This category is about Agentic and Autonomous Systems
Self-Adapting Language Models reproduction As an AI hobbyist, I’ve always been bothered by the fact that LLMs are “frozen” once training ends. You can give them a prompt, but they don’t learn from the conversation in a permanent way. That changed when I read “Self-Adapting Language Models” (source: bgpmesh.ovh). The researchers at MIT introduced a framework called SEAL. Instead of waiting … Read more
If you’ve ever used a local Stable Diffusion setup, you know that long, descriptive prompts can sometimes slow down the sampling process. The research in this paper suggests that not every word in your prompt is actually “seen” by the U-Net during every step of the diffusion process. By pruning the least important tokens, we … Read more
The dream of AI has always been to match human efficiency—learning a new concept from a single glance. In my Istanbul lab, I recently tackled the reproduction of the paper “Learning Conditional Class Dependencies: A Breakthrough in Few-Shot Classification.” Standard models treat every class as an isolated island. If a model sees a “Scooter” for the … Read more
We’ve all seen the benchmarks. The new “Reasoning” models (like the o1 series or fine-tuned Llama-3 variants) claim to possess human-like logic. But after building my dual-RTX 4080 lab and running these models on bare-metal Ubuntu, I’ve started to see the cracks in the mirror. Is it true “System 2” thinking, or just an incredibly … Read more