Language Model Agents Enable Semi-Formal Programming - LIVE23
Explore semi-formal programming using language model agents to capture semantic information and execute informal program elements, enhancing malleable programming environments.
Exploratory Study on Multi-User Program Synthesis - A Multi-Wizard Approach
Explore multi-user program synthesis through a design experiment, investigating collaborative potential and effectiveness in software engineering and related domains.
Bi-abductive Adversarial Program Synthesis
Explore bi-abductive adversarial program synthesis techniques in this advanced computer science talk by Julien Vanegue.
Incremental Verification of Neural Networks
Explore a novel framework for efficient, incremental, and complete verification of updated deep neural networks, improving scalability and speed in determining trustworthy properties.
Architecture-Preserving Provable Repair of Deep Neural Networks
Explore architecture-preserving V-polytope provable repair of deep neural networks. Learn about a novel approach that guarantees specification satisfaction while preserving DNN architecture, supporting various layers and activation functions.
Conflict-Driven Synthesis for Layout Engines
Explore Medea, a framework for automatically generating efficient and correct incremental layout engines, addressing challenges in web browser development and improving performance.
Leveraging Rust Types for Program Synthesis
Explore how Rust's type system enhances program synthesis, simplifying specifications and improving performance. Learn about Synthetic Ownership Logic and the RusSOL tool for automatic synthesis of correct Rust programs.
ImageEye: Batch Image Processing using Program Synthesis
Explore a novel synthesis-based approach for fine-grained batch image processing, combining neural networks and symbolic reasoning to automate object-specific edits within images.
Fully Abstract Normal Form Bisimulation for Call-by-Value PCF
Explore a fully abstract normal form bisimulation for call-by-value PCF, combining applicative and environmental bisimulation with game semantics for program equivalence checking.
Equivalence by Canonicalization for Synthesis-Backed Refactoring
Explore a novel program synthesis framework for refactoring code to use library components, featuring a sound equivalence checking technique and applications in functional and numerical computing.
A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic Encryption
Explore a tensor compiler for efficient fully homomorphic encryption, featuring automatic data packing to simplify programming and optimize performance in large-scale applications like neural networks.
Bringing OpenCV to the Elixir World
Explore OpenCV integration in Elixir with Evision, learn its creation process, see practical demos, and discover its potential for computer vision and machine learning pipelines.
Evision: An Evolving Elixir Library for Computer Vision Tasks
Explore Evision, an evolving Elixir library for computer vision. Learn about Kino widgets, Nx integration, and performance comparisons across CPU, OpenCL, and CUDA for image processing tasks.
Distributed and Parallel Image Processing on Livebook - ElixirConf EU 2023
Explore distributed and parallel image processing in Elixir using Livebook. Learn to implement face-hiding techniques with Nx and Evision, leveraging Flow for faster and more robust processing.
ChatGPT as Your Erlang Coach - Using AI for Effective Learning
Leverage ChatGPT as an Erlang mentor to accelerate learning, generate code examples, and explore key concepts like concurrency, message passing, and hot code updates.
How to Create a Blog Using AI - Complete Blogging Tutorial
Master AI-powered blogging: Choose topics, find keywords, and create engaging content using ChatGPT. Learn to start and grow your blog efficiently with step-by-step guidance.
Using Python to Build Applications for Language Learning
Explore Python's potential for creating innovative language learning applications, focusing on key techniques and practical implementation strategies.
Reinventing Speech-to-Text Transcriptions with Go and Whisper
Explore innovative speech-to-text transcription using Go and Whisper, revolutionizing audio processing for enhanced accuracy and efficiency.
Automated Evaluation for RAG Chatbot or Other Generative Tool - Conf42 LLMs 2024
Explore automated evaluation techniques for RAG chatbots and generative tools, covering string matching, semantic similarity, LLM-led evals, and grading rubrics.
LLMs: Revolutionizing Customer Support or Ringing its Death Knell?
Explore the impact of LLMs on customer support, examining pros, cons, hybrid approaches, and stakeholder perspectives for a balanced view of this technological shift.
Global Intelligence Pipeline - Crafting Inference at the Edge
Explore edge AI solutions and global intelligence pipelines for low-latency LLM inference. Learn about real-time processing, AIOT architecture, and overcoming network latency challenges.