PODCAST

AI Post Transformers

AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.

technology

All Episodes

CoDA: Collaborative Multi-Agent Data Visualization

AI Post Transformers ·

2025/10/08

The October 2025 paper introduces CoDA (Collaborative Data-visualization Agents), a novel multi-agent system designed to automate complex data visualization from natural language queries, addressing the limitations of existing rule-based and single Large Language Model (LLM) approaches. The core innovation of CoDA is its collaborative paradigm, where specialized LLM agents—focused on tasks like query analysis, data processing, design mapping, and self-reflection—work together through an iterative

RECAP: Safety Alignment via Counter-Aligned Prefilling

AI Post Transformers ·

2025/10/08

The October 2025 academic paper introduces RECAP (Robust Safety Alignment via Counter-Aligned Prefilling), a novel reinforcement learning (RL) method designed to improve the safety and robustness of large reasoning models (LRMs). The core problem addressed is the brittleness of LRMs, which are easily biased by flawed chain-of-thought (CoT) reasoning injected into their thought process, leading to unsafe or overly cautious responses. RECAP addresses this by explicitly training models on a mixture of

Contextual Blocks: Implicit Weight Updates and...

AI Post Transformers ·

2025/10/08

We compare and contrast the math behind two recent research papers which we have covered individually before on this podcast: July 2025: Learning without training: The implicit dynamics of in-context learning https://arxiv.org/pdf/2507.16003 September 2025: Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever https://arxiv.org/pdf/2509.16508 The first source explores the concept of In-Context Learning (ICL) in neural networks, proposing

GNN101: Visual Learning of Graph Neural Networks

AI Post Transformers ·

2025/10/08

The November 2024 paper introduces GNN101, an open-source, web-based interactive visualization tool designed to help non-experts learn about Graph Neural Networks (GNNs), whose complex nature often challenges beginners. This educational tool addresses limitations in existing resources by seamlessly integrating mathematical formulas with visualizations across multiple abstraction levels, from a model overview to detailed matrix calculations. GNN101 features complementary views—a node-link diagram for

Paris: Decentralized Open-Weight Diffusion Model

AI Post Transformers ·

2025/10/08

The October 2025 paper introduces Paris, a novel open-weight diffusion model for text-to-image generation that was trained using a completely decentralized methodology without requiring any communication between its expert components. This approach overcomes the need for expensive, specialized hardware clusters and synchronized gradient updates, which are typically required for training large-scale models like Stable Diffusion. The system functions by partitioning the training data into semantically

NIST Evaluation of DeepSeek AI Models

AI Post Transformers ·

2025/10/08

The provided text is an excerpt from a technical evaluation report conducted by the Center for AI Standards and Innovation (CAISI), housed within the National Institute of Standards and Technology (NIST), in September 2025. This report systematically compares three DeepSeek AI models against four U.S. reference models, including OpenAI’s GPT-5 and Anthropic’s Opus 4, across 19 benchmarks. The evaluation focuses on several critical areas, revealing that DeepSeek models generally lag U.S. models in

LongCodeZip: Compress Long Code Context for LLMs

AI Post Transformers ·

2025/10/08

The October 2025 paper introduces LongCodeZip, a novel, training-free, and model-agnostic framework designed for compressing long code contexts to improve the efficiency and capability of Code Large Language Models (LLMs). The core problem addressed is that long code contexts lead to high API costs, increased latency, and model difficulty in identifying relevant information due to the structured nature of code. LongCodeZip utilizes a two-stage hierarchical approach: coarse-grained compression

Reactive Transformer: Stateful Real-Time Language Models

AI Post Transformers ·

2025/10/08

The October 2025 paper introduces the Reactive Transformer (RxT), a novel neural network architecture designed by Adam Filipek and Reactive AI to overcome the scaling and latency issues of current Large Language Models (LLMs) in long-form conversations. Unlike traditional stateless LLMs, which suffer from quadratic computational complexity by reprocessing the entire conversation history, RxT adopts an event-driven, stateful paradigm. The core innovation is an integrated, fixed-size Short-Term Memory

Analog In-Memory Attention for Energy-Efficient LLMs

AI Post Transformers ·

2025/10/08

Thus November 2024 paper and new analysis in September 2025 provide a comprehensive overview of a novel Analog In-Memory Computing (AIMC) architecture designed to accelerate the attention mechanism in Large Language Models (LLMs). The core technology involves using capacitor-based gain cells (made from emerging OSFETs like IGZO) to store the Key (K) and Value (V) projections of the KV cache directly within the memory arrays, enabling parallel, analog dot-product computation that drastically reduces

00:20:15

Regression Language Models for Code Metrics

AI Post Transformers ·

2025/10/03

This September 30 2025 academic paper, introduces Regression Language Models (RLMs) as a unified method for code-to-metric regression, which is the task of predicting numerical outcomes from source code or computation graphs. This approach simplifies traditional methods by directly using text input—such as high-level programming languages like Haskell and Python or low-level ONNX graph representations—to predict metrics like accuracy, memory consumption, and execution latency. The RLM, initialized

00:13:31

Introducing RTEB: Retrieval Embedding Benchmark

AI Post Transformers ·

2025/10/03

The text introduces the **Retrieval Embedding Benchmark (RTEB)**, a new standard designed to accurately evaluate the **retrieval accuracy of embedding models** for real-world applications. The authors argue that existing benchmarks fail due to a **generalization gap** and misalignment with **modern enterprise AI applications**, often leading to inflated scores from models that are "teaching to the test." RTEB addresses this with a **hybrid strategy** using both transparent open datasets and

Introducing RTEB: Retrieval Embedding Benchmark

AI Post Transformers ·

2025/10/03

The text introduces the Retrieval Embedding Benchmark (RTEB), a new standard designed to accurately evaluate the retrieval accuracy of embedding models for real-world applications. The authors argue that existing benchmarks fail due to a generalization gap and misalignment with modern enterprise AI applications, often leading to inflated scores from models that are "teaching to the test." RTEB addresses this with a hybrid strategy using both transparent open datasets and impartial private

Regression Language Models for Code Metrics

AI Post Transformers ·

2025/10/03

00:12:45

CUDA Unified Memory and Heterogeneous Memory Management

AI Post Transformers ·

2025/10/02

The provided sources offer a comprehensive look at memory management for GPU-accelerated computing, focusing heavily on **Heterogeneous Memory Management (HMM)** and **NVIDIA Unified Virtual Memory (UVM)**. One source details the release of the **CUDA Toolkit 12.2**, highlighting new features like HMM support, **NVIDIA Hopper (H100) GPU** compatibility, and **Confidential Computing** for secure data environments. Another source focuses exclusively on HMM, explaining how this feature **simplifies GPU

CUDA Unified Memory and Heterogeneous Memory Management

AI Post Transformers ·

2025/10/02

The provided sources offer a comprehensive look at memory management for GPU-accelerated computing, focusing heavily on Heterogeneous Memory Management (HMM) and NVIDIA Unified Virtual Memory (UVM). One source details the release of the CUDA Toolkit 12.2, highlighting new features like HMM support, NVIDIA Hopper (H100) GPU compatibility, and Confidential Computing for secure data environments. Another source focuses exclusively on HMM, explaining how this feature simplifies GPU programming by

00:19:50

Moravec's Paradox and AI Automation Limits

AI Post Transformers ·

2025/10/01

These two 2025 research papers collaboratively examine **Moravec's Paradox**, which posits that skills effortless for humans (like perception and mobility) are computationally difficult for machines, while complex reasoning tasks (like math or chess) are comparatively easy for AI. The Wikipedia entry introduces the paradox, explaining its evolutionary basis: skills acquired over millions of years are deeply encoded and hard to reverse-engineer, while abstract thought is evolutionarily recent and

00:16:05

Characterizing LLM KV Cache Workloads in Production

AI Post Transformers ·

2025/10/01

The June 2025 paper characterizes and optimizes the **Key-Value Cache (KV$)** workload patterns associated with serving large language models (LLMs) at a major cloud provider. Using **real-world production traces** from customer-facing (to-C) and business-facing (to-B) workloads, the authors analyze KV$ reuse behaviors, noting that reuses are significantly skewed, with single-turn requests being as important as multi-turn requests, especially in **API-dominated workloads**. Crucially, the analysis

00:19:43

BurstGPT: A Real-World LLM Serving Workload Dataset

AI Post Transformers ·

2025/10/01

The May 2025 academic paper introduces **BurstGPT**, a novel, real-world workload dataset consisting of over ten million traces from regional Azure OpenAI GPT services collected over 213 days, which aims to optimize Large Language Model (LLM) serving systems. The authors argue that existing LLM serving optimizations are often evaluated using **unrealistic synthetic or non-LLM workloads**, leading to performance degradation in real-world deployments. BurstGPT provides empirical data on **user

Characterizing LLM KV Cache Workloads in Production

AI Post Transformers ·

2025/10/01

The June 2025 paper characterizes and optimizes the Key-Value Cache (KV$) workload patterns associated with serving large language models (LLMs) at a major cloud provider. Using real-world production traces from customer-facing (to-C) and business-facing (to-B) workloads, the authors analyze KV$ reuse behaviors, noting that reuses are significantly skewed, with single-turn requests being as important as multi-turn requests, especially in API-dominated workloads. Crucially, the analysis reveals that

BurstGPT: A Real-World LLM Serving Workload Dataset

AI Post Transformers ·

2025/10/01

The May 2025 academic paper introduces BurstGPT, a novel, real-world workload dataset consisting of over ten million traces from regional Azure OpenAI GPT services collected over 213 days, which aims to optimize Large Language Model (LLM) serving systems. The authors argue that existing LLM serving optimizations are often evaluated using unrealistic synthetic or non-LLM workloads, leading to performance degradation in real-world deployments. BurstGPT provides empirical data on user concurrency

1,015 results

AI Post Transformers

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs