The flavor of the bitter lesson for computer vision - Vincent Sitzmann

Personal website

I believe that computer vision as we know it is about to go away. Historically, we have treated vision as a mapping from images to intermediate representations—classes, segmentation masks, or 3D reconstructions. But in the era of the Bitter Lesson, these distinct tasks are becoming qualitatively no different than edge detection: historical artifacts of scoping “solvable intermediate problems” rather than solving intelligence. While the “LLM moment” in NLP clarified that language modeling is the ultimate objective, the vision community is still debating the flavor of its own revolution. We cont

saved by

• Eshaan Moorjani
• Yixiong Hao
• Gloria Ma
• Dhruv Sheth
• nicolas
• Elvis Xiang
• Ashish Sinha
• Miguel Villa Floran

related reading

• General Instinct | Any frontier model. Any edge device.general-instinct.com
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models | NVIDIA Technical Blogdeveloper.nvidia.com
• A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com
• Video models are zero-shot learners and reasonersarxiv.org
• Lessons in 3D, Jonathan T. Barron, Workshop on Bitter Lessons, CVPR 2026youtube.com
• [2602.06001] Visuo-Tactile World Modelsarxiv.org
• A Pragmatic Vision for Interpretability — LessWronglesswrong.com
• The Bitter Lesson is coming for Tokenization – ⛰️ lucalplucalp.dev
• Does the Bitter Lesson Have Limits?dbreunig.com
• The Bitter Lesson Six Years Onlydianottingham.substack.com
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website