activity
20242026
most citedMLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

cs.AI2026

Einstein World Models

Munachiso Samuel Nwadike, Zangir Iklassov, Ali Mekky +2

Does intelligence require the ability to reason about phenomena beyond direct experience? It is natural to suspect that some complex thought cannot be captured through language alo…

cs.LG2025

Predicting the Order of Upcoming Tokens Improves Language Modeling

Zayd M. K. Zuhri, Erland Hilman Fuadi, Alham Fikri Aji

Multi-token prediction (MTP) has been proposed as an auxiliary objective to improve next-token prediction (NTP) in language model training but shows inconsistent improvements, unde…

cs.LG2025

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax

Zayd M. K. Zuhri, Erland Hilman Fuadi, Alham Fikri Aji

We introduce softpick, a rectified, not sum-to-one, drop-in replacement for softmax in transformer attention mechanisms that eliminates attention sink and massive activations. Our…

cs.LG2025

QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning

Moses Ananta, Muhammad Farid Adilazuarda, Zayd Muhammad Kawakibi Zuhri +2

Fine-tuning large language models (LLMs) is often constrained by the computational costs of processing massive datasets. We propose \textbf{QLESS} (Quantized Low-rank Gradient Simi…

cs.LG2024★ 1 cited

MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding

Zayd Muhammad Kawakibi Zuhri, Muhammad Farid Adilazuarda, Ayu Purwarianti +1

Auto-regressive inference of transformers benefit greatly from Key-Value (KV) caching, but can lead to major memory bottlenecks as model size, batch size, and sequence length grow…