Junchi Yan

Papers

240

Total Citations

Papers (41)

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

ICLR 2024

citations

PointOBB: Learning Oriented Object Detection via Single Point Supervision

CVPR 2024

citations

Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

CVPR 2024

citations

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes

CVPR 2024

citations

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling

AAAI 2024arXiv

citations

Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances

CVPR 2025arXiv

citations

Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning

AAAI 2025

citations

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

CVPR 2024

citations

EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

ICLR 2024

citations

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

ICLR 2025

citations

RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments

CVPR 2025arXiv

citations

Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

ICLR 2025

citations

Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

ICCV 2025

citations

Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

ICLR 2025

citations

QuanONet: Quantum Neural Operator with Application to Differential Equation

ICML 2025

citations

SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs

ICLR 2025

citations

Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction

CVPR 2025

citations

SelKD: Selective Knowledge Distillation via Optimal Transport Perspective

ICLR 2025

citations

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

ICML 2025

citations

ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization

AAAI 2024

citations

Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning

CVPR 2024

citations

Optimal Control Operator Perspective and a Neural Adaptive Spectral Method

AAAI 2025

citations

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

ICCV 2025

citations

Grounding and Enhancing Grid-based Models for Neural Fields

CVPR 2024

citations

GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer

ICCV 2025

citations

Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning

ICCV 2025

citations

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

ICCV 2025

citations

UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection

CVPR 2025

citations

Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters

CVPR 2025

citations

HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs

ICML 2025

citations

Graph Out-of-Distribution Detection Goes Neighborhood Shaping

ICML 2024

citations

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation

ICML 2024

citations

SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification

ICML 2024

citations

OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport

ICML 2024

citations

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness

ICML 2024

citations

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

ICML 2024

citations

On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm

ICML 2024

citations

MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation

ICML 2024

citations

Junchi Yan

Papers (41)

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

PointOBB: Learning Oriented Object Detection via Single Point Supervision

Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling

Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances

Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and Planning

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments

Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

QuanONet: Quantum Neural Operator with Application to Differential Equation

SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs

Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction

SelKD: Selective Knowledge Distillation via Optimal Transport Perspective

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization

Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning

Optimal Control Operator Perspective and a Neural Adaptive Spectral Method

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

Grounding and Enhancing Grid-based Models for Neural Fields

GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer

Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection

Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters

HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs

Graph Out-of-Distribution Detection Goes Neighborhood Shaping

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation

SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification

OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm

MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation

Learning Divergence Fields for Shift-Robust Graph Representations

How Graph Neural Networks Learn: Lessons from Training Dynamics

Double-Bounded Optimal Transport for Advanced Clustering and Classification