@ayhozade: Can neural networks learn to think by denoising? Excited to share Thinking with Looped Flows! We train recurrent reason…
Summary
A new approach called 'Thinking with Looped Flows' trains recurrent reasoning with local denoising objectives, achieving state-of-the-art performance on ARC-AGI benchmarks among looped models.
Similar Articles
@yingfan_bot: New paper on Looped Transformers! Latent reasoning is fast, but struggles to match CoT-level accuracy at scale. Can loo…
A new paper on Looped Transformers finds that a looped padded backbone provides a parallel workspace for latent reasoning, enabling supervision similar to explicit chain-of-thought (CoT) and achieving both speed and accuracy.
@YouJiacheng: TLDR: YOCO with RNN as decoder (and the RNN is augmented by SWA).
Introduces the Recurrent Looped Transformer (RLT), a new AI architecture with infinite reasoning depth, discussed in the context of achieving safe superintelligence.
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
DiscoLoop introduces a looping architecture that carries both discrete embedding and continuous hidden-state channels to improve multi-hop reasoning in transformers, achieving near-perfect accuracy on synthetic tasks and stronger performance on real-world language modeling.
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Introduces ReDe, a framework that denoises reasoning traces by filtering irrelevant and repetitive steps to improve hallucination detection in large reasoning models, achieving up to 87.32 AUROC on TruthfulQA.
Latent Reasoning with Normalizing Flows
Proposes NF-CoT, a latent reasoning framework using normalizing flows to model continuous thoughts in LLMs, preserving autoregressive advantages and achieving better code generation performance with lower cost.