collaborators

5 papers

cs.CL2026

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Atharva Naik, Prakam, Yash Mathur +6

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from doma…

cs.LG2025

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

Yuhan Liu, Yihua Cheng, Jiayi Yao +8

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV cach…

cs.DC2025

Strata: Hierarchical Context Caching for Long Context Language Model Serving

Zhiqiang Xie, Ziyi Xu, Mark Zhao +5

Large Language Models (LLMs) with expanding context windows face significant performance hurdles. While caching key-value (KV) states is critical for avoiding redundant computation…

cs.LG2025

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Xinyu Yang, Yuwei An, Hongyi Liu +2

Autoregressive Large Language Models (AR-LLMs) frequently exhibit implicit parallelism in sequential generation. Inspired by this, we introduce Multiverse, a new generative model t…

cs.CL2025

HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse

Yuwei An, Yihua Cheng, Seo Jin Park +1

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the performance of large language models (LLMs) by integrating external knowledge into the gen…