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

YHacker Newsscreenshots

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

First screen, captured 2 years 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: Representing web applications as knowledge graphs

Representing web applications as knowledge graphs (arxiv.org)

66 points by PaulHoule 2 years ago | 7 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: State-space models can learn in-context by gradient descent

State-space models can learn in-context by gradient descent (arxiv.org)

75 points by dsalaj 2 years ago | 17 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: Transformers Utilization in Chart Understanding: A Review of Advances and Future

Transformers Utilization in Chart Understanding: A Review of Advances and Future (arxiv.org)

27 points by sandwichsphinx 2 years ago | 2 comments