Xinghao Chen

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking

PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models

OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs

Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing

An Empirical Study of Extremely Low-Bit Quantization for Large Language Models

Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting

RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

SlimLLM: Accurate Structured Pruning for Large Language Models

DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding

Empirical Study on Enhancing Efficiency in Masked Image Modeling Pre-training

GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video