasoning capabilities. In internal validation for disease diagnostics, EVLF-FM achieved the highest average accuracy (0.858) and F1-score (0.797), outperforming leading generalist and specialist models. In medical visual grounding, EVLF-FM also achieved stellar performance across nine modalities with average mIOU of 0.743 and Acc@0.5 of 0.837. External validations further confirmed strong zero-shot and few-shot performance, with competitive F1-scores despite a smaller model size. Through a hybrid training strategy combining supervised and visual reinforcement fine-tuning, EVLF-FM not only achieves state-of-the-art accuracy but also exhibits step-by-step reasoning, aligning outputs with visual evidence. EVLF-FM is an early multi-disease VLM model with explainability and reasoning capabilities that could advance adoption of and trust in foundation models for real-world clinical deployment.

Haoran Cheng, Liang Peng, Linxuan Xia et al.

Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a reduction in video realism. One possible solution is to collect massive data and train the model on it, but this would be extremely expensive. To alleviate this problem, in this paper, we reformulate the typical T2V generation process as a search-based generation pipeline. Instead of scaling up the model training, we employ existing videos as the motion prior database. Specifically, we divide T2V generation process into two steps: (i) For a given prompt input, we search existing text-video datasets to find videos with text labels that closely match the prompt motions. We propose a tailored search algorithm that emphasizes object motion features. (ii) Retrieved videos are processed and distilled into motion priors to fine-tune a pre-trained base T2V model, followed by generating desired videos using input prompt. By utilizing the priors gleaned from the searched videos, we enhance the realism of the generated videos' motion. All operations can be finished on a single NVIDIA RTX 4090 GPU. We validate our method against state-of-the-art T2V models across diverse prompt inputs. The code will be public.