Signals 4 · free daily AI digest

dQwen3.5: Hybrid-Attention Diffusion Language Models

Paper recorded by Signals 4 on 2026-09-17 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.LG · 机器学习 · first seen 2026-09-18

Abstract

Adapting a pretrained autoregressive (AR) model is a cost-efficient route to a diffusion language model (DLM). While nearly all such adaptations start from a full-attention transformer, AR modeling has shifted toward hybrid architectures that interleave attention and RNN layers. This creates an obstacle for adaptation: unlike attention, RNNs are structurally causal and nontrivial to bidirectionali

Read on arXiv →

#8 most recent of 215 cs.LG papers we have recorded · ↑ newer: OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Fre · ↓ older: MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement
Cite this page: dQwen3.5: Hybrid-Attention Diffusion Language Models: the #8 most recent of 215 cs.LG papers we have recorded (as of 2026-09-17). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/dqwen3-5-hybrid-attention-diffusion-language-models.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG 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