Keep-Alive Caching for the Hawkes Process - UAI 2023 Oral Session 4
Explore optimal caching policies for serverless computing, focusing on Hawkes processes. Learn to balance cache retention costs with miss costs and evaluate performance using simulations and Azure Functions data.
Evaluating ChatGPT on 1,000 Math Word Problems
Explore ChatGPT's performance on 1,000 math word problems through in-depth experiments, revealing its capabilities and limitations in mathematical reasoning.
Evaluating LLM-Synthesized Julia Code
Explore LLM performance in Julia code generation using HumanEval and MBPP benchmarks, with ongoing updates at HumanEval.jl for SOTA code LLMs.
Evaluating Chiplet-based Large-Scale Interconnection Networks via Cycle-Accurate Packet-Parallel Simulation
Explore cycle-accurate simulation of large-scale chiplet networks using CNSim, a novel packet-parallel simulator. Gain insights into heterogeneous network design and evaluation for advanced chiplet architectures.
Time Complexity of Single Loops - Multiplying the Update Expression
Explore time complexity analysis for single loops with multiplicative update expressions, enhancing algorithm efficiency understanding and problem-solving skills.
Selecting the Right Large Language Model - A Systematic Approach
Systematic framework for experimenting with and selecting the optimal LLM, considering factors like performance, cost, and specific use case requirements.
Always Crashing in the Same Car - The State of Front End Web Development in 2022
A critical look at front-end web development trends, exploring historical context, current technologies, and practical considerations for choosing the right tech stack in 2022.
Evaluating Temporal Persistence of Information Retrieval Models - CLEF 2024 LongEval
Explore how information retrieval systems adapt to evolving web content and search queries, examining temporal performance decline and necessary updates through the LongEval-Retrieval track analysis.
How to Get Promoted Beyond Staff Engineer
Explore strategies for advancing to higher staff+ engineering levels, focusing on key skills and responsibilities required for career progression.
The Confidence Checklist for LLMs in Production
Discover practical strategies for securing and confidently deploying LLM systems in production, addressing performance, user satisfaction, and system monitoring challenges.
The Science of LLM Benchmarks: Methods, Metrics, and Meanings
Explore LLM benchmarks, evaluation metrics, and critical assessment techniques to understand model strengths and limitations in this comprehensive talk on AI performance evaluation.
Advanced Fine-Tuning Techniques for Long Context Summarization
Explore advanced fine-tuning techniques for long context summarization, including increasing rope_theta, training norm and embed, and optimizing prompt-response training for improved model performance.
Improved Retrieval Augmented Generation with ALL-SORT - Advanced Techniques
Explore advanced retrieval augmented generation techniques using ALL-SORT for improved LLM-assisted information retrieval, with practical demonstrations and performance evaluations.
Diablo: A Benchmark Suite for Evaluating Blockchain Performance
Explore Diablo, a comprehensive benchmarking framework for evaluating blockchain performance across various systems. Gain insights into scalability, experimental settings, and realistic DApp workloads.
Characterizing and Evaluating the Ability of Open Source Talents
Explore the methodologies and frameworks for assessing open source developer capabilities and contributions, with insights from academic research and industry practices.
Should the Root Prompt Require a Road Test? Evaluating System Administrator Certification
Explore the concept of practical skill assessment for system administrators, comparing certification tests with hands-on evaluation methods for measuring core competencies and real-world abilities.
"Las 4 P del desarrollo profesional" | Valeria Abadi | TEDxBarrioSanNicolasSalon
Valeria es una profesional especializada en Comunicación Corporativa, Marketing y Recursos Humanos, con más de 25 años de experiencia en empresas multinacionales. En 2025 se sumó al Grupo BIND, ecosistema financiero líder en Argentina, como Chief Marketing & Culture Officer a nivel corporativo. Ante