14 papers
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
Shiyu Ji, Yixuan Wang, Yijun Liu +2
The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compress…
Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction
Haresh Rengaraj Rajamohan, Xiang Gao, Weicheng Zhu +10
While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present R…
ProxyAttn: Guided Sparse Attention via Representative Heads
Yixuan Wang, Huang He, Siqi Bao +4
The quadratic complexity of attention mechanisms limits the efficiency of Large Language Models (LLMs) on long-text tasks. Recently, methods that dynamically estimate block importa…
Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling
Shiyu Ji, Yixuan Wang, Yijun Liu +2
Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token con…
Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
Yijun Liu, Yixuan Wang, Yuzhuang Xu +4
Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the seque…
CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
Yuzhuang Xu, Xu Han, Yuanchi Zhang +5
Large Language Models (LLMs) with Mixture-of-Experts (MoE) architectures are distinguished by their strong performance scaling with increasing parameters across a wide range of tas…