1 citations · 1 across the 2 of their papers we have counts for
6 papers
Context Memorization for Efficient Long Context Generation
Yasuyuki Okoshi, Hao Mark Chen, Guanxi Lu +3
Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effe…
AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization
Kosuke Matsushima, Yasuyuki Okoshi, Masato Motomura +1
Processing-in-Memory (PIM) architectures offer a promising solution to the memory bottlenecks in data-intensive machine learning, yet often overlook the growing challenge of activa…
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi +3
The strong lottery ticket hypothesis (SLTH) conjectures that high-performing subnetworks, called strong lottery tickets (SLTs), are hidden in randomly initialized neural networks.…
Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
Hao Mark Chen, Guanxi Lu, Yasuyuki Okoshi +3
Test-time scaling (TTS) has proven effective in enhancing the reasoning capabilities of large language models (LLMs). Verification plays a key role in TTS, simultaneously influenci…
Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression
Kyo Kuroki, Yasuyuki Okoshi, Thiem Van Chu +2
This paper proposes a novel matrix quantization method, Binary Quadratic Quantization (BQQ). In contrast to conventional first-order quantization approaches, such as uniform quanti…
Partially Frozen Random Networks Contain Compact Strong Lottery Tickets
Hikari Otsuka, Daiki Chijiwa, Ãngel López GarcÃa-Arias +6
Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstr…