Neha Prakriya

12 papers A* 3Journal 6Unranked 3
YearRankTypeTitle / Venue / Authors
2025 A* conf
Dynamic-Width Speculative Beam Decoding for LLM Inference.
AAAI
Zongyue Qin, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun
2025 — conf
HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing.
NAACL (Long Papers)
Zifan He, Yingqi Cao, Zongyue Qin, Neha Prakriya, Yizhou Sun, Jason Cong
2025 J jnl
LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning.
CoRR
Neha Prakriya, Zijian Ding, Yizhou Sun, Jason Cong
2025 A* conf
Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference.
ICLR
Zongyue Qin, Ziniu Hu, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun
2024 J jnl
Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review.
CoRR
Neha Prakriya, Jui-Nan Yen, Cho-Jui Hsieh, Jason Cong
2024 J jnl
Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference.
CoRR
Zongyue Qin, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun
2024 J jnl
HMT: Hierarchical Memory Transformer for Long Context Language Processing.
CoRR
Zifan He, Zongyue Qin, Neha Prakriya, Yizhou Sun, Jason Cong
2024 J jnl
Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference.
CoRR
Zongyue Qin, Ziniu Hu, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun
2024 A* conf
SpectraFlux: Harnessing the Flow of Multi-FPGA in Mass Spectrometry Clustering.
DAC
Tianqi Zhang, Neha Prakriya, Sumukh Pinge, Jason Cong, Tajana Rosing
2024 — conf
TAPA-CS: Enabling Scalable Accelerator Design on Distributed HBM-FPGAs.
ASPLOS (3)
Neha Prakriya, Yuze Chi, Suhail Basalama, Linghao Song, Jason Cong
2023 — conf
NeSSA: Near-Storage Data Selection for Accelerated Machine Learning Training.
HotStorage
Neha Prakriya, Yu Yang, Baharan Mirzasoleiman, Cho-Jui Hsieh, Jason Cong
2023 J jnl
TAPA-CS: Enabling Scalable Accelerator Design on Distributed HBM-FPGAs.
CoRR
Neha Prakriya, Yuze Chi, Suhail Basalama, Linghao Song, Jason Cong