Wei Xue

15

Papers

201

Total Citations

Papers (15)

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection

Delta Decompression for MoE-based LLMs Compression

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology

Importance Weighting Can Help Large Language Models Self-Improve

Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation

AIRA: Activation-Informed Low-Rank Adaptation for Large Models

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

DetKDS: Knowledge Distillation Search for Object Detectors

Towards a Self-contained Data-driven Global Weather Forecasting Framework

MARBLE: Music Audio Representation Benchmark for Universal Evaluation