Jiawei Liu

17

Papers

126

Total Citations

Papers (17)

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation

PurpCode: Reasoning for Safer Code Generation

BearLLM: A Prior Knowledge-Enhanced Bearing Health Management Framework with Unified Vibration Signal Representation

Noise-assisted Prompt Learning for Image Forgery Detection and Localization

View From Above: Orthogonal-View aware Cross-view Localization

Self-Calibrating Vicinal Risk Minimisation for Model Calibration

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

Magicoder: Empowering Code Generation with OSS-Instruct

Hierarchical Knowledge Prompt Tuning for Multi-task Test-Time Adaptation

I2VControl: Disentangled and Unified Video Motion Synthesis Control

HOIMamba: Efficient Mamba-based Disentangled Progressive Learning for HOI Detection

Reducing AUV Energy Consumption Through Dynamic Sensor Directions Switching via Deep Reinforcement Learning

Interweaving Memories of a Siamese Large Language Model

Residual Denoising Diffusion Models