works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

Output-Aware Rotation for INT2 KV-Cache Quantization

Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4

The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important…

cs.LG2026

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

Donghyun Son, Euntae Choi, Sungjoo Yoo

The paper proposes NSNQuant, a calibration‑free method that uses a double normalization and Hadamard transform to compress the key‑value cache of large language models with low‑bit…

cs.LG2026

LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss

Euntae Choi, Sumin Song, Sungjoo Yoo

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight…

cs.CL2026

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models

Minsoo Cheong, Donghyun Son, Woosang Lim +1

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing…

cs.LG2025

Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer

Euntae Choi, Sumin Song, Woosang Lim +1

We propose Rotate, Clip, and Partition (RCP), a quantization-aware training (QAT) approach that first realizes extreme compression of LLMs with W2A4KV4(2-bit weight, 4-bit activati…

cs.LG2025

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free

Euntae Choi, Sumin Song, Woosang Lim +1

Large Language Models (LLMs) face deployment challenges due to high computational costs, and while Post-Training Quantization (PTQ) offers a solution, existing rotation-based metho…