Tianyi Zhang

22 papers A* 6A 1Journal 12Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float.
CoRR
Tianyi Zhang, Yang Sui, Shaochen Zhong, Vipin Chaudhary, Xia Hu, Anshumali Shrivastava
2025 — conf
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems.
ACL (Findings)
Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
2025 J jnl
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems.
CoRR
Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
2025 J jnl
I3S: Importance Sampling Subspace Selection for Low-Rank Optimization in LLM Pretraining.
CoRR
Haochen Zhang, Junze Yin, Guanchu Wang, Zirui Liu, Tianyi Zhang, Anshumali Shrivastava, Lin Yang, Vladimir Braverman
2025 — conf
IDentity with Locality: An Ideal Hash for Gene Sequence Search.
KDD (1)
Tianyi Zhang, Gaurav Gupta, Aditya Desai, Anshumali Shrivastava
2025 A* conf
LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid.
ICLR
Tianyi Zhang, Anshumali Shrivastava
2025 A* conf
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation.
ICML
Tianyi Zhang, Junda Su, Aditya Desai, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava
2025 J jnl
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.
CoRR
Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, Andrew Wen, Shaochen Zhong, Hanjie Chen, Xia Ben Hu
2025 J jnl
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.
Trans. Mach. Learn. Res.
Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, Andrew Wen, Shaochen Zhong, Na Zou, Hanjie Chen, Xia Hu
2025 J jnl
To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration.
CoRR
Zeyu Yang, Tianyi Zhang, Jianwen Xie, Chuan Li, Zhaozhuo Xu, Anshumali Shrivastava
2024 J jnl
IDentity with Locality: An ideal hash for gene sequence search.
CoRR
Aditya Desai, Gaurav Gupta, Tianyi Zhang, Anshumali Shrivastava
2024 A* conf
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization.
NeurIPS
Tianyi Zhang, Jonah Yi, Zhaozhuo Xu, Anshumali Shrivastava
2024 J jnl
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization.
CoRR
Tianyi Zhang, Jonah Yi, Zhaozhuo Xu, Anshumali Shrivastava
2024 J jnl
LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid.
CoRR
Tianyi Zhang, Anshumali Shrivastava
2024 A* conf
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures.
WWW
Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, Anshumali Shrivastava
2024 A* conf
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention.
NeurIPS
Tianyi Zhang, Jonah Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava
2024 J jnl
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention.
CoRR
Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava
2024 J jnl
SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching.
CoRR
Tianyi Zhang, Junda Su, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava
2023 A conf
Graph Self-supervised Learning via Proximity Distribution Minimization.
UAI
Tianyi Zhang, Zhenwei Dai, Zhaozhuo Xu, Anshumali Shrivastava
2023 J jnl
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures.
CoRR
Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, Anshumali Shrivastava
2022 A* conf
Retaining Knowledge for Learning with Dynamic Definition.
NeurIPS
Zichang Liu, Benjamin Coleman, Tianyi Zhang, Anshumali Shrivastava
2022 — conf
Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification.
EMNLP (Findings)
Tianyi Zhang, Zhaozhuo Xu, Tharun Medini, Anshumali Shrivastava