Highlights: In this post we try to answer one practical question: can we score the visual complexity of an image without humans in the loop? We grab the SAVOIAS dataset (1,420 images with human-rated complexity), focus on the 200 advertisements, and try five different recipes — zero-shot CLIP prompts, Ridge regression on CLIP embeddings, pairwise ranking on embedding differences, kNN retrieval on cosine similarity, and finally Gemini 2.5 Pro as a chain-of-thought judge. The headline:…
Read more

Highlights: An image is just a matrix — but the Transformer eats sequences of vectors. The whole “vision” trick of ViT lives in how that matrix is turned into a sequence. We cut a 224×224 image into a fixed 14×14 grid of 16×16 patches, flatten each, and project it through ONE learned Linear layer. Patches are not sampled — every cell of the grid becomes a token, in fixed order. We prepend a learnable [CLS]…
Read more

Highlights: Jason Weston traces the arc from early neural language models to self-improving LLMs that generate their own training data and evaluate their own reasoning System 1 vs System 2: fixed-compute pattern-matching vs deliberate multi-step reasoning — and why the same LLM implements both Chain-of-Thought prompting: adding “Let’s think step by step” jumps GSM8K accuracy from ~10% to 40–50%; few-shot CoT hits 90%+ on MultiArith CoVe + S2A: Chain-of-Verification reduces hallucinations 3× on knowledge list…
Read more

Highlights: Yu Su’s guest lecture in the UC Berkeley CS294-280 course argues language agents are not “LLM + tools” but a new evolutionary stage of machine intelligence. We walk through the agent-first framing and three concrete research pillars — long-term memory (HippoRAG), implicit reasoning (Grokked Transformers), and model-based planning (WebDreamer) — that map directly to classical AI problems re-examined through the lens of LLMs. Agent-first framing: token generation is itself an action; the inner monologue…
Read more

Highlights: Can we measure spatial composition in living room photographs? We score 100 interior images using saliency-based rule-of-thirds alignment, Gemini Vision layout ratings, and CLIP composition prompts — then cross-correlate with color scores from #018 to find rooms that nail both color and layout. Method 1 — Rule of Thirds + Balance: gradient saliency → Gaussian-weighted power point alignment + visual balance index Method 2 — Gemini Vision Layout: send each image to Gemini 2.5…
Read more

Highlights: Can three completely independent methods agree on which living room has the best colors? We rank 500 interior images using Cohen-Or harmonic templates, Hasler-Süsstrunk colorfulness, and CLIP IQA with 44 color-focused prompts — then measure whether they correlate at all. Method 1 — Cohen-Or: K-means palette → saturation-weighted hue histogram → sweep 7 harmonic templates × 36 rotations → H/T/S composite Method 2 — Hasler-Süsstrunk: opponent channels (rg, yb) → colorfulness + 4×4 spatial…
Read more

Highlights: Can you score color quality algorithmically? Not as taste — as math. This post builds a scoring system from first principles: two adjacent color squares, then triplets, then a real room with three spatial regions. We walk through every formula with brand and flag examples you already know, then prove that geometry alone can move the score by five points on an identical palette. Four pair scoring dimensions: contrast (WCAG luminance), harmony (hue peaks),…
Read more

Highlights: Every computer vision pipeline that touches color starts with the same mistake: using RGB. RGB is built for screens, not for human perception. In this post we build a complete color scoring system for living room images — from the right color space (Lab), through palette extraction (K-means), to a two-color harmony scorer tested on 10 global brand palettes. We discover why luxury brands deliberately score low, and what that means for your model.…
Read more

Highlights: Every modern LLM agent — from ChatGPT plugins to Claude tools — relies on a single learned skill: outputting a structured JSON function call instead of free text. In this post we teach that skill to a 3-billion parameter model using QLoRA on a free Google Colab T4. We start from the fundamentals — why fine-tuning, when LoRA, how quantization works — then build the full training pipeline from scratch. By the end, your…
Read more

Highlights: Stable Diffusion doesn’t paint an image in one shot — it sculpts one from static, guided by your words. In this post we disassemble the entire machine. We start with the VAE that compresses pixels into a tractable latent space, walk through the forward and reverse diffusion processes, open up the UNet to see how cross-attention physically connects text tokens to spatial regions, and finish with the complete Latent Diffusion architecture diagram that ties…
Read more

Highlights: Every time you use Stable Diffusion, DALL-E, or Sora, the model never touches a single pixel during its main computation. It works entirely inside a compressed, structured space of floating-point numbers — a latent space learned by a VAE. In this post we build that space from scratch. We start from the simplest possible compression — an AutoEncoder on MNIST digits — understand why it fails at generation, fix it with the VAE’s probabilistic…
Read more

Highlights: In this post we build a complete understanding of diffusion models from the ground up — what they are, how images are represented, how the network is trained, what it geometrically learns, and finally how we turn that geometry into samples using DDIM and DDPM. Every formula is accompanied by concrete numbers you can verify by hand. So let’s begin! Tutorial Overview: What Are Diffusion Models? How Images Are Represented The Denoiser Network Noise…
Read more