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

00:15:14

GDPval: Measuring AI Performance on Real-World Work

AI Post Transformers ·

2025/09/26

The September 25 2025 dated sources introduce **GDPval**, a novel benchmark created by OpenAI to evaluate the performance of **AI models** on **economically valuable, real-world tasks**. This evaluation spans **44 knowledge work occupations** across the top nine sectors contributing to the U.S. GDP, using tasks meticulously crafted by experienced industry professionals. Results indicate that the best **frontier models** are approaching human expert quality on these tasks, with models like Claude

00:34:53

Adaptive Compression Techniques for Efficient LLM...

AI Post Transformers ·

2025/09/20

These 14 research papers provide an overview of various **compression techniques for Large Language Models (LLMs)**, primarily focusing on **reducing the size and computational overhead of the Key-Value (KV) cache** to handle long contexts more efficiently. Several novel methods are detailed, including **GVote**, an adaptive compression algorithm using query sampling and voting to find an optimal cache budget, and **SnapKV**, which selects clustered, important KV positions based on an "observation"

00:15:38

LLM-I: Interleaved Multimodal Creators via Tool-Use

AI Post Transformers ·

2025/09/20

The September 2025 academic paper introduces **LLM-Interleaved (LLM-I)**, a novel, flexible framework for interleaved image-text generation that reframes the task as a **tool-use problem** to overcome the "one-tool" limitation of unified models. Authored by researchers from Zhejiang University and **ByteDance, BandAI**, the system uses a central Large Language Model (LLM) or Multimodal LLM (MLLM) agent to orchestrate a diverse toolkit of specialized visual tools, including online image search,

LLM-I: Interleaved Multimodal Creators via Tool-Use

AI Post Transformers ·

2025/09/20

The September 2025 academic paper introduces LLM-Interleaved (LLM-I), a novel, flexible framework for interleaved image-text generation that reframes the task as a tool-use problem to overcome the "one-tool" limitation of unified models. Authored by researchers from Zhejiang University and ByteDance, BandAI, the system uses a central Large Language Model (LLM) or Multimodal LLM (MLLM) agent to orchestrate a diverse toolkit of specialized visual tools, including online image search,

Adaptive Compression Techniques for Efficient LLM...

AI Post Transformers ·

2025/09/20

These 14 research papers provide an overview of various compression techniques for Large Language Models (LLMs), primarily focusing on reducing the size and computational overhead of the Key-Value (KV) cache to handle long contexts more efficiently. Several novel methods are detailed, including GVote, an adaptive compression algorithm using query sampling and voting to find an optimal cache budget, and SnapKV, which selects clustered, important KV positions based on an "observation" window