5 papers
YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family
Xu Lin, WenJie Nie, Jinlong Peng +4
Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous operators and detection-specif…
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models
Jinsen Su, Yongdong Luo, Yuexiao Ma +3
Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often b…
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
Wanqi Yang, Yuexiao Ma, Alexander Conzelmann +4
Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in me…
Flow caching for autoregressive video generation
Yuexiao Ma, Xuzhe Zheng, Jing Xu +9
Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. Howeve…
Polybasic Speculative Decoding Through a Theoretical Perspective
Ruilin Wang, Huixia Li, Yuexiao Ma +4
Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in acceler…