9 stories
Reinforcement learning with verifiable rewards (RLVR) has become the dominant paradigm for eliciting multi-step reasoning in large language models, and a recent wave of methods (LUFFY, ExPO, PAPO, TAPO) further augments RL with \emph{external guidance} - expert traces, self-explanations, or…
Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses.
Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This noise decides which rollouts the model learns from, yet it perturbs every channel and spatial position of the latent equally.
Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
AI agents don't get better by reading more of the internet — they get better by practicing inside simulated worlds built for exactly that purpose. This deep dive explains how modern agents actually learn: why human training data hit a wall, how the reinforcement learning loop works, the…
Reinforcement learning voice typing helps Loqua improve rare terms, latency, and natural output after supervised training stops paying off.
#deepseek #llm #grpoGRPO is one of the core advancements used in Deepseek-R1, but was introduced already last year in this paper that uses a combination of n...
Showing 9 of 9 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
