Get started
Author

Xiaoyang Qu

Observed name: Qu, Xiaoyang
Institution: Ping An (China)
Observed institution: Ping An (China)
OpenAlex ID: A5121938089
FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models
2026 · Han, Yuchen, Wu, Jianhan, et al. · arXiv (Cornell University)
PDF
ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification
2026 · Wang, Jianzong, Liu, Chuhang, et al. · arXiv (Cornell University)
PDF
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
2026 · Association for Computational Linguistics 2026, Li, Yuechan, et al. · Underline Science Inc.
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
2026 · Lu, Renjie, Zhang, Xulong, et al. · arXiv (Cornell University)
PDF
WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
2026 · Tao, Wei, Qu, Xiaoyang, et al. · arXiv (Cornell University)
PDF
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
2026 · Shi, Jiaqi, Li, Yuechan, et al. · arXiv (Cornell University)
PDF
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
2026 · Minghui Zheng, Hongxu Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
2026 · Jiaqi Shi, Xulong Zhang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
Works count: 8
Citation count:
H-index:
I10-index:
Year
Topic
Type