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

Spectral Gap: Analysis of Attention Layers and Graph...

AI Post Transformers ·

2025/11/10

We review two papers on Spectral Gap, one 2021 and another from 2025. The first source presents the Spectral Attention Network (SAN), a novel Transformer-based architecture for graph neural networks that addresses the difficulty of defining positional encodings in graphs by leveraging the full Laplacian spectrum to learn node positions. This approach, which involves a Learned Positional Encoding (LPE), enables the fully-connected Transformer to overcome limitations of traditional Graph Neural

AlphaEvolve: Mathematical Discovery at Scale

AI Post Transformers ·

2025/11/10

The November 3, 2025 paper provide an overview of the AlphaEvolve system, an AI-powered evolutionary approach for mathematical exploration and discovery, often involving large language models (LLMs) to generate and mutate programs that act as search heuristics for finding extremal mathematical objects. The first source is a GitHub repository from Google DeepMind that serves as a collection of 67 mathematical problems used to test AlphaEvolve, noting that the code for the system itself is not

Vidur: Simulation for Efficient LLM Inference Deployment

AI Post Transformers ·

2025/11/10

The May 21, 2024 paper introduces Vidur, a new, high-fidelity simulation framework designed to optimize the deployment and performance of Large Language Model (LLM) inference. The authors explain that experimentally optimizing LLM deployment is prohibitively expensive, requiring exploration of a vast configuration space of system parameters like parallelization strategies and batching techniques, which can cost hundreds of thousands of dollars and thousands of GPU hours. Vidur addresses this by

AdaFlow: Variance-Adaptive Flow-Based Imitation Learning

AI Post Transformers ·

2025/11/10

The November 22, 2024 paper from UT Texas introduces AdaFlow, a novel imitation learning framework designed to improve both the efficiency and diversity of policy generation, addressing computational bottlenecks found in previous diffusion-based methods. AdaFlow utilizes flow-based generative modeling represented by ordinary differential equations (ODEs) and incorporates a variance-adaptive ODE solver that dynamically adjusts the number of inference steps based on the complexity of the state. This

Tempo: SLO-Aware LLM Serving Maximizing Service Gain

AI Post Transformers ·

2025/11/10

The April 24, 2025 academic paper introduces Tempo, a novel scheduling system designed to optimize Large Language Model (LLM) serving by addressing the wide variety of Service Level Objectives (SLOs) in modern LLM applications. The authors categorize requests into three types—latency-sensitive, throughput-intensive, and collective requests—each with distinct performance requirements that existing schedulers fail to manage effectively. Tempo maximizes "service gain" by allocating just

Metacognition and Skill Discovery in LLM Math Reasoning

AI Post Transformers ·

2025/11/10

The May 20, 2024 academic paper explores the metacognitive capabilities of Large Language Models (LLMs), specifically focusing on mathematical problem-solving. The core approach involves developing a method for a powerful LLM, such as GPT-4, to identify and label mathematical questions with specific skills, which are then organized into broader, interpretable categories. This process creates a Skill Exemplar Repository containing skill names matched with question-answer pairs. Experiments validate

Continuous Autoregressive Language Models: CALM

AI Post Transformers ·

2025/11/10

The October 31, 2025 paper introduces Continuous Autoregressive Language Models (CALM), a new paradigm designed to overcome the efficiency bottleneck of traditional Large Language Models (LLMs) by shifting from discrete token-by-token prediction to continuous next-vector prediction. This approach compresses a chunk of multiple tokens into a single continuous vector using a high-fidelity autoencoder, thereby reducing the number of generative steps and significantly improving the performance-compute

LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

AI Post Transformers ·

2025/11/10

The January 30, 2025 paper introduces LLM-AutoDiff, a novel framework for Automatic Prompt Engineering (APE) that allows for the optimization of complex Large Language Model (LLM) workflows. This framework models an entire LLM application—including multiple LLM calls, functional components like retrievers, and cyclical operations—as a directed, auto-differentiable graph. By treating textual inputs as trainable parameters, LLM-AutoDiff uses a separate "backward engine" LLM to generate

A Framework for LLM Application Safety Evaluation

AI Post Transformers ·

2025/11/10

The July 13, 2025 paper " Measuring What Matters: A Framework for Evaluating Safety Risks in Real-World LLM Applications" introduces a practical framework for evaluating safety risks in real-world Large Language Model (LLM) applications, arguing that current methods focusing only on foundation models are inadequate. This framework consists of two main parts: principles for developing customized safety risk taxonomies and practices for evaluating these risks within the application itself,

CARTRIDGE: Efficient In-Context Learning via...

AI Post Transformers ·

2025/11/10

The June 13, 2025 joint collaboration between Stanford University, Caltech and University at Buffalo introduces a novel method called CARTRIDGE for efficiently handling long text corpora in large language models, addressing the high memory cost associated with standard In-Context Learning (ICL) and its required KV cache. A CARTRIDGE is a smaller, trained KV cache representation of a corpus, which is created offline using a technique termed SELF-STUDY. This training process involves generating

Confucius: Intent-Driven Network Management with...

AI Post Transformers ·

2025/11/10

The August 27, 2025 paper introduces Confucius, a novel multi-agent Large Language Model (LLM) framework developed by Meta for intent-driven network management in hyper-scale environments. The framework models complex management tasks as directed acyclic graphs (DAGs) and integrates LLMs with existing tools using domain-specific languages (DSLs) to enhance planning and execution. Confucius leverages Retrieval-Augmented Generation (RAG) for long-term memory and employs specialized primitives like

Context Distillation for Language Models

AI Post Transformers ·

2025/11/10

These five papers from 2022 up to 2025 discuss various knowledge distillation techniques aimed at transferring the capabilities of large language models (LLMs) to smaller, more efficient models, often without the need for explicit context during inference. One paper introduces Contextualization Distillation (CD) for Knowledge Graph Completion (KGC), demonstrating that utilizing LLMs like PaLM2 to generate descriptive context for triplets significantly enhances the performance of smaller, specialized

DSPy and TextGrad: Compiling Language Model Systems

AI Post Transformers ·

2025/11/10

These two academic papers introduce novel programming models aimed at systematically optimizing complex AI systems, particularly those built using Large Language Models (LLMs). The first source presents DSPy, a framework that abstracts traditional, hard-coded LLM pipelines into parameterized, declarative modules that can be automatically optimized using a compiler and teleprompters, demonstrating superior performance compared to hand-crafted prompts on tasks like math word problems. The second

Doubly Stochastic Attention for Transformers

AI Post Transformers ·

2025/11/10

The four papers we review dated from 1967 up to two papers in 2025 collectively discuss the mathematical properties and deep learning applications of doubly stochastic matrices, which are nonnegative matrices whose rows and columns sum to one. One paper, "Concerning Nonnegative Matrices and Doubly Stochastic Matrices," provides the foundational mathematical theory regarding the convergence of iterative row and column scaling (known as the Sinkhorn algorithm) to a unique doubly stochastic

Random Walk Methods for Graph Learning and Networks

AI Post Transformers ·

2025/11/10

We provide a review of the evolution of value of Page Rank to Random Walk with Random Restart and it's application to neural networks focusing on five research papers dating from the original page rank to 2025. They collectively focus on methods for learning on graphs, particularly through the use of Random Walk Neural Networks (RWNNs) and related random walk algorithms. One primary source introduces RWNNs, detailing their architecture, which involves a random walk generating a machine-readable

SYMPHONY: Memory Management for LLM Multi-Turn Inference

AI Post Transformers ·

2025/11/10

The 2024 paper introduces SYMPHONY, a novel system designed to improve memory management and scheduling for Large Language Model (LLM) inference workloads, particularly those involving multi-turn interactions like chatbots and AI agents. The authors, researchers from the University of Texas-Austin and the University of Wisconsin-Madison, explain that existing LLM serving engines either waste computation by recomputing Key-Value (K,V) caches or suffer from load imbalance by offloading caches to host

00:14:57

zFLoRA: Zero-Latency Fused Low-Rank Adapters

AI Post Transformers ·

2025/11/04

The October 28, 2025 Samsung research paper introduces **zFLoRA (zero-latency fused low-rank adapter)**, a novel parameter-efficient fine-tuning (PEFT) method designed to address the significant inference latency overheads associated with current adapter methods like **LoRA** in large language models (LLMs). The core contribution is a carefully engineered fusion of adapter blocks with the base model to achieve **zero or negligible latency overhead** during inference, leveraging optimized matrix

00:13:32

SuperBPE: Space Travel for Language Models

AI Post Transformers ·

2025/11/04

The August 26, 2025 collaboration between the University of Washington, NVIDIA and the Allen Institute for AI paper introduces **"SuperBPE: Space Travel for Language Models,"** introduces **SuperBPE**, a novel tokenization method that challenges the standard practice of limiting tokens to subword boundaries. The authors argue that conventional **Byte-Pair Encoding (BPE)** is inefficient because it cannot create "superword" tokens that bridge whitespace, ignoring common multi-word expressions that

00:15:26

Google: Supervised Reinforcement Learning for...

AI Post Transformers ·

2025/11/04

The October 29 2025 Google research paper introduces **Supervised Reinforcement Learning (SRL)**, a novel framework designed to improve the complex, multi-step reasoning abilities of large language models (LLMs). The core issue addressed is that conventional training methods like **Supervised Fine-Tuning (SFT)** and outcome-based **Reinforcement Learning with Verifiable Rewards (RLVR)** struggle with difficult problems because they either overfit rigid expert paths or receive only sparse,

00:13:52

MorphKV: Constant-Sized KV Caches for LLM Inference

AI Post Transformers ·

2025/11/04

The June 7, 2025 UT Austin and University of British Colombia collaboration academic paper introduces **MorphKV**, a novel inference-time technique designed to address the excessive memory consumption caused by Key-Value (KV) caches in Large Language Models (LLMs) during extended responses. The core problem is that KV cache size grows linearly with sequence length, straining GPU memory, leading to prior methods sacrificing accuracy by dropping context or using lossy compression. MorphKV resolves

990 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