Chaoyi Jiang

11 papers A 1Misc 1Journal 7Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	Balancing Fairness Among User Groups in Happiness Maximization Queries. WISA Jie Dong, Chaoyi Jiang, Conghao Liu, Teng Teng
2025	J	`jnl`	DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding. CoRR Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang, Murali Annavaram
2025	J	`jnl`	DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning. CoRR Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang, Murali Annavarm
2025	J	`jnl`	DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing. CoRR Lei Gao, Chaoyi Jiang, Hossein Entezari Zarch, Daniel Wong, Murali Annavaram
2025	—	`conf`	Efficient Processing of Dynamic Rank-Happiness Maximization Queries. APWeb-WAIM (2) Chaoyi Jiang, Jiping Zheng
2025	—	`conf`	KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation. ACL (Findings) Chaoyi Jiang, Lei Gao, Hossein Entezari Zarch, Murali Annavaram
2025	A	`conf`	LEAF: Lightweight, Efficient, Adaptive and Flexible Embedding for Large-Scale Recommendation Models. RecSys Chaoyi Jiang, Abdulla Alshabanah, Murali Annavaram
2025	J	`jnl`	MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention. CoRR Chaoyi Jiang, Sungwoo Kim, Lei Gao, Hossein Entezari Zarch, Won Woo Ro, Murali Annavaram
2025	J	`jnl`	Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding. CoRR Arun Ramachandran, Ramaswamy Govindarajan, Murali Annavaram, Prakash Sathyanath Raghavendra, Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang
2024	J	`jnl`	CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data. CoRR Hossein Entezari Zarch, Abdulla Alshabanah, Chaoyi Jiang, Murali Annavaram
2024	J	`jnl`	Efficient LLM Inference with I/O-Aware Partial KV Cache Recomputation. CoRR Chaoyi Jiang, Lei Gao, Hossein Entezari Zarch, Murali Annavaram