papers

Publications (61)

cs.SE2025

Toward building next-generation Geocoding systems: a systematic review

Zhengcong Yin, Daniel W. Goldberg, Binbin Lin +11

Geocoding systems are widely used in both scientific research for spatial analysis and everyday life through location-based services. The quality of geocoded data significantly imp…

cs.CV2025

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

Zhanwei Zhang, Kaiyuan Liu, Junjie Liu +5

Local geometry-controllable computer-aided design (CAD) generation aims to modify local parts of CAD models automatically, enhancing design efficiency. It also ensures that the sha…

cs.CV2023

CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

Wenxiao Wang, Wei Chen, Qibo Qiu +5

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first pro…

cs.CV2022

Towards In-distribution Compatibility in Out-of-distribution Detection

Boxi Wu, Jie Jiang, Haidong Ren +7

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. T…

cs.DC2026

NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding

Jiefei Chen, Binbin Lin, Jinming Ma +9

Modern serving systems for Mixture-of-Experts (MoE) models adopt hybrid data-expert parallelism: expert parallelism (EP) shards experts across GPUs to scale capacity, while data pa…

stat.AP2023

Statistical Machine Learning Meets High-Dimensional Spatiotemporal Challenges -- A Case Study of COVID-19 Modeling

Binbin Lin, Yimin Dai, Lei Zou +1

Diverse non-pharmacological interventions (NPIs), serving as the primary approach for COVID-19 control prior to pharmaceutical interventions, showed heterogeneous spatiotemporal ef…

cs.CV2023

General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Liang Xie, Yibo Yang, Wenxiao Wang +4

Compared to 2D images, 3D point clouds are much more sensitive to rotations. We expect the point features describing certain patterns to keep invariant to the rotation transformati…

cs.CV2023

Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation

Ping Li, Junjie Chen, Binbin Lin +1

Semantic segmentation plays an important role in widespread applications such as autonomous driving and robotic sensing. Traditional methods mostly use RGB images which are heavily…

cs.LG2014

Stochastic Coordinate Coding and Its Application for Drosophila Gene Expression Pattern Annotation

Binbin Lin, Qingyang Li, Qian Sun +4

\textit{Drosophila melanogaster} has been established as a model organism for investigating the fundamental principles of developmental gene interactions. The gene expression patte…

cs.AI2026

Balancing multiscale similarity and cartographic constraints: A similarity-driven optimization framework for line generalization

Pengbo Li, Haowen Yan, Xiaomin Lu +1

Cartographic generalization is essential for generating multiscale map representations by balancing information preservation and cartographic readability. However, automated genera…

cs.CL2024

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control

Yuxin Xiao, Chaoqun Wan, Yonggang Zhang +5

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become…

cs.CV2023

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training

Yuqi Lin, Minghao Chen, Kaipeng Zhang +7

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to captur…

physics.app-ph2020

Mapping Humidity-dependent Mechanical Properties of a Single Cellulose Fibre

Julia Auernhammer, Tom Keil, Binbin Lin +4

Modelling of single cellulose fibres is usually performed by assuming homogenous properties, such as strength and Young s modulus, for the whole fibre. Additionally, the inhomogene…

cs.LG2012

A Simple Algorithm for Semi-supervised Learning with Improved Generalization Error Bound

Ming Ji, Tianbao Yang, Binbin Lin +2

In this work, we develop a simple algorithm for semi-supervised regression. The key idea is to use the top eigenfunctions of integral operator derived from both labeled and unlabel…

cs.CL2025

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Wei Chen, Zhen Huang, Liang Xie +9

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend t…

cs.CL2024

Model Compression and Efficient Inference for Large Language Models: A Survey

Wenxiao Wang, Wei Chen, Yicong Luo +6

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it chal…

cs.CV2023

NormKD: Normalized Logits for Knowledge Distillation

Zhihao Chi, Tu Zheng, Hengjia Li +4

Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potenti…

cs.LG2026

From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers

Binbin Lin, Wei Chen, Yalun Li +3

Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood. We view a token sequence as a vector field over th…

cs.CV2024

OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Chenxi Huang, Tong He, Haidong Ren +3

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap betw…

cs.LG2025

CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

Mengsong Wu, YaFei Wang, Yidong Ming +7

Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the diffic…

cs.LG2025

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

Yuxiang Zhang, Zhengxu Yu, Weihang Pan +5

Emerging reasoning LLMs such as OpenAI-o1 and DeepSeek-R1 have achieved strong performance on complex reasoning tasks by generating long chain-of-thought (CoT) traces. However, the…

cs.CV2024

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

Yanting Yang, Minghao Chen, Qibo Qiu +5

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and plan…

cs.LG2024

SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

Weigang Lu, Yibing Zhan, Binbin Lin +6

Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing…

cs.LG2026

Predicting Healthcare System Visitation Flow by Integrating Hospital Attributes and Population Socioeconomics with Human Mobility Data

Binbin Lin, Lei Zou, Hao Tian +3

Healthcare visitation patterns are influenced by a complex interplay of hospital attributes, population socioeconomics, and spatial factors. However, existing research often adopts…

cs.CV2023

GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds

Honghui Yang, Tong He, Jiaheng Liu +5

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging du…

physics.soc-ph2021

Revealing the Global Linguistic and Geographical Disparities of Public Awareness to Covid-19 Outbreak through Social Media

Binbin Lin, Lei Zou, Nick Duffield +7

The Covid-19 has presented an unprecedented challenge to public health worldwide. However, residents in different countries showed diverse levels of Covid-19 awareness during the o…

cs.CV2023

One-shot Implicit Animatable Avatars with Model-based Priors

Yangyi Huang, Hongwei Yi, Weiyang Liu +6

Existing neural rendering methods for creating human avatars typically either require dense input signals such as video or multi-view images, or leverage a learned prior from large…

cs.LG2014

Geodesic Distance Function Learning via Heat Flow on Vector Fields

Binbin Lin, Ji Yang, Xiaofei He +1

Learning a distance function or metric on a given data manifold is of great importance in machine learning and pattern recognition. Many of the previous works first embed the manif…

cs.CV2024

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

Zhanwei Zhang, Minghao Chen, Shuai Xiao +7

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels,…

cs.CV2025

Hyperlocal disaster damage assessment using bi-temporal street-view imagery and pre-trained vision models

Yifan Yang, Lei Zou, Bing Zhou +4

Street-view images offer unique advantages for disaster damage estimation as they capture impacts from a visual perspective and provide detailed, on-the-ground insights. Despite se…

cs.CV2021

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

Wenxiao Wang, Lu Yao, Long Chen +4

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among…

physics.data-an2021

A deep learned nanowire segmentation model using synthetic data augmentation

Binbin Lin, Nima Emami, David A Santos +3

Automatized object identification and feature analysis of experimental image data are indispensable for data-driven material science; deep-learning-based segmentation algorithms ha…

cs.CV2023

APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding

Hengjia Li, Tu Zheng, Zhihao Chi +5

Transformer-based networks have achieved impressive performance in 3D point cloud understanding. However, most of them concentrate on aggregating local features, but neglect to dir…

cond-mat.mtrl-sci2025

Deep learning-enabled large-scale analysis of particle geometry-lithiation correlations in battery cathode materials

Binbin Lin, Luis J. Carrillo, Xiang-Long Peng +4

A deep learning model is employed to address the challenging problem of V2O5 nanoparticle segmentation and the correlation between the chemical composition and the geometrical feat…

physics.comp-ph2021

Humidity Influence on Mechanics and Failure of Paper Materials: Joint Numerical and Experimental Study on Fiber and Fiber Network Scale

Binbin Lin, Julia Auernhammer, Jan-Lukas Schäfer +4

Paper materials are natural composite materials and well-known to be hydrophilic unless chemical and mechanical processing treatments are undertaken. The relative humidity impacts…

physics.soc-ph2024

Understanding Human-COVID-19 Dynamics using Geospatial Big Data: A Systematic Literature Review

Binbin Lin, Lei Zou, Mingzheng Yang +5

The COVID-19 pandemic has changed human life. To mitigate the pandemic's impacts, different regions implemented various policies to contain COVID-19 and residents showed diverse re…

cs.CV2026

PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet

Xiaopei Wu, Chenshu Hou, Liang Peng +9

3D dense captioning, an emerging vision-language task, aims to generate descriptive sentences for each object in the 3D scene. Despite the impressive results achieved by previous m…

cs.CV2023

A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation

Minghao Chen, Zepeng Gao, Shuai Zhao +4

Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set…

cs.CL2024

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?

Zhengkai Lin, Zhihang Fu, Kai Liu +6

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the r…

cs.AI2024

AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning

Minghao Chen, Yihang Li, Yanting Yang +3

Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agent…

cs.CV2024

G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction

Zhanwei Zhang, Zishuo Hua, Minghao Chen +4

Predicting future trajectories of traffic agents accurately holds substantial importance in various applications such as autonomous driving. Previous methods commonly infer all fut…

cs.CV2024

NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection

Chenxi Huang, Yuenan Hou, Weicai Ye +5

NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by innovatively utilizing NeRF to enhance representation learning. Despite its notable performance, w…

cs.CV2023

PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer

Honghui Yang, Wenxiao Wang, Minghao Chen +5

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling whil…

cs.CL2025

Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration

Yong Wu, Weihang Pan, Ke Li +3

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mis…

cond-mat.mtrl-sci2024

What can machine learning help with microstructure-informed materials modeling and design?

Xiang-Long Peng, Mozhdeh Fathidoost, Binbin Lin +2

Machine learning techniques have been widely employed as effective tools in addressing various engineering challenges in recent years, particularly for the challenging task of micr…

cs.LG2023

Neural Collapse Inspired Federated Learning with Non-iid Data

Chenxi Huang, Liang Xie, Yibo Yang +3

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant diff…

cs.CV2023

CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Yuqi Lin, Minghao Chen, Wenxiao Wang +5

Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training cos…

cs.CV2025

Enhancing Spatial Reasoning through Visual and Textual Thinking

Xun Liang, Xin Guo, Zhongming Jin +5

The spatial reasoning task aims to reason about the spatial relationships in 2D and 3D space, which is a fundamental capability for Visual Question Answering (VQA) and robotics. Al…

cs.CL2025

SciPIP: An LLM-based Scientific Paper Idea Proposer

Wenxiao Wang, Lihui Gu, Liye Zhang +7

The rapid advancement of large language models (LLMs) has opened new possibilities for automating the proposal of innovative scientific ideas. This process involves two key phases:…

cs.DS2017

Distributed rank-1 dictionary learning: Towards fast and scalable solutions for fMRI big data analytics

Milad Makkie, Xiang Li, Binbin Lin +4

The use of functional brain imaging for research and diagnosis has benefitted greatly from the recent advancements in neuroimaging technologies, as well as the explosive growth in…

cs.CL2025

InsQABench: Benchmarking Chinese Insurance Domain Question Answering with Large Language Models

Jing Ding, Kai Feng, Binbin Lin +6

The application of large language models (LLMs) has achieved remarkable success in various fields, but their effectiveness in specialized domains like the Chinese insurance industr…

cs.CV2024

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Xiaopei Wu, Liang Peng, Liang Xie +6

Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to g…

cs.CV2023

Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation

Ping Li, Yu Zhang, Li Yuan +3

Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not…

cs.CV2022

Boosting Semi-Supervised 3D Object Detection with Semi-Sampling

Xiaopei Wu, Yang Zhao, Liang Peng +6

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D obj…

cs.CV2025

Depth Any Video with Scalable Synthetic Data

Honghui Yang, Di Huang, Wei Yin +6

Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introd…

cs.LG2017

Efficient Approximate Solutions to Mutual Information Based Global Feature Selection

Hemanth Venkateswara, Prasanth Lade, Binbin Lin +2

Mutual Information (MI) is often used for feature selection when developing classifier models. Estimating the MI for a subset of features is often intractable. We demonstrate, that…

cs.CV2024

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Xiaopei Wu, Yuenan Hou, Xiaoshui Huang +8

Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity p…

cs.LG2026

SPAR: Support-Preserving Action Rectification

Jiaxin Zhao, Weihang Pan, Xun Liang +1

Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from ove…

cs.CV2024

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

Honghui Yang, Sha Zhang, Di Huang +9

In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pre-training methods have shown w…

cs.CL2025

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning

Chenxi Huang, Shaotian Yan, Liang Xie +6

Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for significantly improving parameter effic…

cs.CV2026

Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation

Xiaopei Wu, Yuenan Hou, Junkai Xu +7

Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely…