Imagen de portada del espectáculo Artificial Discourse

Artificial Discourse

Podcast de Kenpachi

inglés

Tecnología y ciencia

Oferta limitada

2 meses por 1 €

Después 4,99 € / mesCancela cuando quieras.

  • 20 horas de audiolibros / mes
  • Podcasts solo en Podimo
  • Podcast gratuitos
Empezar

Acerca de Artificial Discourse

Artificial Discourse is a podcast where two advanced AIs explore the latest research papers across various fields. Each episode features engaging discussions that simplify complex concepts and highlight their implications. Tune in for unique insights and a fresh perspective on academic research!

Todos los episodios

41 episodios

Portada del episodio Stronger Models are NOT Stronger Teachers for Instruction Tuning

Stronger Models are NOT Stronger Teachers for Instruction Tuning

This research paper investigates the impact of different language models (LLMs) used as "teachers" to generate synthetic responses for instruction tuning. The authors demonstrate a surprising phenomenon they call the "Larger Models' Paradox," where larger and supposedly "stronger" teacher models do not always lead to improved instruction-following abilities in smaller base models. They propose a novel metric called Compatibility-Adjusted Reward (CAR) to better predict the effectiveness of teacher models, taking into account the compatibility between the teacher and the base model being fine-tuned. The study challenges the common assumption that larger LLMs are always better teachers and suggests that a more nuanced understanding of compatibility is needed for successful instruction tuning.

25 de nov de 2024 - 13 min
Portada del episodio Large Language Models Can Self-Improve in Long-context Reasoning

Large Language Models Can Self-Improve in Long-context Reasoning

This research paper investigates the potential for large language models (LLMs) to self-improve in long-context reasoning, which involves processing and understanding complex information spread across long stretches of text. The authors propose a novel approach called SEALONG that leverages the LLMs' ability to generate multiple outputs for a given question and then scores these outputs using a method called Minimum Bayes Risk (MBR). The MBR approach prioritizes outputs that align better with each other, thereby filtering out outputs that might be incorrect or hallucinatory. SEALONG then uses these high-scoring outputs for further training, either through supervised fine-tuning or preference optimization. The authors demonstrate through extensive experiments that SEALONG significantly improves the long-context reasoning performance of LLMs without requiring expert model annotations or human labeling.

22 de nov de 2024 - 11 min
Portada del episodio LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models, introduces a new method for generating 3D models using large language models (LLMs). The authors address the challenge of tokenizing 3D mesh data for LLMs by representing the mesh data as plain text using the OBJ file format, a standard text-based format for 3D models. This approach allows for direct integration with LLMs without modifying the vocabulary or tokenizers, minimizing additional training overhead. The study then introduces LLAMA-MESH, a fine-tuned LLaMA model that can generate 3D meshes from textual prompts, produce interleaved text and 3D mesh outputs, and understand and interpret 3D meshes. LLAMA-MESH achieves comparable mesh generation quality to models trained from scratch while maintaining strong text generation abilities, demonstrating the potential for LLMs to become universal generative tools for multiple modalities.

21 de nov de 2024 - 18 min
Soy muy de podcasts. Mientras hago la cama, mientras recojo la casa, mientras trabajo… Y en Podimo encuentro podcast que me encantan. De emprendimiento, de salid, de humor… De lo que quiera! Estoy encantada 👍
Soy muy de podcasts. Mientras hago la cama, mientras recojo la casa, mientras trabajo… Y en Podimo encuentro podcast que me encantan. De emprendimiento, de salid, de humor… De lo que quiera! Estoy encantada 👍
MI TOC es feliz, que maravilla. Ordenador, limpio, sugerencias de categorías nuevas a explorar!!!
Me suscribi con los 14 días de prueba para escuchar el Podcast de Misterios Cotidianos, pero al final me quedo mas tiempo porque hacia tiempo que no me reía tanto. Tiene Podcast muy buenos y la aplicación funciona bien.
App ligera, eficiente, encuentras rápido tus podcast favoritos. Diseño sencillo y bonito. me gustó.
contenidos frescos e inteligentes
La App va francamente bien y el precio me parece muy justo para pagar a gente que nos da horas y horas de contenido. Espero poder seguir usándola asiduamente.

Elige tu suscripción

Más populares

Oferta limitada

Premium

20 horas de audiolibros

  • Podcasts solo en Podimo

  • Disfruta los shows de Podimo sin anuncios

  • Cancela cuando quieras

2 meses por 1 €
Después 4,99 € / mes

Empezar

Premium Plus

100 horas de audiolibros

  • Podcasts solo en Podimo

  • Disfruta los shows de Podimo sin anuncios

  • Cancela cuando quieras

Disfruta 30 días gratis
Después 9,99 € / mes

Prueba gratis

Sólo en Podimo

Audiolibros populares

Empezar

2 meses por 1 €. Después 4,99 € / mes. Cancela cuando quieras.