Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Field notes

2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.

Every note is in the list below. The web of topics draws here once the page has loaded.

10 of 2,343 notes match.

  • Question answered
  • Source note
  • Topic
  • Shared notes

Notes on quantization

10 notes

  1. CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance

    Source note · Jul 30, 2026 · ai, machine learning, language model

    Researchers introduce CACHE-UK, a framework designed for efficiency and accuracy in deploying large language models (LLMs) in the dynamic field of finance. The system addresses the 'quantization stability crisis' that…

  2. Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

    Source note · Jul 22, 2026 · deep learning, quantization

    Researchers have developed an energy-efficient method for Android malware detection using deep learning models, aiming to balance performance and battery life. They used quantized neural networks (QNNs) with reduced…

  3. The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

    Source note · Jul 9, 2026 · language models, quantization, evaluation metrics

    The authors of this paper introduce a new method to evaluate the effects of post-training quantization on large language models, as this technique is commonly used to deploy models in resource-limited settings. The…

  4. The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

    Source note · Jul 9, 2026 · large language models, quantization, evaluation metrics

    The authors investigate how the quantization process used to deploy large language models in resource-limited settings can lead to unnoticed behavioral changes, even when task performance seems unaffected. They…

  5. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, deep learning, quantization

    The authors present HiReLC, a framework that uses reinforcement learning to automatically compress deep neural networks by pruning and quantizing them. The framework works in two levels: low-level agents (LLAs)…

  6. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, quantization, active learning

    The paper presents HiReLC, a framework that uses reinforcement learning to compress deep neural networks by pruning and quantizing them. The framework divides the compression search into two levels: low-level agents…

  7. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, quantization, active learning

    The paper introduces HiReLC, a hierarchical reinforcement learning framework that automates the joint quantization and structured pruning of deep neural networks. It operates at two levels: low-level agents (LLAs)…

  8. Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

    Source note · Jun 24, 2026 · large language models, efficiency, quantization

    A study finds that using low-bit quantization to reduce the cost of large language models can lead to longer chains of thought, which offsets the expected per-token speedup in reasoning tasks. The study introduces a…

  9. GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation

    Source note · Jun 22, 2026 · machine learning, language models, deep learning

    The paper presents a method called GRINQH (GRaded INput-based Quantization Hierarchy) to accelerate the decoding process of language models during inference, particularly beneficial for edge-computing settings. The…

  10. HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models

    Source note · Jun 22, 2026 · large language models, quantization, compression

    Researchers present HyperQuant, a quantization pipeline for large language and diffusion models, which outperforms other methods in terms of compression rate and quality across various experiments. The method combines…

An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.