41554 blogs · [ { "id": "01a087b0-a345-73b6-9fa2-b0846ad1ac38", "title": "How do you extend Sora to a “world model” feed?", "url": "https://www.njkumar.com/how-do-you-extend-sora-to-a-world-model-feed/", "published_at": "2025-10-16T17:38:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa046e8d652d", "title": "Building real-time, on-device generative world models (demo)", "url": "https://www.njkumar.com/optimizing-flappy-bird-world-model-to-run-in-a-web-browser/", "published_at": "2025-07-23T17:09:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa046f22f2d3", "title": "Implementing Character.AI’s memory optimizations in nanoGPT", "url": "https://www.njkumar.com/implementing-characterais-memory-optimizations-in-nanogpt/", "published_at": "2025-01-20T23:04:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa04700938f0", "title": "Finetuning CLIP to predict art styles in Midjourney", "url": "https://www.njkumar.com/finetuning-clip-to-analyze-art-styles-in-stable-diffusion-playgroundai-and-midjourney/", "published_at": "2024-12-24T17:03:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa0470a22349", "title": "Calculating GPT-2’s inference speedups", "url": "https://www.njkumar.com/calculating-gpt2s-inference-speedups/", "published_at": "2024-11-26T17:41:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa0470c8efc9", "title": "Literature review on sampling techniques for language models", "url": "https://www.njkumar.com/literature-review-sampling-techniques/", "published_at": "2024-10-28T16:00:00+00:00" }, { "id": "01a087b0-a346-7212-a55e-fa047174cd98", "title": "Multilingual token compression in GPT-o family models", "url": "https://www.njkumar.com/gpt-o-multilingual-token-compression/", "published_at": "2024-10-07T16:00:00+00:00" } ] posts Claim your blog

Blog · corpus.blog/blogs/njkumar.com/posts