Jie Zhou

Zhibin Lan, Liqiang Niu, Fandong Meng et al.

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation paradigm. In this work, we pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm. We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy: a cold-start supervised fine-tuning equips the model with reasoning capabilities and enables it to generate both discriminative and generative embeddings; a subsequent reinforcement learning enhances reasoning and further optimizes generative embedding quality. This pioneering work reveals four key insights: 1) generative embeddings unlock substantial performance gains over conventional discriminative embeddings by leveraging the powerful generative reasoning capabilities of MLLMs; 2) discriminative and generative embeddings are complementary, whose combined oracle performance far exceeding that of either alone; 3) RL can effectively enhance generative embeddings, establishing a scalable optimization paradigm.; 4) repeated sampling at inference boosts downstream task coverage (pass@k), highlighting the inference-time scalability potential of generative embeddings. Evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents, UME-R1 significantly outperforms conventional discriminative embedding models and offers a foundation for more interpretable, reasoning-driven generative multimodal embeddings. Our code, models, and datasets will be publicly available at https://github.com/XMUDeepLIT/UME-R1.

Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang et al.

3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse representations from previous frames to infer the current 3D occupancy. However, they fail to consider the continuity of driving scenarios and ignore the strong prior provided by the evolution of 3D scenes (e.g., only dynamic objects move). In this paper, we propose a world-model-based framework to exploit the scene evolution for perception. We reformulate 3D occupancy prediction as a 4D occupancy forecasting problem conditioned on the current sensor input. We decompose the scene evolution into three factors: 1) ego motion alignment of static scenes; 2) local movements of dynamic objects; and 3) completion of newly-observed scenes. We then employ a Gaussian world model (GaussianWorld) to explicitly exploit these priors and infer the scene evolution in the 3D Gaussian space considering the current RGB observation. We evaluate the effectiveness of our framework on the widely used nuScenes dataset. Our GaussianWorld improves the performance of the single-frame counterpart by over 2% in mIoU without introducing additional computations. Code: https://github.com/zuosc19/GaussianWorld.

Yuqi Wu, Wenzhao Zheng, Sicheng Zuo et al.

3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to embodied agents that demand to gradually perceive the scene through progressive embodied exploration. In this paper, we formulate an embodied 3D occupancy prediction task to target this practical scenario and propose a Gaussian-based EmbodiedOcc framework to accomplish it. We initialize the global scene with uniform 3D semantic Gaussians and progressively update local regions observed by the embodied agent. For each update, we extract semantic and structural features from the observed image and efficiently incorporate them via deformable cross-attention to refine the regional Gaussians. Finally, we employ Gaussian-to-voxel splatting to obtain the global 3D occupancy from the updated 3D Gaussians. Our EmbodiedOcc assumes an unknown (i.e., uniformly distributed) environment and maintains an explicit global memory of it with 3D Gaussians. It gradually gains knowledge through the local refinement of regional Gaussians, which is consistent with how humans understand new scenes through embodied exploration. We reorganize an EmbodiedOcc-ScanNet benchmark based on local annotations to facilitate the evaluation of the embodied 3D occupancy prediction task. Our EmbodiedOcc outperforms existing methods by a large margin and accomplishes the embodied occupancy prediction with high accuracy and efficiency. Code: https://github.com/YkiWu/EmbodiedOcc.

Lang Yu, Zhangyang Gao, Cheng Tan et al.

SE(3)-based generative models have shown great promise in protein geometry modeling and effective structure design. However, the field currently lacks a modularized benchmark to enable comprehensive investigation and fair comparison of different methods. In this paper, we propose Protein-SE(3), a new benchmark based on a unified training framework, which comprises protein scaffolding tasks, integrated generative models, high-level mathematical abstraction, and diverse evaluation metrics. Recent advanced generative models designed for protein scaffolding, from multiple perspectives like DDPM (Genie1 and Genie2), Score Matching (FrameDiff and RfDiffusion) and Flow Matching (FoldFlow and FrameFlow) are integrated into our framework. All integrated methods are fairly investigated with the same training dataset and evaluation metrics. Furthermore, we provide a high-level abstraction of the mathematical foundations behind the generative models, enabling fast prototyping of future algorithms without reliance on explicit protein structures. Accordingly, we release the first comprehensive benchmark built upon unified training framework for SE(3)-based protein structure design, which is publicly accessible at https://github.com/BruthYU/protein-se3.

Zhiqiang Yuan, Ting Zhang, Ying Deng et al.

Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language models (VLMs), applying VLMs to offer walking guidance has become popular. However, the existing methods of walking guidance are mainly based on self-curated question-answering datasets that are not publicly accessible, without a standardized benchmark for training or evaluation. Moreover, walking assistance often requires real-time streaming video analysis and the generation of concise yet informative reminders, making VLMs struggle due to excessive responses and low efficiency in inferences. In this paper, we introduce the first large-scale dataset dedicated to walking assistance, comprising 12,000 video-annotation pairs, to provide a unified benchmark for training and evaluating systems to help visually-impaired individuals walk. Furthermore, a WalkVLM model is proposed, which employs chain of thought for hierarchical planning to generate concise but informative reminders and utilizes temporal-aware adaptive prediction to reduce the temporal redundancy of reminders. Finally, we have established a solid benchmark for blind walking task and verified the advantages of WalkVLM in stream video processing for this task compared to other VLMs. Our dataset and code are available at https://walkvlm2024.github.io.

Shuyang Xie, Jie Zhou, Jun Wang et al.

Computer-generated holography (CGH) presents a transformative solution for near-eye displays in augmented and virtual reality. Recent advances in deep learning have greatly improved CGH in reconstructed quality and computational efficiency. However, deploying neural CGH pipelines directly on compact, eyeglass-style devices is hindered by stringent constraints on computation and energy consumption, while cloud offloading followed by transmission with natural image codecs often distorts phase information and requires high bandwidth to maintain reconstruction quality. Neural compression methods can reduce bandwidth but impose heavy neural decoders at the edge, increasing inference latency and hardware demand. In this work, we introduce JPEG-Inspired Cloud-Edge Holography, an efficient pipeline designed around a learnable transform codec that retains the block-structured and hardware-friendly nature of JPEG. Our system shifts all heavy neural processing to the cloud, while the edge device performs only lightweight decoding without any neural inference. To further improve throughput, we implement custom CUDA kernels for entropy coding on both cloud and edge. This design achieves a peak signal-to-noise ratio of 32.15 dB at $<$ 2 bits per pixel with decode latency as low as 4.2 ms. Both numerical simulations and optical experiments confirm the high reconstruction quality of the holograms. By aligning CGH with a codec that preserves JPEG's structural efficiency while extending it with learnable components, our framework enables low-latency, bandwidth-efficient hologram streaming on resource-constrained wearable devices-using only simple block-based decoding readily supported by modern system-on-chips, without requiring neural decoders or specialized hardware.

Ziyi Wang, Yongming Rao, Shuofeng Sun et al. · tsinghua

Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is able to process various downstream tasks simultaneously. Encouraged by their impressive performance, an increasing number of researchers are venturing into the realm of applying these models to computer vision tasks. However, the inputs and outputs of vision tasks are more diverse, and it is difficult to summarize them as a unified representation. In this paper, we provide a comprehensive overview of the vision generalist models, delving into their characteristics and capabilities within the field. First, we review the background, including the datasets, tasks, and benchmarks. Then, we dig into the design of frameworks that have been proposed in existing research, while also introducing the techniques employed to enhance their performance. To better help the researchers comprehend the area, we take a brief excursion into related domains, shedding light on their interconnections and potential synergies. To conclude, we provide some real-world application scenarios, undertake a thorough examination of the persistent challenges, and offer insights into possible directions for future research endeavors.

Lijie Liu, Jiwen Lu, Chunjing Xu et al.

In this paper, we propose to learn a deep fitting degree scoring network for monocular 3D object detection, which aims to score fitting degree between proposals and object conclusively. Different from most existing monocular frameworks which use tight constraint to get 3D location, our approach achieves high-precision localization through measuring the visual fitting degree between the projected 3D proposals and the object. We first regress the dimension and orientation of the object using an anchor-based method so that a suitable 3D proposal can be constructed. We propose FQNet, which can infer the 3D IoU between the 3D proposals and the object solely based on 2D cues. Therefore, during the detection process, we sample a large number of candidates in the 3D space and project these 3D bounding boxes on 2D image individually. The best candidate can be picked out by simply exploring the spatial overlap between proposals and the object, in the form of the output 3D IoU score of FQNet. Experiments on the KITTI dataset demonstrate the effectiveness of our framework.

Jie Zhou, Xin Tan, Zhiwei Shao et al.

3D object detection from raw and sparse point clouds has been far less treated to date, compared with its 2D counterpart. In this paper, we propose a novel framework called FVNet for 3D front-view proposal generation and object detection from point clouds. It consists of two stages: generation of front-view proposals and estimation of 3D bounding box parameters. Instead of generating proposals from camera images or bird's-eye-view maps, we first project point clouds onto a cylindrical surface to generate front-view feature maps which retains rich information. We then introduce a proposal generation network to predict 3D region proposals from the generated maps and further extrude objects of interest from the whole point cloud. Finally, we present another network to extract the point-wise features from the extruded object points and regress the final 3D bounding box parameters in the canonical coordinates. Our framework achieves real-time performance with 12ms per point cloud sample. Extensive experiments on the 3D detection benchmark KITTI show that the proposed architecture outperforms state-of-the-art techniques which take either camera images or point clouds as input, in terms of accuracy and inference time.