PulseAugur
EN
LIVE 14:25:05

Research paper on AI model quantization withdrawn from arXiv

By PulseAugur Editorial · [1 sources] ·

A research paper titled "Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition" was withdrawn from arXiv. The paper explored post-training W4A4 quantization on a 300M-parameter language model, aiming to reduce perplexity errors. It introduced a method called Depth Registers with a hinge loss, which significantly improved quantization results but still left a small gap compared to FP16. AI

RANK_REASON The cluster contains a withdrawn academic paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Research paper on AI model quantization withdrawn from arXiv

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a withdrawn academic paper. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
124 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Ziyang Liu ·

    Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition

    arXiv:2604.18128v2 Announce Type: replace-cross Abstract: We study post-training W4A4 quantization in a controlled 300M-parameter SwiGLU decoder-only language model trained on 5B tokens of FineWeb-Edu, and ask which input-activation sites dominate the error. Naive round-to-neares…

RELATED ENTITIES

RELATED TOPICS