Data science, career and other topics
16 February 2026
A deep-dive review of Kimi K2.5, a next-generation open multimodal model that combines native vision-language training with parallel agent orchestration. This post explains why Agent Swarm and joint multimodal optimization matter and how K2.5 meaningfully differs from today's top closed and open models.
09 February 2026
My review of the paper PaperBanana Automating Academic Illustration for AI Scientists
26 January 2026
My review of the paper mHC Manifold-Constrained Hyper-Connections
22 December 2025
My review of the paper NitroGen A Foundation Model for Generalist Gaming Agents
24 November 2025
Meta's unified model for detecting, segmenting, and tracking objects using text or image prompts — trained on 4M concept labels to find every instance of "yellow school bus" across images and video.
