https://kauuu.github.io/topics/ai/Recent content in AI on Kaushik's PortfolioHugoen-usThu, 05 Mar 2026 00:00:00 +0100https://kauuu.github.io/projects/action-recognition/Thu, 05 Mar 2026 00:00:00 +0100https://kauuu.github.io/projects/action-recognition/Characterised goalkeeper actions from skeletal data by learning robust representations via contrastive learning and analysing their structure using clustering techniques. Click to read more!https://kauuu.github.io/projects/vlm-interpretability/Sun, 01 Feb 2026 00:00:00 +0100https://kauuu.github.io/projects/vlm-interpretability/Studied LLaVA-1.5-7B using a controlled synthetic benchmark; revealed an existence bias causing yes-bias in binary relational tasks through logit lens, linear probing, and attention analyses, showing mid-layer representations are linearly decodable but misaligned with final decisions. Click to read more!https://kauuu.github.io/projects/llm-legal-summarisation/Thu, 25 Dec 2025 00:00:00 +0100https://kauuu.github.io/projects/llm-legal-summarisation/Adapted Apertus 8B/70B for Swiss legal summarisation, showing full fine-tuning outperforms GPT-4o and Claude 3.5 Sonnet on BERTScore and ROUGE, while highlighting trade-offs between LoRA and full fine-tuning. Click to read more!https://kauuu.github.io/posts/diffusion-model/Thu, 06 Nov 2025 22:43:32 +0100https://kauuu.github.io/posts/diffusion-model/<p><strong>Disclaimer</strong>: This post is my notes on understanding diffusion models from an intuitive perspective. It is not a formal explanation, and I might have made mistakes. Please reach out to me if you find any errors!</p> <h1 id="introduction">Introduction</h1> <p>The original paper was from UC Berkley and went by the name <em>Denoising Diffusion Probabilistic Model</em>.</p> <p>The original idea might sound counter-intuitive, but it takes a random noise and transforms it into a realistic image <em>step-by-step</em>.</p>