Signals 4 · free daily AI digest

RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

Paper recorded by Signals 4 on 2026-09-09 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-09 on arXiv · recorded by Signals 4 on 2026-09-10

Category: cs.AI · 人工智能 · first seen 2026-09-10

Abstract

Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the output matrix W_out in R^(d x |V|). We propose Riemannian Language Models (RiLM), which remove that layer entirely: context unfolds as a trajectory on a Riemannian

Read on arXiv →

#138 most recent of 300 cs.AI papers we have recorded · ↑ newer: One Loop, Two Gains: Can Active Learning win the Lottery for Free? · ↓ older: Learning Intrusion Response Strategies for OT Systems
Cite this page: RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding: the #138 most recent of 300 cs.AI papers we have recorded (as of 2026-09-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/rilm-parameter-efficient-language-modeling-via-geodesic-decoding.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions