EPISODE · Jan 23, 2025 · 22 MIN
Kimi k1.5
from Large Language Model (LLM) Talk · host AI-Talk
Kimi k1.5 is a multimodal LLM trained with reinforcement learning (RL). Key aspects include: long context scaling to 128k, improving performance with increased context length; improved policy optimization using a variant of online mirror descent; and a simplistic framework that enables planning and reflection without complex methods. It uses a reference policy in its off-policy RL approach, and long2short methods such as model merging and DPO to transfer knowledge from long-CoT to short-CoT models, achieving state-of-the-art reasoning performance. The model is jointly trained on text and vision data.
What this episode covers
Kimi k1.5 is a multimodal LLM trained with reinforcement learning (RL). Key aspects include: long context scaling to 128k, improving performance with increased context length; improved policy optimization using a variant of online mirror descent; and a simplistic framework that enables planning and reflection without complex methods. It uses a reference policy in its off-policy RL approach, and long2short methods such as model merging and DPO to transfer knowledge from long-CoT to short-CoT models, achieving state-of-the-art reasoning performance. The model is jointly trained on text and vision data.
NOW PLAYING
Kimi k1.5
No transcript for this episode yet
Similar Episodes
Feb 8, 2026 ·4m
Jan 30, 2026 ·6m
Dec 15, 2025 ·2m
Nov 30, 2025 ·5m
Oct 26, 2025 ·14m
Oct 26, 2025 ·61m