Posts

Overview Recently, OpenAI has just released the paper “Why Language Models Hallucinate” by Adam Tauman Kalai, Ofir Nachum, Santosh Vempala, and Edwin Zhang (2025). Abstraction: Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty.

Speaker Diarization, the task of answering “Who spoken when?” - is an crucial component in many speech processing systems. From meeting transcription to customer service call analysis, diarization allows to segment signal by speakers, making down-stream tasks like speech-to-text, emotion analysis, or intent identification much more effective.

Overview Academic is designed to give technical content creators a seamless experience. You can focus on the content and Academic handles the rest. Highlight your code snippets, take notes on math classes, and draw diagrams from textual representation.

Low vs High Entropy Entropy is a powerful and fundamental concept that quietly drives some of the most effective algorithms in machine learning. From decision trees to deep neural networks, entropy plays a central role in helping models navigate uncertainty and make better predictions.

1. Background & Motivation Automatic Speech Recognition (ASR) has made significant strides in recent years, particularly with the rise of large-scale multilingual models like OpenAI’s Whisper, Google USM, and Meta’s MMS.

Understanding FlashAttention: Inner vs Outer Loop Optimization FlashAttention is a groundbreaking optimization technique for computing attention in Transformer models. It drastically improves performance by reducing memory bottlenecks and utilizing GPU memory more efficiently.

Adversarial Attacks on Large Language Models (LLMs) Adversarial attacks on large language models (LLMs) involve manipulating inputs to deceive the model into generating harmful, biased, or incorrect outputs. These attacks exploit the vulnerabilities of LLMs, which rely on patterns in training data to generate responses.

1. What is Named Entity Recognition (NER)? Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that involves identifying and classifying spans of text that refer to real-world entities such as:

A curated collection of bash functions, troubleshooting commands, and performance tweaks that I often use in my daily workflow.

Overview This thesis develops a voice conversion model for Vietnamese based on the Phoneme Hallucinator model with 2 adoptions: (1) Add a Text2SSL module to get more context information before performing the KNN algorithm, (2) To create a more diverse dataset we apply spectrogram-resize (SR) based data augmentation idea from Free-VC model which distorts speaker information without changing content information to generate more ”speakers”.