6 citations · 15 across the 18 of their papers we have counts for
20 papers
Fast-VLA: You Only Think Once for Robot Manipulation
Kehong Gong, Guanli Hou, Xiaoxu Zheng +6
Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whenever they predict a new actio…
StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs
Zhe Wei, Mengqi Guo, Yuan Yuan +3
Serving a large language model (LLM) across a fleet of deployments requires several weight-precision operating points. Multi-precision formats serve them all from one stream whose…
Breaking the Horizontal Prior: From Long-Tailed Orientation Bias to Roll-Robust Monocular Depth Estimation
Kaihua Tang, Ziqing Xia, Xiaoxu Zheng +4
Despite recent advances in Monocular Depth Estimation, state-of-the-art depth foundation models remain vulnerable to robustness issues. Particularly, even slight camera rolls can r…
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
Xiaoxue Zhang, Xiaoxu Zheng, Yixuan Yin +5
Recent feed-forward Gaussian reconstruction models adopt a pixel-aligned formulation that maps each 2D pixel to a 3D Gaussian, entangling Gaussian representations tightly with the…
HiFloat4 Format for Language Model Inference
Yuanyong Luo, Jing Huang, Yu Cheng +19
This paper introduces HiFloat4 (HiF4), a block floating-point data format tailored for deep learning. Each HiF4 unit packs 64 4-bit elements with 32 bits of shared scaling metadata…
GhostRNN: Reducing State Redundancy in RNN with Cheap Operations
Hang Zhou, Xiaoxu Zheng, Yunhe Wang +3
Recurrent neural network (RNNs) that are capable of modeling long-distance dependencies are widely used in various speech tasks, eg., keyword spotting (KWS) and speech enhancement…
Vista3D: Unravel the 3D Darkside of a Single Image
Qiuhong Shen, Xingyi Yang, Michael Bi Mi +1
We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes…
Isomorphic Pruning for Vision Models
Gongfan Fang, Xinyin Ma, Michael Bi Mi +1
Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. However, assessing the relative importance of different sub-stru…
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
Xinyin Ma, Gongfan Fang, Michael Bi Mi +1
Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, s…
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators
Hanyang Kong, Dongze Lian, Michael Bi Mi +1
We introduce DreamDrone, a novel zero-shot and training-free pipeline for generating unbounded flythrough scenes from textual prompts. Different from other methods that focus on wa…
Learning Unorthogonalized Matrices for Rotation Estimation
Kerui Gu, Zhihao Li, Shiyong Liu +6
Estimating 3D rotations is a common procedure for 3D computer vision. The accuracy depends heavily on the rotation representation. One form of representation -- rotation matrices -…
Priority-Centric Human Motion Generation in Discrete Latent Space
Hanyang Kong, Kehong Gong, Dongze Lian +2
Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While th…
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
Ming Nie, Yujing Xue, Chunwei Wang +7
Recently, polar-based representation has shown promising properties in perceptual tasks. In addition to Cartesian-based approaches, which separate point clouds unevenly, representi…
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
Kai Xu, Ziwei Yu, Xin Wang +2
In video super-resolution, it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhan…
Bias-Compensated Integral Regression for Human Pose Estimation
Kerui Gu, Linlin Yang, Michael Bi Mi +1
In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coor…
DepGraph: Towards Any Structural Pruning
Gongfan Fang, Xinyin Ma, Mingli Song +2
Structural pruning enables model acceleration by removing structurally-grouped parameters from neural networks. However, the parameter-grouping patterns vary widely across differen…
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
Xin Yang, Michael Bi Mi, Yuan Yuan +2
Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, renderin…
ONCE-3DLanes: Building Monocular 3D Lane Detection
Fan Yan, Ming Nie, Xinyue Cai +7
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. Conventional 2D lane detection from a monocular image yields poor performa…
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
Kehong Gong, Bingbing Li, Jianfeng Zhang +5
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior…
Point2Seq: Detecting 3D Objects as Sequences
Yujing Xue, Jiageng Mao, Minzhe Niu +5
We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. In contrast to previous methods that normally {predict attributes of 3D obj…