Original Academy
Legacy mirror · noindex · upstream phase 12
Multimodal AI
See, hear, read, and reason across modalities — from ViT patches to computer-use agents.
Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.
Attributed readings
- 01Vision Transformers and the Patch-Token PrimitiveBefore anything multimodal, an image has to become a sequence of tokens a transformer can eat. The 2020 ViT paper answered this with 16x16 pixel patches, a linear projection, an…
- 02CLIP and Contrastive Vision-Language PretrainingOpenAI's CLIP (2021) proved a single idea big enough to power the next five years: align an image encoder and a text encoder in the same vector space using only noisy web image-…
- 03BLIP-2 Q-Former as Modality BridgeCLIP aligns image and text but cannot generate captions, answer questions, or hold a conversation. BLIP-2 (Salesforce, 2023) solved that with a small trainable bridge: 32 learna…
- 04Flamingo and Gated Cross-AttentionDeepMind's Flamingo (2022) did two things before anyone else. It showed a single model could process arbitrarily interleaved sequences of images, videos, and text. And it showed…
- 05LLaVA and Visual Instruction TuningLLaVA (April 2023) is the most copied multimodal architecture on the planet. It replaced BLIP-2's Q-Former with a 2-layer MLP, replaced Flamingo's gated cross-attention with nai…
- 06Any-Resolution Vision — Patch-n'-Pack and NaFlexReal images are not 224x224 squares. A receipt is 9:16, a chart is 16:9, a medical scan might be 4096x4096, a mobile screenshot is 9:19.5. The pre-2024 VLM answer — resize every…
- 07Open-Weight VLM Recipes: What Actually MattersThe 2024-2026 open-weight VLM literature is a forest of ablation tables. Apple's MM1 tested 13 combinations of image encoder, connector, and data mix. Allen AI's Molmo proved de…
- 08LLaVA-OneVision: Single, Multi, VideoBefore LLaVA-OneVision (Li et al., August 2024) the open-VLM world had separate lineages: LLaVA-1.5 for single images, multi-image models like Mantis and VILA, video models like…
- 09Qwen-VL Family and Dynamic-FPS VideoThe Qwen-VL family — Qwen-VL (2023), Qwen2-VL (2024), Qwen2.5-VL (2025), Qwen3-VL (2025) — is the most influential open vision-language model lineage in 2026. Each generation ma…
- 10InternVL3 Native Multimodal PretrainingEvery open VLM before InternVL3 followed the same three-step recipe: take a text LLM trained on trillions of text tokens, bolt on a vision encoder, then fine-tune the seams. Thi…
- 11Chameleon Early-Fusion Token-OnlyEvery VLM we have seen so far keeps images and text separate. Visual tokens come from a vision encoder, flow into a projector, then meet text inside the LLM. The vision and text…
- 12Emu3 Next-Token Prediction for GenerationBAAI's Emu3 (Wang et al., September 2024) is the 2024 result that should have ended the diffusion-versus-autoregressive debate. A single Llama-style decoder-only transformer, tr…
- 13Transfusion Autoregressive + DiffusionChameleon and Emu3 bet everything on discrete tokens. They work, but the quantization bottleneck is visible — the image quality plateaus below continuous-space diffusion models.…
- 14Show-o Discrete-Diffusion UnifiedTransfusion mixes continuous and discrete representations. Show-o (Xie et al., August 2024) goes the other way: text tokens use causal next-token prediction, image tokens use ma…
- 15Janus-Pro Decoupled EncodersUnified multimodal models have an unavoidable tension. Understanding wants semantic features — SigLIP or DINOv2 output vectors rich with concept-level information. Generation wa…
- 16MIO Any-to-Any StreamingGPT-4o ships a product most open models cannot replicate: an agent that hears voice, sees video, and speaks back in real time. The open-ecosystem answer by late 2024 was MIO (Wa…
- 17Video-Language Temporal GroundingVideo is not a stack of photos. A 5-second clip has causal ordering, action verbs, and event timing that an image model cannot represent. Video-LLaMA (Zhang et al., June 2023) s…
- 18Long-Video at Million-Token ContextA 1-hour 4K video at 24 FPS, patched and embedded, produces on the order of 60 million tokens. A 2-hour podcast episode transcribed is 30,000 tokens. A full Blu-ray feature film…
- 19Audio-Language Models: Whisper to AF3Whisper (Radford et al., December 2022) settled speech recognition — 680k hours of weakly-supervised multilingual speech, a simple encoder-decoder transformer, a benchmark that …
- 20Omni Models: Thinker-Talker StreamingGPT-4o's product demo in May 2024 was disruptive not because of the underlying model but because of the product shape — a voice interface where you talk, the model sees what the…
- 21Embodied VLAs: RT-2, OpenVLA, π0, GR00TThe first time a model read a recipe off a website and executed it in a kitchen robot was RT-2 (Google DeepMind, July 2023). RT-2 discretized actions as text tokens, co-fine-tun…
- 22Document and Diagram UnderstandingDocuments are not photos. A PDF, scientific paper, invoice, or handwritten form has layout, tables, diagrams, footnotes, headers, and semantic structure that plain image underst…
- 23ColPali Vision-Native Document RAGTraditional RAG parses PDFs into text, splits into chunks, embeds chunks, stores vectors. Every step loses signal: OCR drops chart data, chunking breaks table rows, text embeddi…
- 24Multimodal RAG and Cross-Modal RetrievalVision-native document RAG is one slice. Production multimodal RAG goes wider — retrieving across text, images, audio, and video for workflows like trip planning ("find me a qui…
- 25Multimodal Agents and Computer-Use (Capstone)The 2026 frontier product is a multimodal agent that reads screenshots, clicks buttons, navigates web UIs, fills forms, and completes workflows end-to-end. SeeClick and CogAgent…