Zheng Wang

50

Papers

126

Total Citations

Papers (50)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Contributing Dimension Structure of Deep Feature for Coreset Selection

ProtCLIP: Function-Informed Protein Multi-Modal Learning

VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence

You Think, You ACT: The New Task of Arbitrary Text to Motion Generation

Rethinking Cancer Gene Identification Through Graph Anomaly Analysis

NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval

The Parables of the Mustard Seed and the Yeast: Extremely Low-Budget, High-Performance Nighttime Semantic Segmentation

TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification

Language Pre-training Guided Masking Representation Learning for Time Series Classification

Balancing Privacy and Performance: A Many-in-One Approach for Image Anonymization

Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks

Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer

PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation

Bi-Causal: Group Activity Recognition via Bidirectional Causality

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement

Ensemble Diversity Facilitates Adversarial Transferability

IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

A3S: A General Active Clustering Method with Pairwise Constraints

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

Universal Weighting Metric Learning for Cross-Modal Matching

Image Inpainting Guided by Coherence Priors of Semantics and Textures

Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning

Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding

Balanced Contrastive Learning for Long-Tailed Visual Recognition

Multilateral Semantic Relations Modeling for Image Text Retrieval

Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification

Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes

DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

Context-Enhanced Stereo Transformer

Colorization for In Situ Marine Plankton Images

Prototypical Residual Networks for Anomaly Detection and Localization

Anomize: Better Open Vocabulary Video Anomaly Detection

Federated Learning with Domain Shift Eraser

ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector

CCIN: Compositional Conflict Identification and Neutralization for Composed Image Retrieval

Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

Cross-Category Subjectivity Generalization for Style-Adaptive Sketch Re-ID

BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning

Self-Adaptable Point Processes with Nonparametric Time Decays

Infinite-Fidelity Coregionalization for Physical Simulation

Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes

Streaming Factor Trajectory Learning for Temporal Tensor Decomposition