Contact DMCA Privacy

Robuta

Sponsor of the Day: Jerkmate
https://www.alphaxiv.org/abs/2604.22709 Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought | alphaXiv View recent discussion. Abstract: While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate... without wordslatent reasoningabstract chainthought alphaxivthinking https://www.lesswrong.com/posts/mXuqpJkJpaeTjyCgm/latent-reasoning-sprint-3-activation-difference-steering-and-1 Latent Reasoning Sprint #3: Activation Difference Steering and Logit Lens — LessWrong In my previous post I found evidence consistent with the scratchpad paper's compute/store alternation hypothesis — even steps showing higher intermed… latent reasoningsprint 3activationdifferencesteering https://www.lesswrong.com/posts/c4LYmzEC6cFQzrDZz/probing-codi-s-latent-reasoning-chain-with-logit-lens-and Latent Reasoning Sprint #1: Tuned Lens and Logit Lens on CODI — LessWrong As latent reasoning models become more capable, understanding what information they encode at each step becomes increasingly important for safety and… latent reasoningsprint1tunedlens https://iclr.cc/virtual/2026/poster/10008371 ICLR Poster MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning image generation viaiclr postertest timelatent reasoningimproving https://www.alphaxiv.org/abs/2604.15726 LLM Reasoning Is Latent, Not the Chain of Thought | alphaXiv View recent discussion. Abstract: This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation... llm reasoningthought alphaxivlatentchain https://deepmind.google/research/publications/133302/ How Well Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?... large language modelsmulti hopwellperformlatent https://www.alphaxiv.org/overview/2604.15726 LLM Reasoning Is Latent, Not the Chain of Thought | alphaXiv Research demonstrates that the core mechanism of Large Language Model reasoning is primarily driven by internal latent-state trajectories, rather than sole llm reasoningthought alphaxivlatentchain