no code implementations • 9 Feb 2024 • Yukun Huang, Yixin Liu, Raghuveer Thirukovalluru, Arman Cohan, Bhuwan Dhingra
Addressing this gap, we introduce a unified calibration framework, in which both the correctness of the LLMs' responses and their associated confidence levels are treated as distributions across a range of scores.
no code implementations • 6 Dec 2023 • Yunhan Yang, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Song-Hai Zhang, Hengshuang Zhao, Tong He, Xihui Liu
However, due to the lack of information from multiple views, these works encounter difficulties in generating controllable novel views.
no code implementations • 17 Oct 2023 • Matthew Toles, Yukun Huang, Zhou Yu, Luis Gravano
Here we present a definition and framework for natural language pragmatic asking of clarifying questions (PACQ), the problem of generating questions that result in answers useful for a reasoning task.
no code implementations • 16 Oct 2023 • Yukai Shi, Jianan Wang, He Cao, Boshi Tang, Xianbiao Qi, Tianyu Yang, Yukun Huang, Shilong Liu, Lei Zhang, Heung-Yeung Shum
In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image.
no code implementations • 21 Jun 2023 • Yukun Huang, Jianan Wang, Yukai Shi, Boshi Tang, Xianbiao Qi, Lei Zhang
Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled 3D content creation by optimizing a randomly initialized differentiable 3D representation with score distillation.
no code implementations • CVPR 2023 • Chengzhi Cao, Xueyang Fu, Hongjian Liu, Yukun Huang, Kunyu Wang, Jiebo Luo, Zheng-Jun Zha
Video-based person re-identification (Re-ID) is a prominent computer vision topic due to its wide range of video surveillance applications.
Representation Learning Video-Based Person Re-Identification
no code implementations • CVPR 2023 • Kunyu Wang, Xueyang Fu, Yukun Huang, Chengzhi Cao, Gege Shi, Zheng-Jun Zha
This loss enables the network to concentrate on extracting domain-invariant spectrum and domain-specific spectrum, so as to achieve better disentangling results.
no code implementations • 20 Dec 2022 • Yukun Huang, Yanda Chen, Zhou Yu, Kathleen McKeown
We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models.
no code implementations • CVPR 2023 • Ruili Feng, Kecheng Zheng, Kai Zhu, Yujun Shen, Jian Zhao, Yukun Huang, Deli Zhao, Jingren Zhou, Michael Jordan, Zheng-Jun Zha
Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others.
1 code implementation • 16 Sep 2022 • Jia Zhang, Yukun Huang, Zheng Zhang, Yuhang Shi
There has been growing research interest in using deep learning based method to achieve fully automated segmentation of lesion in Positron emission tomography computed tomography(PET CT) scans for the prognosis of various cancers.
no code implementations • 13 Jun 2022 • Ruili Feng, Kecheng Zheng, Yukun Huang, Deli Zhao, Michael Jordan, Zheng-Jun Zha
By virtue of our numerical tools, we provide the first empirical analysis of the per-layer behavior of network rank in practical settings, i. e., ResNets, deep MLPs, and Transformers on ImageNet.
no code implementations • 25 May 2022 • Yukun Huang, Kun Qian, Zhou Yu
So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data.
no code implementations • 28 Oct 2021 • Congqing He, Jie Zhang, Xiangyu Zhu, Huan Liu, Yukun Huang
To this end, we introduce a fresh perspective to revisit the relational event-cause extraction task and propose a novel sequence tagging framework, instead of extracting event types and events-causes separately.
no code implementations • ICCV 2021 • Yukun Huang, Xueyang Fu, Zheng-Jun Zha
In unconstrained real-world surveillance scenarios, person re-identification (Re-ID) models usually suffer from different low-level perceptual variations, e. g., cross-resolution and insufficient lighting.
no code implementations • CVPR 2020 • Yukun Huang, Zheng-Jun Zha, Xueyang Fu, Richang Hong, Liang Li
Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e. g., low-resolution, weak illumination, blurring and adverse weather.