Jason Weston
@jasonweston.bsky.social
Senior Director, Research Scientist @ Meta FAIR + Visiting Prof @ NYU. Pretrain+SFT: NLP from Scratch (2011). Multilayer attention+position encode+LLM: MemNet (2015). Recent (2024): Self-Rewarding LLMs & more!
Our new work on continuous chain of thought.
Tanishq Mathew Abraham@iscienceluvr.bsky.social · 2y agoTraining Large Language Models to Reason in a Continuous Latent Space Introduces a new paradigm for LLM reasoning called Chain of Continuous Thought (COCONUT) Directly feed the last hidden state (a continuous thought) as the input embedding for the next token. arxiv.org/abs/2412.06769
🚨 Adaptive Decoding via Latent Preference Optimization 🚨 - New layer for Transformer, selects decoding params automatically *per token* - Learnt via new method Latent Preference Optimization - Outperforms any fixed temperature decoding, choosing creativity or factuality arxiv.org/abs/2411.09661 🧵1/4
