LLMs Research Podcast
by LLMs Research
Latest episode
Your 70-Billion-Parameter Model Might Be 40% Wasted
Your 70-Billion-Parameter Model Might Be 40% Wasted
About this podcast
Podcast covering important research papers of large language models.
llmsresearch.substack.com
Episodes
- Your 70-Billion-Parameter Model Might Be 40% Wasted · 12 min · Season 1 Episode 7Your 70-Billion-Parameter Model Might Be 40% Wasted Three papers from February 1–6, 2026 converge on a question the field has been avoiding since 2016: what if most transformer…
- Fixing Reasoning from Three Directions at Once · 13 min · Season 1 Episode 6Fixing Reasoning from Three Directions at OnceLLMs Research Podcast | Episode: Feb 1–6, 2026 DeepSeek-R1 made RL the default approach for reasoning. This episode covers the 30…
- Mamba's Memory Problem · 7 min · Season 2 Episode 3State space models like Mamba promised linear scaling and constant memory. They delivered on efficiency, but researchers kept hitting the same wall: ask Mamba to recall something…
- What ICLR 2026 Taught Us About Multi-Agent Failures · 17 min · Season 1 Episode 5Episode Title: What ICLR 2026 Taught Us About Multi-Agent Failures Episode Summary: We scanned ICLR 2026 accepted papers and found 14 that address real problems when building…
- The Evolution of Long-Context LLMs: From 512 to 10M Tokens · 16 min · Season 2 Episode 2The podcast discusses the technical shift in large language models from a standard 512-token context window to modern architectures capable of processing millions of tokens…
- Jan 17–23, 2026: The Rise of the Action Layer · 16 min · Season 1 Episode 4Jan 17–23, 2026: The Rise of the Action LayerHow multimodal AI is shifting from passive perception to active controlThe current landscape of research reflects a shift toward…
- From Transformers to Autonomous Agents: A Timeline of the Research That Got Us Here · 25 min · Season 2 Episode 1Over the past several years, we have moved from the machine learning era through the large language model era and into what researchers now call the agent era. But we did not…
- LLM Research Highlights: January 10th to 16th, 2026 · 23 min · Season 1 Episode 3The focus of LLM research is undergoing a significant shift from simply increasing model size to making existing capabilities practically usable for deployment. This week’s…
- LLM Research Highlights: January 2nd to 9th, 2026 · 18 min · Season 1 Episode 2Key takeaway from todays podcast: Robust Reasoning: The Holonomic Network achieves perfect fidelity extrapolation 100x beyond training lengths, demonstrating a new universality…
- LLM Research Highlights: December 27, 2025 – January 2, 2026 · 16 min · Season 1 Episode 1* Bayesian & Cognitive Advances: Transformers achieve ultra-precise Bayesian inference with 10⁻³ to 10⁻⁴ bit accuracy, while CREST boosts reasoning accuracy by 17.5% and cuts…








