About this podcast
Daily podcast about the published articles in the LLM field.
Episodes
The newest 20 of 49 episodes
- Marco-o1 · 15 min · Season 1 Episode 49🤖 Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions The Alibaba MarcoPolo team presents Marco-o1, a large reasoning model designed to excel in open-ended…
- Scaling Laws for Precision · 19 min · Season 1 Episode 48⚖️ Scaling Laws for Precision This research paper investigates the impact of precision in training and inference on the performance of large language models. The authors explore…
- Test-Time Training · 15 min · Season 1 Episode 47⌛️ The Surprising Effectiveness of Test-Time Training for Abstract Reasoning This paper examines how test-time training (TTT) can enhance the abstract reasoning abilities of…
- Qwen2.5-Coder · 24 min · Season 1 Episode 46🔷 Qwen2.5-Coder Technical Report The report introduces the Qwen2.5-Coder series, which includes the Qwen2.5-Coder-1.5B and Qwen2.5-Coder-7B models. These models are specifically…
- Attacking Vision-Language Computer Agents via Pop-ups · 22 min · Season 1 Episode 45😈 Attacking Vision-Language Computer Agents via Pop-ups This research paper examines vulnerabilities in vision-language models (VLMs) that power autonomous agents performing…
- Number Cookbook · 16 min · Season 1 Episode 44📓 Number Cookbook: Number Understanding of Language Models and How to Improve It This research paper examines the numerical understanding and processing abilities (NUPA) of…
- Jigsaw Puzzles · 17 min · Season 1 Episode 43🧩 Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models This research paper investigates the vulnerabilities of large language models (LLMs) to…
- Multi-expert Prompting with LLMs · 13 min · Season 1 Episode 42🤝 Multi-expert Prompting with LLMs The research paper presents Multi-expert Prompting, a novel method for improving the reliability, safety, and usefulness of Large Language…
- Investigating the Role of Prompting and External Tools in Hallucination Rates of LLMs · 16 min · Season 1 Episode 41🔎 Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models This paper examines the effectiveness of different prompting techniques…
- Mind Your Step (by Step) · 17 min · Season 1 Episode 40🌀 Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse This research paper examines how chain-of-thought (CoT)…
- SimpleQA · 18 min · Season 1 Episode 39❓Measuring short-form factuality in large language models This document introduces SimpleQA, a new benchmark for evaluating the factuality of large language models. The…
- GPT-4o System Card · 24 min · Season 1 Episode 38📜 GPT-4o System Card This technical document is the System Card for OpenAI's GPT-4o, a multimodal, autoregressive language model that can process and generate text, audio…
- Mixture of Parrots · 11 min · Season 1 Episode 37🦜 Mixture of Parrots: Experts improve memorization more than reasoning This research paper investigates the effectiveness of Mixture-of-Experts (MoE) architectures in deep…
- Improve Vision Language Model Chain-of-thought Reasoning · 16 min · Season 1 Episode 36🖼 Improve Vision Language Model Chain-of-thought Reasoning This research paper investigates how to improve the chain-of-thought (CoT) reasoning capabilities of vision language…
- Breaking the Memory Barrier · 16 min · Season 1 Episode 35🧠 Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss This research paper introduces Inf-CL, a novel approach for contrastive learning that…
- LLMs Reflect the Ideology of their Creators · 11 min · Season 1 Episode 34⚖️ Large Language Models Reflect the Ideology of their Creators This study examines the ideological stances of large language models (LLMs) by analyzing their responses to…
- LongRAG · 18 min · Season 1 Episode 33📜 LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering The source is a research paper that proposes a new approach called…
- A Theoretical Understanding of Chain-of-Thought · 10 min · Season 1 Episode 32⛓️ A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration The paper explores Chain-of-Thought (CoT) prompting, a method to enhance the…
- A Survey on Data Synthesis and Augmentation for Large Language Models · 21 min · Season 1 Episode 31📚 A Survey on Data Synthesis and Augmentation for Large Language Models This research paper examines the use of synthetic and augmented data to enhance the capabilities of Large…
- Revealing the Barriers of Language Agents in Planning · 9 min · Season 1 Episode 30🤔 Revealing the Barriers of Language Agents in Planning This research paper examines the challenges faced by language agents in planning tasks. The authors explore the reasons…
