Xin Wang

105

Papers

820

Total Citations

1

Affiliations

Affiliations

The Ohio State University

Papers (105)

Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks

NeurIPS 2017arXiv

VTimeLLM: Empower LLM to Grasp Video Moments

When Do We Not Need Larger Vision Models?

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

SCALM: Detecting Bad Practices in Smart Contracts Through LLMs

Adversarial Prompt Tuning for Vision-Language Models

$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging

Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation

Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising

Variational Counterfactual Intervention Planning to Achieve Target Outcomes

AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization

AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark

Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision

Preserving Fairness Generalization in Deepfake Detection

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data

A Dual-module Framework for Counterfactual Estimation over Time

CurBench: Curriculum Learning Benchmark

Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet

Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization

Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer

Video Captioning via Hierarchical Reinforcement Learning

MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation

Visual Query Answering by Entity-Attribute Graph Matching and Reasoning

Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Self-Supervised Deep Visual Odometry With Online Adaptation

Learning Saliency Propagation for Semi-Supervised Instance Segmentation

Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments

Online Learning of a Probabilistic and Adaptive Scene Representation

DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Robust Contrastive Learning Against Noisy Views

Unknown-Aware Object Detection: Learning What You Don't Know From Videos in the Wild

You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement

Doubly Right Object Recognition: A Why Prompt for Visual Rationales

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Top-Down Visual Attention From Analysis by Synthesis

CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions

ACE: Adapting to Changing Environments for Semantic Segmentation

Local Supports Global: Deep Camera Relocalization With Sequence Enhancement

Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research

Few-Shot Object Detection via Feature Reweighting

Wanderlust: Online Continual Object Detection in the Real World

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Distilling Holistic Knowledge With Graph Neural Networks

Interpreting Attributions and Interactions of Adversarial Attacks

Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering

HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting

HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World

Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards

Neural-Sim: Learning to Generate Training Data with NeRF

LiDAL: Inter-Frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

Context-Aware Streaming Perception in Dynamic Environments

Exponential Hardness of Optimization from the Locality in Quantum Neural Networks

FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models

From Abyssal Darkness to Blinding Glare: A Benchmark on Extreme Exposure Correction in Real World

TopicGeo: An Efficient Unified Framework for Geolocation

Identity-Text Video Corpus Grounding

ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement

Modular-Cam: Modular Dynamic Camera-view Video Generation with LLM

Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation

Adaptive Dual Guidance Knowledge Distillation

Improving Generalization for AI-Synthesized Voice Detection

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

Set-Valued Sensitivity Analysis of Deep Neural Networks

Data-Augmented Curriculum Graph Neural Architecture Search under Distribution Shifts

Rethinking Propagation for Unsupervised Graph Domain Adaptation

Multimodal Graph Neural Architecture Search under Distribution Shifts

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Graph Differentiable Architecture Search with Structure Learning

Disentangled Contrastive Learning on Graphs

Not All Low-Pass Filters are Robust in Graph Convolutional Networks

Curriculum Disentangled Recommendation with Noisy Multi-feedback

NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search

VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation

Sketching based Representations for Robust Image Classification with Provable Guarantees

Dynamic Graph Neural Networks Under Spatio-Temporal Distribution Shift

Generalization Bounds for Estimating Causal Effects of Continuous Treatments

Learning Invariant Graph Representations for Out-of-Distribution Generalization

Concentration of Data Encoding in Parameterized Quantum Circuits

Power and limitations of single-qubit native quantum neural networks

NeurIPS 2022arXiv

A Theoretical View on Sparsely Activated Networks

Module-Aware Optimization for Auxiliary Learning

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

Joint Data-Task Generation for Auxiliary Learning

Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion

Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks

Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision

Alternating Updates for Efficient Transformers

Disentangled Graph Convolutional Networks

Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization