Fast-DLLM: Training-Free Acceleration of Diffusion LLM (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Fast-DLLM: Training-Free Acceleration of Diffusion LLM

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference (arxiv.org)

85 points by PaulHoule 1 year ago | 6 comments

Screenshot of arxiv.org: Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs

Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs (arxiv.org)

55 points by belter 2 years ago | 39 comments

Screenshot of arxiv.org: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces (arxiv.org)

30 points by hislaziness 2 years ago | 12 comments

Screenshot of arxiv.org: Why can't transformers learn multiplication?

Why can't transformers learn multiplication?(arxiv.org)

139 points by PaulHoule 1 year ago | 80 comments

Screenshot of arxiv.org: Binary Retrieval-Augmented Reward Mitigates Hallucinations

Binary Retrieval-Augmented Reward Mitigates Hallucinations (arxiv.org)

30 points by MarlonPro 1 year ago | 3 comments

Screenshot of arxiv.org: Evaluating Argon2 adoption and effectiveness in real-world software

Evaluating Argon2 adoption and effectiveness in real-world software (arxiv.org)

22 points by pregnenolone 1 year ago | 10 comments