x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

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

Generalist Reward Modeling with Inference-Time Scaling

AI Post Transformers ·

2025/09/16

This April 2025 paper introduces Self-Principled Critique Tuning (SPCT), a novel method designed to enhance the inference-time scalability of Generative Reward Models (GRMs) for various domains. It details how SPCT, through a combination of rejective fine-tuning and rule-based online reinforcement learning, facilitates the adaptive generation of principles and critiques, thereby improving the quality and inference-time scalability of GRMs. The paper compares different reward generation paradigms

en

00:19:24

AWQ: On-Device LLM Compression and Acceleration

AI Post Transformers ·

2025/09/15

This July 2024 paper introduces Activation-aware Weight Quantization (AWQ), a novel method for compressing Large Language Models (LLMs) by quantizing weights to low-bit integers for efficient deployment on edge devices. It highlights that AWQ identifies and protects crucial "salient" weights by observing activation distributions, which significantly reduces quantization error without requiring computationally intensive training or overfitting to specific datasets. Complementing AWQ, the paper also

en

00:22:58

HybridServe: Efficient LLM Inference with Hybrid Caching

AI Post Transformers ·

2025/09/15

This January 2025 paper introduces HybridServe, an LLM inference system designed to enhance throughput and cost-effectiveness for large language models by optimizing memory usage and host-GPU communication. It tackles the challenges of host memory offloading, where model parameters and KV cache are stored on slower host memory to reduce costs but can lead to GPU underutilization due to limited transfer bandwidth. HybridServe proposes a novel activation checkpointing technique with a KV-Activation

en

00:20:20

FlexGen: High-Throughput LLM Inference on a Single GPU

AI Post Transformers ·

2025/09/15

This June 2023 paper introduces FlexGen, a novel high-throughput generation engine designed to overcome the substantial computational and memory demands of large language model (LLM) inference on limited hardware, specifically a single commodity GPU. It details FlexGen's ability to aggregate memory and computation across the GPU, CPU, and disk, employing an optimized scheduling approach and a linear programming-based policy search to store and access tensors efficiently. Furthermore, FlexGen

en

00:26:38

GraphSAGE: Inductive Representation Learning on Large...

AI Post Transformers ·

2025/09/15

This September 2018 paper introduces GraphSAGE, a novel inductive framework designed to generate node embeddings for large, evolving graphs, addressing limitations of prior transductive methods that struggle with unseen data. Instead of learning a specific embedding for each node, GraphSAGE learns a function that generates these embeddings by sampling and aggregating features from a node's local neighborhood. The authors evaluate various aggregator architectures, including mean, LSTM, and pooling

en

00:17:23

MetaGraph: knowledge graphs from financial NLP

AI Post Transformers ·

2025/09/15

This September 2025 paper presents MetaGraph, a novel methodology for constructing knowledge graphs from scientific literature, specifically applied to Financial Natural Language Processing (NLP) research between 2022 and 2025. The authors utilized Large Language Models (LLMs) to extract key information from 681 papers, including tasks, datasets, models, motivations, and limitations, and organized it into a structured, queryable format. The analysis highlights three phases in Financial NLP's

en

00:19:10

Hallucination to Truth: A Review of Fact-Checking and...

AI Post Transformers ·

2025/09/15

This August 2025 paper explores the critical area of fact-checking and factuality evaluation in Large Language Models (LLMs). It systematically analyzes the challenges of misinformation generation, particularly hallucinations, which are factually incorrect but fluent outputs from LLMs. The paper investigates various mitigation strategies, including fine-tuning, instruction tuning, and Retrieval-Augmented Generation (RAG), which grounds LLM outputs in external knowledge. It further

en

00:15:58

The Illusion of Diminishing Returns in LLM Execution

AI Post Transformers ·

2025/09/15

This September 2025 paper explores the concept of long-horizon execution in Large Language Models (LLMs), arguing that marginal gains in single-step accuracy can lead to exponential improvements in the length of tasks LLMs can complete. The authors introduce a novel framework to isolate execution capabilities by providing models with necessary knowledge and plans, revealing that larger models can execute significantly more steps, even when smaller models achieve perfect single-turn accuracy. A key

en

Hallucination to Truth: A Review of Fact-Checking and...

AI Post Transformers ·

2025/09/15

This August 2025 paper explores the critical area of fact-checking and factuality evaluation in Large Language Models (LLMs). It systematically analyzes the challenges of misinformation generation, particularly hallucinations, which are factually incorrect but fluent outputs from LLMs. The paper investigates various mitigation strategies, including fine-tuning, instruction tuning, and Retrieval-Augmented Generation (RAG), which grounds LLM outputs in external knowledge. It further examines

en

FlexGen: High-Throughput LLM Inference on a Single GPU

AI Post Transformers ·

2025/09/15

This June 2023 paper introduces FlexGen, a novel high-throughput generation engine designed to overcome the substantial computational and memory demands of large language model (LLM) inference on limited hardware, specifically a single commodity GPU. It details FlexGen's ability to aggregate memory and computation across the GPU, CPU, and disk, employing an optimized scheduling approach and a linear programming-based policy search to store and access tensors efficiently. Furthermore, FlexGen

en

MetaGraph: knowledge graphs from financial NLP

AI Post Transformers ·

2025/09/15

This September 2025 paper presents MetaGraph, a novel methodology for constructing knowledge graphs from scientific literature, specifically applied to Financial Natural Language Processing (NLP) research between 2022 and 2025. The authors utilized Large Language Models (LLMs) to extract key information from 681 papers, including tasks, datasets, models, motivations, and limitations, and organized it into a structured, queryable format. The analysis highlights three phases in Financial NLP's

en

PyTorch FSDP: Scaling Fully Sharded Data Parallel

AI Post Transformers ·

2025/09/15

This September 2023 paper introduces PyTorch Fully Sharded Data Parallel (FSDP), an advanced solution designed to scale the training of exceptionally large machine learning models. It addresses limitations of previous methods like Distributed Data Parallel (DDP) by sharding model parameters, gradients, and optimizer states across multiple GPUs, thereby drastically reducing individual GPU memory consumption. FSDP employs various techniques, including deferred initialization, flexible sharding

en

GraphSAGE: Inductive Representation Learning on Large...

AI Post Transformers ·

2025/09/15

This September 2018 paper introduces GraphSAGE, a novel inductive framework designed to generate node embeddings for large, evolving graphs, addressing limitations of prior transductive methods that struggle with unseen data. Instead of learning a specific embedding for each node, GraphSAGE learns a function that generates these embeddings by sampling and aggregating features from a node's local neighborhood. The authors evaluate various aggregator architectures, including mean, LSTM, and

en

HybridServe: Efficient LLM Inference with Hybrid Caching

AI Post Transformers ·

2025/09/15

This January 2025 paper introduces HybridServe, an LLM inference system designed to enhance throughput and cost-effectiveness for large language models by optimizing memory usage and host-GPU communication. It tackles the challenges of host memory offloading, where model parameters and KV cache are stored on slower host memory to reduce costs but can lead to GPU underutilization due to limited transfer bandwidth. HybridServe proposes a novel activation checkpointing technique with a KV-Activation

en

The Illusion of Diminishing Returns in LLM Execution

AI Post Transformers ·

2025/09/15

This September 2025 paper explores the concept of long-horizon execution in Large Language Models (LLMs), arguing that marginal gains in single-step accuracy can lead to exponential improvements in the length of tasks LLMs can complete. The authors introduce a novel framework to isolate execution capabilities by providing models with necessary knowledge and plans, revealing that larger models can execute significantly more steps, even when smaller models achieve perfect single-turn accuracy. A key

en

AWQ: On-Device LLM Compression and Acceleration

AI Post Transformers ·

2025/09/15

This July 2024 paper introduces Activation-aware Weight Quantization (AWQ), a novel method for compressing Large Language Models (LLMs) by quantizing weights to low-bit integers for efficient deployment on edge devices. It highlights that AWQ identifies and protects crucial "salient" weights by observing activation distributions, which significantly reduces quantization error without requiring computationally intensive training or overfitting to specific datasets. Complementing AWQ, the

en

00:19:56

PyTorch FSDP: Scaling Fully Sharded Data Parallel

AI Post Transformers ·

2025/09/15

This September 2023 paper introduces PyTorch Fully Sharded Data Parallel (FSDP), an advanced solution designed to scale the training of exceptionally large machine learning models. It addresses limitations of previous methods like Distributed Data Parallel (DDP) by sharding model parameters, gradients, and optimizer states across multiple GPUs, thereby drastically reducing individual GPU memory consumption. FSDP employs various techniques, including deferred initialization, flexible sharding

en

00:22:28

Llama 3: Architecture, Capabilities, and Safety

AI Post Transformers ·

2025/09/14

On this November 2025 paper the Meta Llama Team's paper introduces Llama 3, a new family of large language models featuring 8B, 70B, and 405B parameters, designed with native multilingual support, coding, reasoning, and tool usage capabilities. The development emphasizes data quality and diversity, employing extensive filtering, de-duplication, and heuristic cleaning processes for both English and multilingual data, alongside scaling laws to optimize model size and training budgets. The models

en

00:15:49

Graph Patterns of Knowledge in Large Language Models

AI Post Transformers ·

2025/09/14

This May 2025 paper explores the structural patterns of knowledge within Large Language Models (LLMs) by adopting a graph-based perspective. The authors quantify LLM knowledge at both the triplet and entity levels, analyzing its relationship with graph properties like node degree. Key findings include the discovery of knowledge homophily, where closely connected entities exhibit similar knowledgeability, and a positive correlation between an entity's degree and its knowledge. These insights further

en

Llama 3: Architecture, Capabilities, and Safety

AI Post Transformers ·

2025/09/14

On this November 2025 paper the Meta Llama Team's paper introduces Llama 3, a new family of large language models featuring 8B, 70B, and 405B parameters, designed with native multilingual support, coding, reasoning, and tool usage capabilities. The development emphasizes data quality and diversity, employing extensive filtering, de-duplication, and heuristic cleaning processes for both English and multilingual data, alongside scaling laws to optimize model size and training budgets. The models

en

1,015 results

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