Keze Wang

Affiliations

University of California, Los Angeles

papers

201

total citations

papers (13)

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

ICML 2025arXiv

citations

Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation

AAAI 2024arXiv

citations

Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body

CVPR 2025arXiv

citations

Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models

AAAI 2024

citations

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

CVPR 2025

citations

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

NEURIPS 2025arXiv

citations

6402 NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

AAAI 2024

citations

Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering

ICCV 2021

citations

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

NEURIPS 2025arXiv

citations

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

AAAI 2025arXiv

citations

Keze Wang

Affiliations

papers (13)

Solving Inefficiency of Self-Supervised Representation Learning

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

MAT-Agent: Adaptive Multi-Agent Training Optimization

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation

Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body

Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

6402 NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

papers (13)

Solving Inefficiency of Self-Supervised Representation Learning

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

MAT-Agent: Adaptive Multi-Agent Training Optimization

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation

Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body

Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

6402 NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks