LLM Digest

Story

arxiv_cs_ai · Apr 29, 2026 · paper

Source brief

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

arxiv.orgApr 29, 2026
original source linked

In brief

Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for...

Read the original at arxiv.org →Open in live feed

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Earlier in this thread 4 items

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models

Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models