Podcast Episodes

Back to Search
TheoryCoder: Bilevel Planning with Synthesized World Models
TheoryCoder: Bilevel Planning with Synthesized World Models

This research paper introduces TheoryCoder, a novel reinforcement learning agent. TheoryCoder integrates large language models (LLMs) for synthesizin…

1 year, 5 months ago

Short Long
View Episode
Driving Forces in AI: Scaling to 2025 and Beyond (Jason Wei, OpenAI)
Driving Forces in AI: Scaling to 2025 and Beyond (Jason Wei, OpenAI)

This conversation discusses the presentation from Jason Wei at OpenAI, who explores the driving forces behind recent rapid progress in artificial int…

1 year, 5 months ago

Short Long
View Episode
Expert Demonstrations for Sequential Decision Making under Heterogeneity
Expert Demonstrations for Sequential Decision Making under Heterogeneity

This paper introduces a new framework called Experts-as-Priors (ExPerior). This framework addresses the challenge of sequential decision-making in si…

1 year, 5 months ago

Short Long
View Episode
TextGrad: Backpropagating Language Model Feedback for Generative AI Optimization
TextGrad: Backpropagating Language Model Feedback for Generative AI Optimization

This paper introduces TextGrad, a novel framework for optimizing generative AI systems. This method uses large language models (LLMs) to provide natu…

1 year, 5 months ago

Short Long
View Episode
MemReasoner: Generalizing Language Models on Reasoning-in-a-Haystack Tasks
MemReasoner: Generalizing Language Models on Reasoning-in-a-Haystack Tasks

This paper aims to improve reasoning capabilities over long contextual information by learning the relative order of facts and enabling selective att…

1 year, 5 months ago

Short Long
View Episode
RAFT: In-Domain Retrieval-Augmented Fine-Tuning for Language Models
RAFT: In-Domain Retrieval-Augmented Fine-Tuning for Language Models

This paper introduces Retrieval Augmented Fine Tuning (RAFT), a novel training method designed to improve large language models' ability to answer qu…

1 year, 5 months ago

Short Long
View Episode
Inductive Biases for Exchangeable Sequence Modeling
Inductive Biases for Exchangeable Sequence Modeling

This paper explores inductive biases in exchangeable sequence modeling, focusing on architectural choices and inferential methods, particularly for d…

1 year, 5 months ago

Short Long
View Episode
InverseRLignment: LLM Alignment via Inverse Reinforcement Learning
InverseRLignment: LLM Alignment via Inverse Reinforcement Learning

This paper introduces a novel approach called Alignment from Demonstrations (AfD) for aligning large language models (LLMs) using demonstration datas…

1 year, 5 months ago

Short Long
View Episode
Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting
Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting

This paper introduces Prompt-OIRL, a novel method to enhance the arithmetic reasoning of large language models by optimizing prompts based on individ…

1 year, 5 months ago

Short Long
View Episode
Alignment from Demonstrations for Large Language Models
Alignment from Demonstrations for Large Language Models

The provided text is a research paper introducing Alignment from Demonstrations (AfD) as a novel method for aligning large language models (LLMs) usi…

1 year, 5 months ago

Short Long
View Episode

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us