Tianhua Xia

According to our database, Tianhua Xia authored at least 7 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding.

Yunhai Hu, Tianhua Xia, Zining Liu, Rahul Raman, Xingyu Liu, Bo Bao, Eric Sather, Vithursan Thangarasa, Sai Qian Zhang

CoRR, May, 2025

Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference.

Patrick Yubeaton, Tareq Mahmoud, Shehab Naga, Pooria Taheri, Tianhua Xia, Arun George, Yasmein Khalil, Sai Qian Zhang, Siddharth Joshi, Chinmay Hegde, Siddharth Garg

CoRR, February, 2025

HAAN: A Holistic Approach for Accelerating Normalization Operations in Large Language Models.

Tianfan Peng, Tianhua Xia, Jiajun Qin, Sai Qian Zhang

Proceedings of the Design, Automation & Test in Europe Conference, 2025

Foveated Instance Segmentation.

Hongyi Zeng, Wenxuan Liu, Tianhua Xia, Jinhui Chen, Ziyun Li, Sai Qian Zhang

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

PICACHU: Plug-In CGRA Handling Upcoming Nonlinear Operations in LLMs.

Jiajun Qin, Tianhua Xia, Cheng Tan, Jeff Zhang, Sai Qian Zhang

Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2025

2024

Hyft: A Reconfigurable Softmax Accelerator with Hybrid Numeric Format for both Training and Inference.

Tianhua Xia, Sai Qian Zhang

Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design, 2024

2023

Softmax Acceleration with Adaptive Numeric Format for both Training and Inference.

Tianhua Xia, Sai Qian Zhang

CoRR, 2023