48 citations · 212 across the 29 of their papers we have counts for
30 papers
AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?
Haotian Luo, Haoyu Wang, Zeyu Qin +5
Recent gains in language model capability have come more from data than from architecture. Frontier labs and data companies produce verifiable agentic tasks, which supervised finet…
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Senqiao Yang, Chengyao Wang, Yuxin Chen +13
Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodie…
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Senqiao Yang, Yukang Chen, Zhuotao Tian +4
Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raisin…
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models
Longxiang Tang, Zhuotao Tian, Kai Li +5
This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes va…
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Xin Lai, Zhuotao Tian, Yukang Chen +3
Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the cor…
Scalable Language Model with Generalized Continual Learning
Bohao Peng, Zhuotao Tian, Shu Liu +2
Continual learning has gained increasing importance as it facilitates the acquisition and refinement of scalable knowledge and skills in language models. However, existing methods…
Unified Language-driven Zero-shot Domain Adaptation
Senqiao Yang, Zhuotao Tian, Li Jiang +1
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explic…
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
Bohao Peng, Xiaoyang Wu, Li Jiang +4
The booming of 3D recognition in the 2020s began with the introduction of point cloud transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models, especia…
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
Chengyao Wang, Li Jiang, Xiaoyang Wu +4
Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as t…
LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
Senqiao Yang, Tianyuan Qu, Xin Lai +4
While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish differen…
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
Zhenhua Ning, Zhuotao Tian, Guangming Lu +1
Although extensive research has been conducted on 3D point cloud segmentation, effectively adapting generic models to novel categories remains a formidable challenge. This paper pr…
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
Xiaoyang Wu, Zhuotao Tian, Xin Wen +4
The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep l…
LISA: Reasoning Segmentation via Large Language Model
Xin Lai, Zhuotao Tian, Yukang Chen +4
Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target object…
Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract
Bohao Peng, Zhuotao Tian, Xiaoyang Wu +4
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic featu…
Decoupled Kullback-Leibler Divergence Loss
Jiequan Cui, Zhuotao Tian, Zhisheng Zhong +3
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss…
Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Bohao Peng, Zhuotao Tian, Xiaoyang Wu +4
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic featu…
Learning Context-aware Classifier for Semantic Segmentation
Zhuotao Tian, Jiequan Cui, Li Jiang +5
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature dist…
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
Jianhui Liu, Yukang Chen, Xiaoqing Ye +3
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyz…
Generalized Parametric Contrastive Learning
Jiequan Cui, Zhisheng Zhong, Zhuotao Tian +3
In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we obse…
Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions
Dong Zhang, Yi Lin, Hao Chen +4
Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg).…
DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
Xin Lai, Zhuotao Tian, Xiaogang Xu +5
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset…
Region Rebalance for Long-Tailed Semantic Segmentation
Jiequan Cui, Yuhui Yuan, Zhisheng Zhong +4
In this paper, we study the problem of class imbalance in semantic segmentation. We first investigate and identify the main challenges of addressing this issue through pixel rebala…
SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment
Yixin Chen, Zhuotao Tian, Pengguang Chen +2
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them. We address the pixel-level i…
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
Li Jiang, Shaoshuai Shi, Zhuotao Tian +4
Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the hig…