ZARZA We are Zarza, the prestigious firm behind major projects in information technology.

Best AI papers explained

Por: Enoch H. Kang

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

620 episodios disponibles

Latest episodes of the podcast Best AI papers explained

Mostrando página 31 de 31

Inductive Biases for Exchangeable Sequence Modeling 26/03/2025

InverseRLignment: LLM Alignment via Inverse Reinforcement Learning 26/03/2025

Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting 26/03/2025

Alignment from Demonstrations for Large Language Models 25/03/2025

Q♯: Distributional RL for Optimal LLM Post-Training 18/03/2025

Scaling Test-Time Compute Without Verification or RL is Suboptimal 14/03/2025

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning 14/03/2025

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning 14/03/2025

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback 14/03/2025

Revisiting Superficial Alignment Hypothesis 14/03/2025

Diagnostic uncertainty: teaching language Models to describe open-ended uncertainty 14/03/2025

Language Model Personalization via Reward Factorization 14/03/2025

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration 14/03/2025

How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach 14/03/2025

Can Large Language Models Extract Customer Needs as well as Professional Analysts? 13/03/2025

Spurlens: finding spurious correlations in Multimodal llms 13/03/2025

Improving test-time search with backtrack- Ing Improving test-time search with backtrack- Ing against in-context value verifiersagainst in-context value verifiers 13/03/2025

Adaptive elicitation of latent information Using natural language 13/03/2025

Document Valuation in LLM Summaries: A Cluster Shapley Approach 13/03/2025

s1: simple test time scaling 13/03/2025

« Primera ‹ Anterior 1 ... 29 30 31