272 citations · 310 across the 16 of their papers we have counts for
16 papers
ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
Zukang Xu, Zhixiong Zhao, Xing Hu +5
Mixture-of-Experts (MoE) architectures provide an efficient paradigm for scaling large language models (LLMs), yet fixed top-k routing activates the same number of expert slots for…
Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
Jun Li, Ziwei Qin
Semi-supervised learning has become a dominant paradigm for reducing annotation costs. However, we argue that the current progress is clouded by a twofold overconfidence problem. A…
DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
Jiazhen Pan, Weixiang Shen, Jun Li +7
Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revise a differential diagnosis,…
Bézier Degradation Modeling for LiDAR-based Human Motion Capture
Xiaoqi An, Lin Zhao, Jun Li +2
LiDAR-based 3D human motion capture has broad applications in fields such as autonomous driving and robotics, where accurate motion reconstruction is crucial. However, existing met…
Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting
Yue Yu, Haibo Chen, Shuo Chen +2
Instilling creativity in text-to-image (T2I) generation presents a significant challenge, as it requires synthesized images to exhibit not only visual novelty and surprise, but als…
CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model
Houji Wen, Jiangyong Yu, Jun Li +1
Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to th…
RMLer: Synthesizing Novel Objects across Diverse Categories via Reinforcement Mixing Learning
Jun Li, Zikun Chen, Haibo Chen +2
Novel object synthesis by integrating distinct textual concepts from diverse categories remains a significant challenge in Text-to-Image (T2I) generation. Existing methods often su…
Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation
Xiaoqi An, Lin Zhao, Chen Gong +2
With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captur…
Novel Object Synthesis via Adaptive Text-Image Harmony
Zeren Xiong, Zedong Zhang, Zikun Chen +5
In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this t…
TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling
Jun Li, Zedong Zhang, Jian Yang
Generating creative combinatorial objects from two seemingly unrelated object texts is a challenging task in text-to-image synthesis, often hindered by a focus on emulating existin…
Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution
Xi Cheng, Jun Li, Qiang Dai +2
Structured illumination microscopy (SIM) is an important super-resolution based microscopy technique that breaks the diffraction limit and enhances optical microscopy systems. With…
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Haobo Jiang, Yaqi Shen, Jin Xie +3
In this paper, by modeling the point cloud registration task as a Markov decision process, we propose an end-to-end deep model embedded with the cross-entropy method (CEM) for unsu…
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Kun Wang, Zhenyu Zhang, Zhiqiang Yan +4
Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and…
RigNet: Repetitive Image Guided Network for Depth Completion
Zhiqiang Yan, Kun Wang, Xiang Li +3
Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent approaches mainly focus o…
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Xiang Li, Wenhai Wang, Xiaolin Hu +3
Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-M…
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Xiang Li, Wenhai Wang, Lijun Wu +5
One-stage detector basically formulates object detection as dense classification and localization. The classification is usually optimized by Focal Loss and the box location is com…