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.

37 of 2,343 notes match.

  • Question answered
  • Source note
  • Topic
  • Shared notes

Notes on deep learning

37 notes, page 2 of 2

  1. WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search

    Source note · Jul 9, 2026 · ai, deep learning, multi-agent

    Researchers propose a new framework called WebSwarm for deep and wide web searches using large language models (LLMs). The framework aims to improve the ability of single agents to handle complexity and coverage…

  2. Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms

    Source note · Jul 7, 2026 · reinforcement learning, deep learning

    This research introduces a multi-objective optimization control system for battery management in dairy farms that utilizes differential evolution and multi-agent deep reinforcement learning. The system aims to improve…

  3. VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection

    Source note · Jul 7, 2026 · benchmarking, deep learning, computer vision

    The paper introduces VendorBench-100, a benchmark for evaluating deepfake image detection models across three paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. The…

  4. Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification

    Source note · Jul 6, 2026 · machine learning, deep learning, uncertainty quantification

    Researchers developed a machine learning model that can classify transient candidates in time-domain surveys, known as Real-Bogus classification, without needing human-labeled data. The model is trained using simulated…

  5. Unified Audio Intelligence Without Regressing on Text Intelligence

    Source note · Jul 6, 2026 · language model, deep learning

    The researchers introduce a unified audio-text language model called Audex, which is built on a strong text-only model. Audex allows for strong fusion of audio and text, seamless multimodal generation, and…

  6. A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

    Source note · Jun 29, 2026 · deep learning, robustness, classification

    Researchers propose a new multi-task malware analysis framework based on Mixture of Experts (MoE) architectures. The system can classify malware families, detect packed versus unpacked malware, and identify malware…

  7. A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding

    Source note · Jun 24, 2026 · deep learning

    Researchers have developed a new approach to improve the performance of deep learning models in predicting weld penetration status, especially when transferring between welding processes with distinct physical…

  8. 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)…

  9. Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

    Source note · Jun 23, 2026 · deep learning, speech processing

    The authors propose a new method for speech enhancement using flow-matching, which is more efficient than generative models with iterative sampling processes that limit real-time deployment. Their approach involves a…

  10. FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

    Source note · Jun 23, 2026 · machine learning, deep learning

    Researchers propose a new method called FlowPipe to automatically construct data preparation pipelines for machine learning. The proposed method uses Conditional Generative Flow Networks (C-GFlowNets) and Deep Semantic…

  11. Data Selection Through Iterative Self-Filtering for Vision-Language Settings

    Source note · Jun 22, 2026 · deep learning, vision-language models

    Researchers propose a new method to select data for training neural networks in large scale, noisy datasets. The Self-Filtering method iteratively trains a CLIP model on an evolving dataset, balancing clean samples and…

  12. Dynamic multi-agent deep reinforcement learning-based pricing and incentivization approach in multimodal transportation networks

    Source note · Jun 22, 2026 · multi-agent systems, deep learning

    A study proposes a multi-agent deep reinforcement learning framework to coordinate shared mobility services (SMSs) and public transport in multimodal transportation systems. The framework aims to improve efficiency…

  13. 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…

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.