Zhiwei Lin

Tingting Liang, Hongwei Xie, Kaicheng Yu et al. · pku

Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to leverage the feature from the image space. However, people discovered that this underlying assumption makes the current fusion framework infeasible to produce any prediction when there is a LiDAR malfunction, regardless of minor or major. This fundamentally limits the deployment capability to realistic autonomous driving scenarios. In contrast, we propose a surprisingly simple yet novel fusion framework, dubbed BEVFusion, whose camera stream does not depend on the input of LiDAR data, thus addressing the downside of previous methods. We empirically show that our framework surpasses the state-of-the-art methods under the normal training settings. Under the robustness training settings that simulate various LiDAR malfunctions, our framework significantly surpasses the state-of-the-art methods by 15.7% to 28.9% mAP. To the best of our knowledge, we are the first to handle realistic LiDAR malfunction and can be deployed to realistic scenarios without any post-processing procedure. The code is available at https://github.com/ADLab-AutoDrive/BEVFusion.

Kaicheng Yu, Tang Tao, Hongwei Xie et al. · pku

There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR. The camera provides rich semantic information such as color, texture, and the LiDAR reflects the 3D shape and locations of surrounding objects. People discover that fusing these two modalities can significantly boost the performance of 3D perception models as each modality has complementary information to the other. However, we observe that current datasets are captured from expensive vehicles that are explicitly designed for data collection purposes, and cannot truly reflect the realistic data distribution due to various reasons. To this end, we collect a series of real-world cases with noisy data distribution, and systematically formulate a robustness benchmark toolkit, that simulates these cases on any clean autonomous driving datasets. We showcase the effectiveness of our toolkit by establishing the robustness benchmark on two widely-adopted autonomous driving datasets, nuScenes and Waymo, then, to the best of our knowledge, holistically benchmark the state-of-the-art fusion methods for the first time. We observe that: i) most fusion methods, when solely developed on these data, tend to fail inevitably when there is a disruption to the LiDAR input; ii) the improvement of the camera input is significantly inferior to the LiDAR one. We further propose an efficient robust training strategy to improve the robustness of the current fusion method. The benchmark and code are available at https://github.com/kcyu2014/lidar-camera-robust-benchmark

Zhiwei Lin, Tingting Liang, Taihong Xiao et al. · pku

Existing optical flow estimators usually employ the network architectures typically designed for image classification as the encoder to extract per-pixel features. However, due to the natural difference between the tasks, the architectures designed for image classification may be sub-optimal for flow estimation. To address this issue, we propose a neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task. We first design a suitable search space including various convolutional operators and construct a weight-sharing super-network for efficiently evaluating the candidate architectures. Then, for better training the super-network, we propose Feature Alignment Distillation, which utilizes a well-trained flow estimator to guide the training of super-network. Finally, a resource-constrained evolutionary algorithm is exploited to find an optimal architecture (i.e., sub-network). Experimental results show that the discovered architecture with the weights inherited from the super-network achieves 4.67\% F1-all error on KITTI, an 8.4\% reduction of RAFT baseline, surpassing state-of-the-art handcrafted models GMA and AGFlow, while reducing the model complexity and latency. The source code and trained models will be released in https://github.com/VDIGPKU/FlowNAS.

Zhiwei Lin, Yongtao Wang, Shengxiang Qi et al.

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive and time-consuming. Self-supervised pre-training is an effective and desirable way to alleviate this dependence on extensive annotated data. In this work, we present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation in a BEV perspective and avoid complex decoder design during pre-training. Furthermore, we introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder with fine-tuning for masked point cloud inputs. Based on the property of outdoor point clouds in autonomous driving scenarios, i.e., the point clouds of distant objects are more sparse, we propose point density prediction to enable the 3D encoder to learn location information, which is essential for object detection. Experimental results show that BEV-MAE surpasses prior state-of-the-art self-supervised methods and achieves a favorably pre-training efficiency. Furthermore, based on TransFusion-L, BEV-MAE achieves new state-of-the-art LiDAR-based 3D object detection results, with 73.6 NDS and 69.6 mAP on the nuScenes benchmark. The source code will be released at https://github.com/VDIGPKU/BEV-MAE

Junyang Shu, Zhiwei Lin, Bingqing Wei et al.

Reinforcement learning is a promising approach for improving the capabilities of vision-language-action (VLA) models while avoiding the heavy data requirements of imitation learning. However, its effectiveness for VLA models is often constrained by sparse supervision and the difficulty of designing informative reward signals for long-horizon manipulation. In this work, we present Feat2Go, a fine-grained value estimation framework for embodied reinforcement learning. Specifically, Feat2Go first derives a continuous progress target from a pretrained visual world model by measuring patch-level similarity to subgoal states and partitioning episodes into semantic stages with trend-based clustering. We then train an embodied value model to predict this structural progress from the current observation and task instruction, and use the predicted value to reshape terminal rewards during policy optimization. The proposed framework is compatible with existing VLA policy reinforcement learning pipelines, including PPO and GRPO, and does not rely on manual reward engineering. Extensive experiments on ManiSkill3 and RoboTwin 2.0 demonstrate that Feat2Go consistently improves the performance of existing VLA models under both single-arm and bimanual manipulation settings. More specifically, on ManiSkill3, Feat2Go improves OpenVLAOFT from 17.5% to 82.9% average out-of-distribution success while retaining 96.9% in-distribution performance. On RoboTwin 2.0, Feat2Go achieves an average success rate of 88.8% in domain-randomized task settings, outperforming prior reinforcement learning methods.

Zhiwei Lin, Zengyu Yang, Yongtao Wang

Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at https://github.com/VDIGPKU/FORMULA.

Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan et al.

Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input. In this paper, we introduce SAMPLING, a Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image based on improved multiplane images (MPI). Observing that depth distribution varies significantly for unbounded outdoor scenes, we employ an adaptive-bins strategy for MPI to arrange planes in accordance with each scene image. To represent intricate geometry and multi-scale details, we further introduce a hierarchical refinement branch, which results in high-quality synthesized novel views. Our method demonstrates considerable performance gains in synthesizing large-scale unbounded outdoor scenes using a single image on the KITTI dataset and generalizes well to the unseen Tanks and Temples dataset.The code and models will soon be made available.

Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan et al.

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https://github.com/VDIGPKU/DrivingGaussian.

Zhiwei Lin, Zhe Liu, Yongtao Wang et al.

Perceiving the surrounding environment is a fundamental task in autonomous driving. To obtain highly accurate perception results, modern autonomous driving systems typically employ multi-modal sensors to collect comprehensive environmental data. Among these, the radar-camera multi-modal perception system is especially favored for its excellent sensing capabilities and cost-effectiveness. However, the substantial modality differences between radar and camera sensors pose challenges in fusing information. To address this problem, this paper presents RCBEVDet, a radar-camera fusion 3D object detection framework. Specifically, RCBEVDet is developed from an existing camera-based 3D object detector, supplemented by a specially designed radar feature extractor, RadarBEVNet, and a Cross-Attention Multi-layer Fusion (CAMF) module. Firstly, RadarBEVNet encodes sparse radar points into a dense bird's-eye-view (BEV) feature using a dual-stream radar backbone and a Radar Cross Section aware BEV encoder. Secondly, the CAMF module utilizes a deformable attention mechanism to align radar and camera BEV features and adopts channel and spatial fusion layers to fuse them. To further enhance RCBEVDet's capabilities, we introduce RCBEVDet++, which advances the CAMF through sparse fusion, supports query-based multi-view camera perception models, and adapts to a broader range of perception tasks. Extensive experiments on the nuScenes show that our method integrates seamlessly with existing camera-based 3D perception models and improves their performance across various perception tasks. Furthermore, our method achieves state-of-the-art radar-camera fusion results in 3D object detection, BEV semantic segmentation, and 3D multi-object tracking tasks. Notably, with ViT-L as the image backbone, RCBEVDet++ achieves 72.73 NDS and 67.34 mAP in 3D object detection without test-time augmentation or model ensembling.

Zhiwei Lin, Zhe Liu, Zhongyu Xia et al.

Three-dimensional object detection is one of the key tasks in autonomous driving. To reduce costs in practice, low-cost multi-view cameras for 3D object detection are proposed to replace the expansive LiDAR sensors. However, relying solely on cameras is difficult to achieve highly accurate and robust 3D object detection. An effective solution to this issue is combining multi-view cameras with the economical millimeter-wave radar sensor to achieve more reliable multi-modal 3D object detection. In this paper, we introduce RCBEVDet, a radar-camera fusion 3D object detection method in the bird's eye view (BEV). Specifically, we first design RadarBEVNet for radar BEV feature extraction. RadarBEVNet consists of a dual-stream radar backbone and a Radar Cross-Section (RCS) aware BEV encoder. In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders. The RCS-aware BEV encoder takes RCS as the object size prior to scattering the point feature in BEV. Besides, we present the Cross-Attention Multi-layer Fusion module to automatically align the multi-modal BEV feature from radar and camera with the deformable attention mechanism, and then fuse the feature with channel and spatial fusion layers. Experimental results show that RCBEVDet achieves new state-of-the-art radar-camera fusion results on nuScenes and view-of-delft (VoD) 3D object detection benchmarks. Furthermore, RCBEVDet achieves better 3D detection results than all real-time camera-only and radar-camera 3D object detectors with a faster inference speed at 21~28 FPS. The source code will be released at https://github.com/VDIGPKU/RCBEVDet.

Yiwei Zhou, Xiaobo Xia, Zhiwei Lin et al.

The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial robustness by aligning adversarial visual features with text supervision. However, in practice, they are still unsatisfactory due to several issues, including heavy adaptation cost, suboptimal text supervision, and uncontrolled natural generalization capacity. In this paper, to address these issues, we propose a few-shot adversarial prompt framework where adapting input sequences with limited data makes significant adversarial robustness improvement. Specifically, we achieve this by providing adversarially correlated text supervision that is end-to-end learned from adversarial examples. We also propose a novel training objective that enhances the consistency of multi-modal features while encourages differentiated uni-modal features between natural and adversarial examples. The proposed framework gives access to learn adversarial text supervision, which provides superior cross-modal adversarial alignment and matches state-of-the-art zero-shot adversarial robustness with only 1% training data. Code is available at: https://github.com/lionel-w2/FAP.

Xu He, Qiaochu Huang, Zhensong Zhang et al.

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion.

Haoyu Wang, Zhuo Huang, Xiaolong Wang et al.

The growing concern over training data privacy has elevated the "Right to be Forgotten" into a critical requirement, thereby raising the demand for effective Machine Unlearning. However, existing unlearning approaches commonly suffer from a fundamental trade-off: aggressively erasing the influence of target data often degrades model utility on retained data, while conservative strategies leave residual target information intact. In this work, the intrinsic representation properties learned during model pretraining are analyzed. It is demonstrated that semantic class concepts are entangled at the feature-pattern level, sharing associated features while preserving concept-specific discriminative components. This entanglement fundamentally limits the effectiveness of existing unlearning paradigms. Motivated by this insight, we propose Machine-Guided Unlearning (MeGU), a novel framework that guides unlearning through concept-aware re-alignment. Specifically, Multi-modal Large Language Models (MLLMs) are leveraged to explicitly determine re-alignment directions for target samples by assigning semantically meaningful perturbing labels. To improve efficiency, inter-class conceptual similarities estimated by the MLLM are encoded into a lightweight transition matrix. Furthermore, MeGU introduces a positive-negative feature noise pair to explicitly disentangle target concept influence. During finetuning, the negative noise suppresses target-specific feature patterns, while the positive noise reinforces remaining associated features and aligns them with perturbing concepts. This coordinated design enables selective disruption of target-specific representations while preserving shared semantic structures. As a result, MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.

Zhongyu Xia, ZhiWei Lin, Xinhao Wang et al.

Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception precision, large image encoders, high-resolution images, and long-term temporal inputs have been adopted in recent 3D perception models, bringing remarkable performance gains. However, these techniques are often incompatible in training and inference scenarios due to computational resource constraints. Besides, modern autonomous driving systems prefer to adopt an end-to-end framework for multi-task 3D perception, which can simplify the overall system architecture and reduce the implementation complexity. However, conflict between tasks often arises when optimizing multiple tasks jointly within an end-to-end 3D perception model. To alleviate these issues, we present an end-to-end framework named HENet for multi-task 3D perception in this paper. Specifically, we propose a hybrid image encoding network, using a large image encoder for short-term frames and a small image encoder for long-term temporal frames. Then, we introduce a temporal feature integration module based on the attention mechanism to fuse the features of different frames extracted by the two aforementioned hybrid image encoders. Finally, according to the characteristics of each perception task, we utilize BEV features of different grid sizes, independent BEV encoders, and task decoders for different tasks. Experimental results show that HENet achieves state-of-the-art end-to-end multi-task 3D perception results on the nuScenes benchmark, including 3D object detection and BEV semantic segmentation. The source code and models will be released at https://github.com/VDIGPKU/HENet.

Bingqing Wei, Zhongyu Xia, Dingai Liu et al.

Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a fundamental gap between the static training data of VLMs and the physical interaction for embodied tasks. VLMs can learn rich semantic knowledge from static data but lack the ability to interact with the world. To address this issue, we introduce ELITE, an embodied agent framework with {E}xperiential {L}earning and {I}ntent-aware {T}ransfer that enables agents to continuously learn from their own environment interaction experiences, and transfer acquired knowledge to procedurally similar tasks. ELITE operates through two synergistic mechanisms, \textit{i.e.,} self-reflective knowledge construction and intent-aware retrieval. Specifically, self-reflective knowledge construction extracts reusable strategies from execution trajectories and maintains an evolving strategy pool through structured refinement operations. Then, intent-aware retrieval identifies relevant strategies from the pool and applies them to current tasks. Experiments on the EB-ALFRED and EB-Habitat benchmarks show that ELITE achieves 9\% and 5\% performance improvement over base VLMs in the online setting without any supervision. In the supervised setting, ELITE generalizes effectively to unseen task categories, achieving better performance compared to state-of-the-art training-based methods. These results demonstrate the effectiveness of ELITE for bridging the gap between semantic understanding and reliable action execution.

Shun Lei, Yaoxun Xu, Zhiwei Lin et al.

Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in audio quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, a language model based framework consisting of LeLM and Music Codec. LeLM is capable of parallel modeling of two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve better vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following ability, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and post-training. Experimental results demonstrate that LeVo significantly outperforms existing open-source methods in both objective and subjective metrics, while performing competitively with industry systems. Ablation studies further justify the effectiveness of our designs. Audio examples and source code are available at https://levo-demo.github.io and https://github.com/tencent-ailab/songgeneration.

Zhongyu Xia, Zhiwei Lin, Yongtao Wang et al.

Three-dimensional feature extraction is a critical component of autonomous driving systems, where perception tasks such as 3D object detection, bird's-eye-view (BEV) semantic segmentation, and occupancy prediction serve as important constraints on 3D features. While large image encoders, high-resolution images, and long-term temporal inputs can significantly enhance feature quality and deliver remarkable performance gains, these techniques are often incompatible in both training and inference due to computational resource constraints. Moreover, different tasks favor distinct feature representations, making it difficult for a single model to perform end-to-end inference across multiple tasks while maintaining accuracy comparable to that of single-task models. To alleviate these issues, we present the HENet and HENet++ framework for multi-task 3D perception and end-to-end autonomous driving. Specifically, we propose a hybrid image encoding network that uses a large image encoder for short-term frames and a small one for long-term frames. Furthermore, our framework simultaneously extracts both dense and sparse features, providing more suitable representations for different tasks, reducing cumulative errors, and delivering more comprehensive information to the planning module. The proposed architecture maintains compatibility with various existing 3D feature extraction methods and supports multimodal inputs. HENet++ achieves state-of-the-art end-to-end multi-task 3D perception results on the nuScenes benchmark, while also attaining the lowest collision rate on the nuScenes end-to-end autonomous driving benchmark.

Zhiwei Lin, Hongbo Jin, Yongtao Wang et al.

As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view or neural radiance fields, while ignoring the advantages of using long-temporal information. In this paper, we propose a radar-camera multi-modal temporal enhanced occupancy prediction network, dubbed TEOcc. Our method is inspired by the success of utilizing temporal information in 3D object detection. Specifically, we introduce a temporal enhancement branch to learn temporal occupancy prediction. In this branch, we randomly discard the t-k input frame of the multi-view camera and predict its 3D occupancy by long-term and short-term temporal decoders separately with the information from other adjacent frames and multi-modal inputs. Besides, to reduce computational costs and incorporate multi-modal inputs, we specially designed 3D convolutional layers for long-term and short-term temporal decoders. Furthermore, since the lightweight occupancy prediction head is a dense classification head, we propose to use a shared occupancy prediction head for the temporal enhancement and main branches. It is worth noting that the temporal enhancement branch is only performed during training and is discarded during inference. Experiment results demonstrate that TEOcc achieves state-of-the-art occupancy prediction on nuScenes benchmarks. In addition, the proposed temporal enhancement branch is a plug-and-play module that can be easily integrated into existing occupancy prediction methods to improve the performance of occupancy prediction. The code and models will be released at https://github.com/VDIGPKU/TEOcc.

Zhongyu Xia, Jishuo Li, Zhiwei Lin et al.

Open-world perception aims to develop a model adaptable to novel domains and various sensor configurations and can understand uncommon objects and corner cases. However, current research lacks sufficiently comprehensive open-world 3D perception benchmarks and robust generalizable methodologies. This paper introduces OpenAD, the first real open-world autonomous driving benchmark for 3D object detection. OpenAD is built upon a corner case discovery and annotation pipeline that integrates with a multimodal large language model (MLLM). The proposed pipeline annotates corner case objects in a unified format for five autonomous driving perception datasets with 2000 scenarios. In addition, we devise evaluation methodologies and evaluate various open-world and specialized 2D and 3D models. Moreover, we propose a vision-centric 3D open-world object detection baseline and further introduce an ensemble method by fusing general and specialized models to address the issue of lower precision in existing open-world methods for the OpenAD benchmark. We host an online challenge on EvalAI. Data, toolkit codes, and evaluation codes are available at https://github.com/VDIGPKU/OpenAD.

Zhiwei Lin, Yongtao Wang, Hongxiang Lin

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are suffering from a catastrophic forgetting problem, which is not studied extensively. In this paper, we make the first attempt to tackle the catastrophic forgetting problem in the mainstream self-supervised methods, i.e., contrastive learning methods. Specifically, we first develop a rehearsal-based framework combined with a novel sampling strategy and a self-supervised knowledge distillation to transfer information over time efficiently. Then, we propose an extra sample queue to help the network separate the feature representations of old and new data in the embedding space. Experimental results show that compared with the naive self-supervised baseline, which learns tasks one by one without taking any technique, we improve the image classification accuracy by 1.60% on CIFAR-100, 2.86% on ImageNet-Sub, and 1.29% on ImageNet-Full under 10 incremental steps setting. Our code will be available at https://github.com/VDIGPKU/ContinualContrastiveLearning.

Zhiwei Lin, Hui Wang, Cees H. Elzinga

Preference orderings are orderings of a set of items according to the preferences (of judges). Such orderings arise in a variety of domains, including group decision making, consumer marketing, voting and machine learning. Measuring the mutual information and extracting the common patterns in a set of preference orderings are key to these areas. In this paper we deal with the representation of sets of preference orderings, the quantification of the degree to which judges agree on their ordering of the items (i.e. the concordance), and the efficient, meaningful description of such sets. We propose to represent the orderings in a subsequence-based feature space and present a new algorithm to calculate the size of the set of all common subsequences - the basis of a quantification of concordance, not only for pairs of orderings but also for sets of orderings. The new algorithm is fast and storage efficient with a time complexity of only $O(Nn^2)$ for the orderings of $n$ items by $N$ judges and a space complexity of only $O(\min\{Nn,n^2\})$. Also, we propose to represent the set of all $N$ orderings through a smallest set of covering preferences and present an algorithm to construct this smallest covering set. The source code for the algorithms is available at https://github.com/zhiweiuu/secs

Xiaoyu Zhou, Xingjian Ran, Yajiao Xiong et al.

We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at gala3d.github.io.

Chih-Chung Liu, Zhiwei Lin, Yongtao Wang

Open-world object detection aims to localize and recognize objects beyond a fixed closed-set label space. It is commonly divided into two categories, i.e., open-vocabulary detection, which assumes a predefined category list at test time, and open-ended detection, which requires generating candidate categories during the inference. Existing methods rely primarily on coarse textual semantics and parametric knowledge, which often provide insufficient visual evidence for fine-grained appearance variation, rare categories, and cluttered scenes. In this paper, we propose VL-SAM-v3, a unified framework that augments open-world detection with retrieval-grounded external visual memory. Specifically, once candidate categories are available, VL-SAM-v3 retrieves relevant visual prototypes from a non-parametric memory bank and transforms them into two complementary visual priors, i.e., sparse priors for instance-level spatial anchoring and dense priors for class-aware local context. These priors are integrated with the original detection prompts via Memory-Guided Prompt Refinement, enabling a shared retrieval-and-refinement mechanism that supports open-vocabulary and open-ended inference.Extensive zero-shot experiments on LVIS show that VL-SAM-v3 consistently improves detection performance under both open-vocabulary and open-ended inference, with particularly strong gains on rare categories.Moreover, experiments with a stronger open-vocabulary detector (i.e., SAM3) validate the generality of the proposed retrieval-and-refinement mechanism.

Jingtong Yue, Zhiwei Lin, Xin Lin et al.

While recent low-cost radar-camera approaches have shown promising results in multi-modal 3D object detection, both sensors face challenges from environmental and intrinsic disturbances. Poor lighting or adverse weather conditions degrade camera performance, while radar suffers from noise and positional ambiguity. Achieving robust radar-camera 3D object detection requires consistent performance across varying conditions, a topic that has not yet been fully explored. In this work, we first conduct a systematic analysis of robustness in radar-camera detection on five kinds of noises and propose RobuRCDet, a robust object detection model in BEV. Specifically, we design a 3D Gaussian Expansion (3DGE) module to mitigate inaccuracies in radar points, including position, Radar Cross-Section (RCS), and velocity. The 3DGE uses RCS and velocity priors to generate a deformable kernel map and variance for kernel size adjustment and value distribution. Additionally, we introduce a weather-adaptive fusion module, which adaptively fuses radar and camera features based on camera signal confidence. Extensive experiments on the popular benchmark, nuScenes, show that our model achieves competitive results in regular and noisy conditions.

Zhiwei Lin, Jun Chen, Boshi Tang et al.

Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention. Nevertheless, previous VAEs still encounter issues with overly long feature sequences and generated results lack contextual coherence, thus the challenge of modeling long multi-track symbolic music still remains unaddressed. To this end, we propose Multi-view MidiVAE, as one of the pioneers in VAE methods that effectively model and generate long multi-track symbolic music. The Multi-view MidiVAE utilizes the two-dimensional (2-D) representation, OctupleMIDI, to capture relationships among notes while reducing the feature sequences length. Moreover, we focus on instrumental characteristics and harmony as well as global and local information about the musical composition by employing a hybrid variational encoding-decoding strategy to integrate both Track- and Bar-view MidiVAE features. Objective and subjective experimental results on the CocoChorales dataset demonstrate that, compared to the baseline, Multi-view MidiVAE exhibits significant improvements in terms of modeling long multi-track symbolic music.

Xinhao Wang, Zhonyu Xia, Zhiwei Lin et al.

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning are standard compression techniques, they are usually treated as independent optimizations. In this paper, we show that these two techniques are strongly coupled: naively applying semantic-based token pruning to PTQ-optimized MLLMs can discard activation outliers that are important for numerical stability and thus worsen quantization errors in low-bit regimes (\textit{e.g.}, W4A4). To address this issue, we propose a quantization-aware vision token pruning framework. Our method introduces a lightweight hybrid sensitivity metric that combines simulated group-wise quantization error with outlier intensity. By combining this metric with standard semantic relevance scores, the method retains tokens that are both semantically informative and robust to quantization. Experiments on standard LLaVA architectures show that our method consistently outperforms naive integration baselines. At an aggressive pruning ratio that retains only 12.5\% of visual tokens, our framework improves accuracy by 2.24\% over the baseline and even surpasses dense quantization without pruning. To the best of our knowledge, this is the first method that explicitly co-optimizes vision token pruning and PTQ for accurate low-bit MLLM inference.

Weihao Wu, Liang Cao, Xinyu Wu et al.

Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona adoption. However, current RPCA research faces dual limitations. First, existing work predominantly focuses on the textual modality, entirely overlooking critical paralinguistic features including intonation, prosody, and rhythm in speech, which are essential for conveying character emotions and shaping vivid identities. Second, the speech-based role-playing domain suffers from a long-standing lack of standardized evaluation benchmarks. Most current spoken dialogue datasets target only fundamental capability assessments, featuring thinly sketched or ill-defined character profiles. Consequently, they fail to effectively quantify model performance on core competencies like long-term persona consistency. To address this critical gap, we introduce VoxRole, the first comprehensive benchmark specifically designed for the evaluation of speech-based RPCAs. The benchmark comprises 13335 multi-turn dialogues, totaling 65.6 hours of speech from 1228 unique characters across 261 movies. To construct this resource, we propose a novel two-stage automated pipeline that first aligns movie audio with scripts and subsequently employs an LLM to systematically build multi-dimensional profiles for each character. Leveraging VoxRole, we conduct a multi-dimensional evaluation of contemporary spoken dialogue models, revealing crucial insights into their respective strengths and limitations in maintaining persona consistency.

Xinhao Wang, Zhiwei Lin, Zhongyu Xia et al.

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes substantial GPU memory requirements and extended training time due to weight fine-tuning. In this paper, we propose PTQAT, a novel general hybrid quantization algorithm for the efficient deployment of 3D perception networks. To address the speed accuracy trade-off between PTQ and QAT, our method selects critical layers for QAT fine-tuning and performs PTQ on the remaining layers. Contrary to intuition, fine-tuning the layers with smaller output discrepancies before and after quantization, rather than those with larger discrepancies, actually leads to greater improvements in the model's quantization accuracy. This means we better compensate for quantization errors during their propagation, rather than addressing them at the point where they occur. The proposed PTQAT achieves similar performance to QAT with more efficiency by freezing nearly 50% of quantifiable layers. Additionally, PTQAT is a universal quantization method that supports various quantization bit widths (4 bits) as well as different model architectures, including CNNs and Transformers. The experimental results on nuScenes across diverse 3D perception tasks, including object detection, semantic segmentation, and occupancy prediction, show that our method consistently outperforms QAT-only baselines. Notably, it achieves 0.2%-0.9% NDS and 0.3%-1.0% mAP gains in object detection, 0.3%-2.0% mIoU gains in semantic segmentation and occupancy prediction while fine-tuning fewer weights.

Weihao wu, Zhiwei Lin, Yixuan Zhou et al.

Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, existing CSS systems are limited to deterministic prediction, overlooking the diversity of potential responses. Moreover, they rarely employ language model (LM)-based TTS backbones, limiting the naturalness and quality of synthesized speech. To address these issues, in this paper, we propose DiffCSS, an innovative CSS framework that leverages diffusion models and an LM-based TTS backbone to generate diverse, expressive, and contextually coherent speech. A diffusion-based context-aware prosody predictor is proposed to sample diverse prosody embeddings conditioned on multimodal conversational context. Then a prosody-controllable LM-based TTS backbone is developed to synthesize high-quality speech with sampled prosody embeddings. Experimental results demonstrate that the synthesized speech from DiffCSS is more diverse, contextually coherent, and expressive than existing CSS systems

Yuhan Chen, Lumei Su, Lihua Chen et al.

In this paper, the LCV2 modular method is proposed for the Grounded Visual Question Answering task in the vision-language multimodal domain. This approach relies on a frozen large language model (LLM) as intermediate mediator between the off-the-shelf VQA model and the off-the-shelf visual grounding (VG) model, where the LLM transforms and conveys textual information between the two modules based on a designed prompt. LCV2 establish an integrated plug-and-play framework without the need for any pre-training process. This framework can be deployed for VQA Grounding tasks under low computational resources. The modularized model within the framework allows application with various state-of-the-art pre-trained models, exhibiting significant potential to be advance with the times. Experimental implementations were conducted under constrained computational and memory resources, evaluating the proposed method's performance on benchmark datasets including GQA, CLEVR, and VizWiz-VQA-Grounding. Comparative analyses with baseline methods demonstrate the robust competitiveness of LCV2.

Zhe Li, Zhiwei Lin, Yongtao Wang

The integration of Large Language Models (LLMs) with Neural Architecture Search (NAS) has introduced new possibilities for automating the design of neural architectures. However, most existing methods face critical limitations, including architectural invalidity, computational inefficiency, and inferior performance compared to traditional NAS. In this work, we present Collaborative LLM-based NAS (CoLLM-NAS), a two-stage NAS framework with knowledge-guided search driven by two complementary LLMs. Specifically, we propose a Navigator LLM to guide search direction and a Generator LLM to synthesize high-quality candidates, with a dedicated Coordinator module to manage their interaction. CoLLM-NAS efficiently guides the search process by combining LLMs' inherent knowledge of structured neural architectures with progressive knowledge from iterative feedback and historical trajectory. Experimental results on ImageNet and NAS-Bench-201 show that CoLLM-NAS surpasses existing NAS methods and conventional search algorithms, achieving new state-of-the-art results. Furthermore, CoLLM-NAS consistently enhances the performance and efficiency of various two-stage NAS methods (e.g., OFA, SPOS, and AutoFormer) across diverse search spaces (e.g., MobileNet, ShuffleNet, and AutoFormer), demonstrating its excellent generalization.

Zhiwei Lin, Weicheng Zheng, Yongtao Wang

Detecting objects efficiently from radar sensors has recently become a popular trend due to their robustness against adverse lighting and weather conditions compared with cameras. This paper presents an efficient object detection model for Range-Doppler (RD) radar maps. Specifically, we first represent RD radar maps with multi-representation, i.e., heatmaps and grayscale images, to gather high-level object and fine-grained texture features. Then, we design an additional Adapter branch, an Exchanger Module with two modes, and a Primary-Auxiliary Fusion Module to effectively extract, exchange, and fuse features from the multi-representation inputs, respectively. Furthermore, we construct a supernet with various width and fusion operations in the Adapter branch for the proposed model and employ a One-Shot Neural Architecture Search method to further improve the model's efficiency while maintaining high performance. Experimental results demonstrate that our model obtains favorable accuracy and efficiency trade-off. Moreover, we achieve new state-of-the-art performance on RADDet and CARRADA datasets with mAP@50 of 71.9 and 57.1, respectively.

Xinyi Yu, Zhiwei Lin, Yongtao Wang

Synthetic Aperture Radar (SAR) object detection faces significant challenges from speckle noise, small target ambiguities, and on-board computational constraints. While existing approaches predominantly focus on SAR-specific architectural modifications, this paper explores the application of the existing lightweight object detector, i.e., YOLOv10, for SAR object detection and enhances its performance through Neural Architecture Search (NAS). Specifically, we employ NAS to systematically optimize the network structure, especially focusing on the backbone architecture search. By constructing an extensive search space and leveraging evolutionary search, our method identifies a favorable architecture that balances accuracy, parameter efficiency, and computational cost. Notably, this work introduces NAS to SAR object detection for the first time. The experimental results on the large-scale SARDet-100K dataset demonstrate that our optimized model outperforms existing SAR detection methods, achieving superior detection accuracy while maintaining lower computational overhead. We hope this work offers a novel perspective on leveraging NAS for real-world applications.

Yuan-Chen Shu, Zhiwei Lin, Yongtao Wang

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific developed for specific domains. If used on other domains may lead to performance degradation. This issue of catastrophic forgetting severely limits the model's scalability. To address this issue, this paper proposes RegCL, a novel non-replay continual learning (CL) framework designed for efficient multi-domain knowledge integration through model merging. Specifically, RegCL incorporates the model merging algorithm into the continual learning paradigm by merging the parameters of SAM's adaptation modules (e.g., LoRA modules) trained on different domains. The merging process is guided by weight optimization, which minimizes prediction discrepancies between the merged model and each of the domain-specific models. RegCL effectively consolidates multi-domain knowledge while maintaining parameter efficiency, i.e., the model size remains constant regardless of the number of tasks, and no historical data storage is required. Experimental results demonstrate that RegCL achieves favorable continual learning performance across multiple downstream datasets, validating its effectiveness in dynamic scenarios.

Zhiwei Lin, Yongtao Wang

Current perception models have achieved remarkable success by leveraging large-scale labeled datasets, but still face challenges in open-world environments with novel objects. To address this limitation, researchers introduce open-set perception models to detect or segment arbitrary test-time user-input categories. However, open-set models rely on human involvement to provide predefined object categories as input during inference. More recently, researchers have framed a more realistic and challenging task known as open-ended perception that aims to discover unseen objects without requiring any category-level input from humans at inference time. Nevertheless, open-ended models suffer from low performance compared to open-set models. In this paper, we present VL-SAM-V2, an open-world object detection framework that is capable of discovering unseen objects while achieving favorable performance. To achieve this, we combine queries from open-set and open-ended models and propose a general and specific query fusion module to allow different queries to interact. By adjusting queries from open-set models, we enable VL-SAM-V2 to be evaluated in the open-set or open-ended mode. In addition, to learn more diverse queries, we introduce ranked learnable queries to match queries with proposals from open-ended models by sorting. Moreover, we design a denoising point training strategy to facilitate the training process. Experimental results on LVIS show that our method surpasses the previous open-set and open-ended methods, especially on rare objects.

Fanghua Ye, Zhiwei Lin, Chuan Chen et al.

The proliferation of Web services makes it difficult for users to select the most appropriate one among numerous functionally identical or similar service candidates. Quality-of-Service (QoS) describes the non-functional characteristics of Web services, and it has become the key differentiator for service selection. However, users cannot invoke all Web services to obtain the corresponding QoS values due to high time cost and huge resource overhead. Thus, it is essential to predict unknown QoS values. Although various QoS prediction methods have been proposed, few of them have taken outliers into consideration, which may dramatically degrade the prediction performance. To overcome this limitation, we propose an outlier-resilient QoS prediction method in this paper. Our method utilizes Cauchy loss to measure the discrepancy between the observed QoS values and the predicted ones. Owing to the robustness of Cauchy loss, our method is resilient to outliers. We further extend our method to provide time-aware QoS prediction results by taking the temporal information into consideration. Finally, we conduct extensive experiments on both static and dynamic datasets. The results demonstrate that our method is able to achieve better performance than state-of-the-art baseline methods.

Isaac K. E. Ampomah, Sally McClean, Zhiwei Lin et al.

Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using the character-level and the word embedding vectors as inputs. Others have shown that linguistic features can improve the performance of neural models on tasks such as chunking and named entity recognition (NER). However, the change in performance depends on the degree of semantic relatedness between the linguistic features and the target task; in some instances, linguistic features can have a negative impact on performance. This paper presents an approach to jointly learn these linguistic features along with the target sequence labelling tasks with a new multi-task learning (MTL) framework called Gated Tasks Interaction (GTI) network for solving multiple sequence tagging tasks. The GTI network exploits the relations between the multiple tasks via neural gate modules. These gate modules control the flow of information between the different tasks. Experiments on benchmark datasets for chunking and NER show that our framework outperforms other competitive baselines trained with and without external training resources.

Lianbo Ma, Peng Sun, Zhiwei Lin et al.

Learning knowledge graph embedding from an existing knowledge graph is very important to knowledge graph completion. For a fact $(h,r,t)$ with the head entity $h$ having a relation $r$ with the tail entity $t$, the current approaches aim to learn low dimensional representations $(\mathbf{h},\mathbf{r},\mathbf{t})$, each of which corresponds to the elements in $(h, r, t)$, respectively. As $(\mathbf{h},\mathbf{r},\mathbf{t})$ is learned from the existing facts within a knowledge graph, these representations can not be used to detect unknown facts (if the entities or relations never occur in the knowledge graph). This paper proposes a new approach called TransW, aiming to go beyond the current work by composing knowledge graph embeddings using word embeddings. Given the fact that an entity or a relation contains one or more words (quite often), it is sensible to learn a mapping function from word embedding spaces to knowledge embedding spaces, which shows how entities are constructed using human words. More importantly, composing knowledge embeddings using word embeddings makes it possible to deal with the emerging new facts (either new entities or relations). Experimental results using three public datasets show the consistency and outperformance of the proposed TransW.

Zhengui Xue, Zhiwei Lin, Hui Wang et al.

Rankings, representing preferences over a set of candidates, are widely used in many information systems, e.g., group decision making and information retrieval. It is of great importance to evaluate the consensus of the obtained rankings from multiple agents. An overall measure of the consensus degree provides an insight into the ranking data. Moreover, it could provide a quantitative indicator for consensus comparison between groups and further improvement of a ranking system. Existing studies are insufficient in assessing the overall consensus of a ranking set. They did not provide an evaluation of the consensus degree of preference patterns in most rankings. In this paper, a novel consensus quantifying approach, without the need for any correlation or distance functions as in existing studies of consensus, is proposed based on a concept of q-support patterns of rankings. The q-support patterns represent the commonality embedded in a set of rankings. A method for detecting outliers in a set of rankings is naturally derived from the proposed consensus quantifying approach. Experimental studies are conducted to demonstrate the effectiveness of the proposed approach.

Zhiwei Lin, Yi Li, Xiaolian Guo

A ranking is an ordered sequence of items, in which an item with higher ranking score is more preferred than the items with lower ranking scores. In many information systems, rankings are widely used to represent the preferences over a set of items or candidates. The consensus measure of rankings is the problem of how to evaluate the degree to which the rankings agree. The consensus measure can be used to evaluate rankings in many information systems, as quite often there is not ground truth available for evaluation. This paper introduces a novel approach for consensus measure of rankings by using graph representation, in which the vertices or nodes are the items and the edges are the relationship of items in the rankings. Such representation leads to various algorithms for consensus measure in terms of different aspects of rankings, including the number of common patterns, the number of common patterns with fixed length and the length of the longest common patterns. The proposed measure can be adopted for various types of rankings, such as full rankings, partial rankings and rankings with ties. This paper demonstrates how the proposed approaches can be used to evaluate the quality of rank aggregation and the quality of top-$k$ rankings from Google and Bing search engines.