Ming Lu

AAAI Conference 2026 Conference Paper

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning

• Jiajun Cao
• Qizhe Zhang
• Peidong Jia
• Xuhui Zhao
• Bo Lan
• Xiaoan Zhang
• Lizhuo
• Xiaobao Wei

Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.

AAAI Conference 2026 Conference Paper

ManipDreamer3D: Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory

• Ying Li
• Xiaobao Wei
• Xiaowei Chi
• Yuming Li
• Zhongyu Zhao
• Hao Wang
• Ningning Ma
• Ming Lu

Data scarcity continues to be a critical bottleneck in the field of robotic manipulation, limiting the ability to train robust and generalizable models. While diffusion models provide a promising approach to synthesizing realistic robotic manipulation videos, their effectiveness hinges on the availability of precise and reasonable control instructions. Current methods primarily rely on 2D trajectories as instruction prompts, which inherently face issues with 3D spatial ambiguity. In this work, we present a novel framework named ManipDreamer3Dfor generating plausible 3D-aware robotic manipulation videos from the input image and the text instruction. Our method combines 3D trajectory planning with a reconstructed 3D occupancy map created from a third-person perspective, along with a novel trajectory-to-video diffusion model. Specifically, ManipDreamer3D first reconstructs the 3D occupancy representation from the input image and then computes an optimized 3D end-effector trajectory, minimizing path length, avoiding collisions and retiming. Next, we employ a latent editing technique to create video sequences from the initial image latent, text instruction and the optimized 3D trajectory. This process conditions our specially trained trajectory-to-video diffusion model to produce robotic pick-and-place videos. Our method significantly reduces human intervention requirements by autonomously planing plausible 3D trajectories. Experimental results demonstrate its superior visual quality and precision.

AAAI Conference 2026 Conference Paper

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

• Junpeng Ma
• Qizhe Zhang
• Ming Lu
• Zhibin Wang
• Qiang Zhou
• Jun Song
• Shanghang Zhang

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token pruning. However, they do not consider the dynamic characteristics and temporal dependencies of video frames, as they perceive video understanding as a multi-frame task. To address these challenges, we propose MMG-Vid, a novel training-free visual token pruning framework that removes redundancy by Maximizing Marginal Gains at both segment-level and token-level. Specifically, we first divide the video into segments based on frame similarity, and then dynamically allocate the token budget for each segment to maximize the marginal gain of each segment. Subsequently, we propose a temporal-guided DPC algorithm that jointly models inter-frame uniqueness and intra-frame diversity, thereby maximizing the marginal gain of each token. By combining both stages, MMG-Vid can maximize the utilization of the limited token budget, significantly improving efficiency while maintaining strong performance. Extensive experiments demonstrate that MMG-Vid can maintain over 99.5% of the original performance, while effectively reducing 75% visual tokens and accelerating the prefilling stage by 3.9x on LLaVA-OneVision-7B.

AAAI Conference 2026 Conference Paper

Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate–Distortion Awareness

• Wuyang Cong
• Junqi Shi
• Lizhong Wang
• Weijing Shi
• Ming Lu
• Hao Chen
• Zhan Ma

Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Existing rate control schemes typically leverage frame content to capture distortion interactions, overlooking inter-frame rate dependencies arising from shifts in per-frame coding parameters. This often leads to suboptimal bitrate allocation and cascading parameter decisions. To address this, we propose a reinforcement‑learning (RL)‑based rate control framework that formulates the task as a frame‑by‑frame sequential decision process. At each frame, an RL agent observes a spatiotemporal state and selects coding parameters to optimize a long‑term reward that reflects rate‑distortion (R-D) performance and bitrate adherence. Unlike prior methods, our approach jointly determines bitrate allocation and coding configuration in a single step, independent of group‑of‑pictures (GOP) structure. Extensive experiments across diverse NVC architectures show that our method reduces the average relative bitrate error to 1.20 percent and achieves up to 13.45 percent bitrate savings at typical GOP sizes, outperforming existing approaches. In addition, our framework demonstrates improved robustness to content variation and bandwidth fluctuations with lower encoding/decoding overhead, making it highly suitable for practical deployment.

AAAI Conference 2026 Conference Paper

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

• Yilong Chen
• Xiang Bai
• Zhibin Wang
• Chengyu Bai
• Yuhan Dai
• Ming Lu

Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose StreamKV, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency.

NeurIPS Conference 2025 Conference Paper

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

• Qizhe Zhang
• Mengzhen Liu
• Lichen Li
• Ming Lu
• Yuan Zhang
• Junwen Pan
• Qi She
• Shanghang Zhang

In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference cost. Many works aim to address this issue by removing redundant visual tokens. However, current approaches either rely on attention-based pruning, which retains numerous duplicate tokens, or use similarity-based pruning, overlooking the instruction relevance, consequently causing suboptimal performance. In this paper, we go beyond attention or similarity by proposing a novel visual token pruning method named CDPruner, which maximizes the conditional diversity of retained tokens. We first define the conditional similarity between visual tokens conditioned on the instruction, and then reformulate the token pruning problem with determinantal point process (DPP) to maximize the conditional diversity of the selected subset. The proposed CDPruner is training-free and model-agnostic, allowing easy application to various MLLMs. Extensive experiments across diverse MLLMs show that CDPruner establishes new state-of-the-art on various vision-language benchmarks. By maximizing conditional diversity through DPP, the selected subset better represents the input images while closely adhering to user instructions, thereby preserving strong performance even with high reduction ratios. When applied to LLaVA, CDPruner reduces FLOPs by 95\% and CUDA latency by 78\%, while maintaining 94\% of the original accuracy. Our code is available at https: //github. com/Theia-4869/CDPruner.

AAAI Conference 2025 Conference Paper

GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians

• Xiaobao Wei
• Peng Chen
• Ming Lu
• Hui Chen
• Feng Tian

Rendering photorealistic head avatars from arbitrary viewpoints is crucial for various applications like virtual reality. Although previous methods based on Neural Radiance Fields (NeRF) can achieve impressive results, they lack fidelity and efficiency. Recent methods using 3D Gaussian Splatting (3DGS) have improved rendering quality and real-time performance but still require significant storage overhead. In this paper, we introduce a method called GraphAvatar that utilizes Graph Neural Networks (GNN) to generate 3D Gaussians for the head avatar. Specifically, GraphAvatar trains a geometric GNN and an appearance GNN to generate the attributes of the 3D Gaussians from the tracked mesh. Therefore, our method can store the GNN models instead of the 3D Gaussians, significantly reducing the storage overhead to just 10MB. To reduce the impact of face-tracking errors, we also present a novel graph-guided optimization module to refine face-tracking parameters during training. Finally, we introduce a 3D-aware enhancer for post-processing to enhance the rendering quality. We conduct comprehensive experiments to demonstrate the advantages of GraphAvatar, surpassing existing methods in visual fidelity and storage consumption. The ablation study sheds light on the trade-offs between rendering quality and model size.

IJCAI Conference 2025 Conference Paper

K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers

• Haofan Ren
• Zunjie Zhu
• Xiang Chen
• Ming Lu
• Rongfeng Lu
• Chenggang Yan

Neural fields are now the central focus of research in 3D vision and computer graphics. Existing methods mainly focus on various scene representations, such as neural points and 3D Gaussians. However, few works have studied the rendering process to enhance the neural fields. In this work, we propose a plug-in method named K-Buffers that leverages multiple buffers to improve the rendering performance. Our method first renders K buffers from scene representations and constructs K pixel-wise feature maps. Then, We introduce a K-Feature Fusion Network (KFN) to merge the K pixel-wise feature maps. Finally, we adopt a feature decoder to generate the rendering image. We also introduce an acceleration strategy to improve rendering speed and quality. We apply our method to well-known radiance field baselines, including neural point fields and 3D Gaussian Splatting (3DGS). Extensive experiments demonstrate that our method effectively enhances the rendering performance of neural point fields and 3DGS.

NeurIPS Conference 2025 Conference Paper

Neural B-frame Video Compression with Bi-directional Reference Harmonization

• Yuxi Liu
• jin dengchao
• Shuai Huo
• Jiawen Gu
• Chao Zhou
• Huihui Bai
• Ming Lu
• Zhan Ma

Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding may complicate continuous temporal prediction, especially at some hierarchical levels with a large frame span, which could cause the contribution of the two reference frames to be unbalanced. To optimize reference information utilization, we propose a novel NBVC method, termed Bi-directional Reference Harmonization Video Compression (BRHVC), with the proposed Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF). BMC converges multiple optical flows in motion compression, leading to more accurate motion compensation on a larger scale. Then BCF explicitly models the weights of reference contexts under the guidance of motion compensation accuracy. With more efficient motions and contexts, BRHVC can effectively harmonize bi-directional references. Experimental results indicate that our BRHVC outperforms previous state-of-the-art NVC methods, even surpassing the traditional coding, VTM-RA (under random access configuration), on the HEVC datasets. The source code will be released. The source code is released at https: //github. com/kwai/NVC.

AAAI Conference 2025 Conference Paper

Towards Loss-Resilient Image Coding for Unstable Satellite Networks

• Hongwei Sha
• Muchen Dong
• Quanyou Luo
• Ming Lu
• Hao Chen
• Zhan Ma

Geostationary Earth Orbit (GEO) satellite communication demonstrates significant advantages in emergency short burst data services. However, unstable satellite networks, particularly those with frequent packet loss, present a severe challenge to accurate image transmission. To address it, we propose a loss-resilient image coding approach that leverages end-to-end optimization in learned image compression (LIC). Our method builds on the channel-wise progressive coding framework, incorporating Spatial-Channel Rearrangement (SCR) on the encoder side and Mask Conditional Aggregation (MCA) on the decoder side to improve reconstruction quality with unpredictable errors. By integrating the Gilbert-Elliot model into the training process, we enhance the model's ability to generalize in real-world network conditions. Extensive evaluations show that our approach outperforms traditional and deep learning-based methods in terms of compression performance and stability under diverse packet loss, offering robust and efficient progressive transmission even in challenging environments.

NeurIPS Conference 2025 Conference Paper

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

• Ruichuan An
• Sihan Yang
• Renrui Zhang
• zijun shen
• Ming Lu
• Gaole Dai
• Hao Liang
• Ziyu Guo

Personalized models have demonstrated remarkable success in understanding and generating concepts provided by users. However, existing methods use separate concept tokens for understanding and generation, treating these tasks in isolation. This may result in limitations for generating images with complex prompts. For example, given the concept $\langle bo\rangle$, generating "$\langle bo\rangle$ wearing its hat" without additional textual descriptions of its hat. We call this kind of generation \textit{\textbf{personalized attribute-reasoning generation}}. To address the limitation, we present UniCTokens, a novel framework that effectively integrates personalized information into a unified vision language model (VLM) for understanding and generation. UniCTokens trains a set of unified concept tokens to leverage complementary semantics, boosting two personalized tasks. Moreover, we propose a progressive training strategy with three stages: understanding warm-up, bootstrapping generation from understanding, and deepening understanding from generation to enhance mutual benefits between both tasks. To quantitatively evaluate the unified VLM personalization, we present UnifyBench, the first benchmark for assessing concept understanding, concept generation, and attribute-reasoning generation. Experimental results on UnifyBench indicate that UniCTokens shows competitive performance compared to leading methods in concept understanding, concept generation, and achieving state-of-the-art results in personalized attribute-reasoning generation. Our research demonstrates that enhanced understanding improves generation, and the generation process can yield valuable insights into understanding. Our code and dataset will be released at: \href{https: //github. com/arctanxarc/UniCTokens}{https: //github. com/arctanxarc/UniCTokens}.

NeurIPS Conference 2024 Conference Paper

All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation

• Xu Zhang
• Peiyao Guo
• Ming Lu
• Zhan Ma

Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and bitrate usage, or face challenges in multi-objective optimization under a unified representation, failing to achieve both performance and efficiency. To this end, we propose Multi-Path Aggregation (MPA) integrated into existing coding models for joint human-machine vision, unifying the feature representation with an all-in-one architecture. MPA employs a predictor to allocate latent features among task-specific paths based on feature importance varied across tasks, maximizing the utility of shared features while preserving task-specific features for subsequent refinement. Leveraging feature correlations, we develop a two-stage optimization strategy to alleviate multi-task performance degradation. Upon the reuse of shared features, as low as 1. 89\% parameters are further augmented and fine-tuned for a specific task, which completely avoids extensive optimization of the entire model. Experimental results show that MPA achieves performance comparable to state-of-the-art methods in both task-specific and multi-objective optimization across human viewing and machine analysis tasks. Moreover, our all-in-one design supports seamless transitions between human- and machine-oriented reconstruction, enabling task-controllable interpretation without altering the unified model. Code is available at https: //github. com/NJUVISION/MPA.

AAAI Conference 2024 Conference Paper

Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding

• Yichi Zhang
• Zhihao Duan
• Ming Lu
• Dandan Ding
• Fengqing Zhu
• Zhan Ma

While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering operations and local attention for correlation characterization and compact representation of an image. As seen, CLIC expands the receptive field into the entire image for intra-cluster feature aggregation. Afterward, features are reordered to their original spatial positions to pass through the local attention units for inter-cluster embedding. Additionally, we introduce the Guided Post-Quantization Filtering (GuidedPQF) into CLIC, effectively mitigating the propagation and accumulation of quantization errors at the initial decoding stage. Extensive experiments demonstrate the superior performance of CLIC over state-of-the-art works: when optimized using MSE, it outperforms VVC by about 10% BD-Rate in three widely-used benchmark datasets; when optimized using MS-SSIM, it saves more than 50% BD-Rate over VVC. Our CLIC offers a new way to generate compact representations for image compression, which also provides a novel direction along the line of LIC development.

AAAI Conference 2024 Conference Paper

Deep Hierarchical Video Compression

• Ming Lu
• Zhihao Duan
• Fengqing Zhu
• Zhan Ma

Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale Variational AutoEncoder (VAE) must devise complex networks for conditional probability estimation in latent space, neglecting multiscale characteristics of video frames. Instead, this work proposes hierarchical probabilistic predictive coding, for which hierarchal VAEs are carefully designed to characterize multiscale latent features as a family of flexible priors and posteriors to predict the probabilities of future frames. Under such a hierarchical structure, lightweight networks are sufficient for prediction. The proposed method outperforms representative learned video compression models on common testing videos and demonstrates computational friendliness with much less memory footprint and faster encoding/decoding. Extensive experiments on adaptation to temporal patterns also indicate the better generalization of our hierarchical predictive mechanism. Furthermore, our solution is the first to enable progressive decoding that is favored in networked video applications with packet loss.

YNICL Journal 2021 Journal Article

Sensitivity and specificity of CEST and NOE MRI in injured spinal cord in monkeys

• Feng Wang
• Zhongliang Zu
• Tung-Lin Wu
• Xinqiang Yan
• Ming Lu
• Pai-Feng Yang
• Nellie E. Byun
• Jamie L. Reed

AAAI Conference 2020 Conference Paper

Learned Video Compression via Joint Spatial-Temporal Correlation Exploration

• Haojie Liu
• Han Shen
• Lichao Huang
• Ming Lu
• Tong Chen
• Zhan Ma

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Ef- ficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit the temporal correlation using both first-order optical flow and second-order flow prediction. We suggest an one-stage learning approach to encapsulate flow as quantized features from consecutive frames which is then entropy coded with adaptive contexts conditioned on joint spatial-temporal priors to exploit second-order correlations. Joint priors are embedded in autoregressive spatial neighbors, co-located hyper elements and temporal neighbors using ConvLSTM recurrently. We evaluate our approach for the low-delay scenario with High-Efficiency Video Coding (H. 265/HEVC), H. 264/AVC and another learned video compression method, following the common test settings. Our work offers the state-of-theart performance, with consistent gains across all popular test sequences.