Fan Yang

72

Papers

502

Total Citations

Papers (72)

Cascade Graph Neural Networks for RGB-D Salient Object Detection

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Selective inference for group-sparse linear models

NeurIPS 2016arXiv

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

Differentiable Learning of Logical Rules for Knowledge Base Reasoning

NeurIPS 2017arXiv

Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver

MagicArticulate: Make Your 3D Models Articulation-Ready

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems

Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

TVE: Learning Meta-attribution for Transferable Vision Explainer

Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning

Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers

Object-Aware Dense Semantic Correspondence

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals

LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking

Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph Convolution

Which Is Plagiarism: Fashion Image Retrieval Based on Regional Representation for Design Protection

Probabilistic Model Distillation for Semantic Correspondence

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Towards Compact CNNs via Collaborative Compression

Mutual Graph Learning for Camouflaged Object Detection

CT-Net: Complementary Transfering Network for Garment Transfer With Arbitrary Geometric Changes

Learning Optical Flow With Kernel Patch Attention

Class-Aware Contrastive Semi-Supervised Learning

SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification

UniVIP: A Unified Framework for Self-Supervised Visual Pre-Training

PyPose: A Library for Robot Learning With Physics-Based Optimization

Multi-Task Learning With Low Rank Attribute Embedding for Person Re-Identification

Clustered Object Detection in Aerial Images

RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting

GAFlow: Incorporating Gaussian Attention into Optical Flow

AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts

Towards Fast, Accurate and Stable 3D Dense Face Alignment

PAMS: Quantized Super-Resolution via Parameterized Max Scale

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation

Detecting Generated Images by Real Images

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Good Semi-supervised Learning That Requires a Bad GAN

NeurIPS 2017arXiv

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection

MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification

Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring

The Source Image is the Best Attention for Infrared and Visible Image Fusion

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations

3DHumanEdit: Multi-modal Body Part-aware Conditioning Information Integration for 3D Human Manipulation

An Effective Augmented Lagrangian Method for Fine-Grained Multi-View Optimization

Implicit Modeling of Non-rigid Objects with Cross-Category Signals

Multi-Modal Disordered Representation Learning Network for Description-Based Person Search

Sparse Bayesian Deep Learning for Cross Domain Medical Image Reconstruction

Causal-Driven Skill Prerequisite Structure Discovery

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Game Design for Eliciting Distinguishable Behavior

Bayesian Multi-type Mean Field Multi-agent Imitation Learning

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

MST: Masked Self-Supervised Transformer for Visual Representation

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration

Forecasting Human Trajectory from Scene History

UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup

NeurIPS 2022arXiv

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Model-enhanced Vector Index

Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design