Best AI papers explained
En podkast av Enoch H. Kang - Fredager
203 Episoder
-
TextGrad: Backpropagating Language Model Feedback for Generative AI Optimization
Publisert: 27.3.2025 -
MemReasoner: Generalizing Language Models on Reasoning-in-a-Haystack Tasks
Publisert: 27.3.2025 -
RAFT: In-Domain Retrieval-Augmented Fine-Tuning for Language Models
Publisert: 27.3.2025 -
Inductive Biases for Exchangeable Sequence Modeling
Publisert: 26.3.2025 -
InverseRLignment: LLM Alignment via Inverse Reinforcement Learning
Publisert: 26.3.2025 -
Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting
Publisert: 26.3.2025 -
Alignment from Demonstrations for Large Language Models
Publisert: 25.3.2025 -
Q♯: Distributional RL for Optimal LLM Post-Training
Publisert: 18.3.2025 -
Scaling Test-Time Compute Without Verification or RL is Suboptimal
Publisert: 14.3.2025 -
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Publisert: 14.3.2025 -
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Publisert: 14.3.2025 -
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Publisert: 14.3.2025 -
Revisiting Superficial Alignment Hypothesis
Publisert: 14.3.2025 -
Diagnostic uncertainty: teaching language Models to describe open-ended uncertainty
Publisert: 14.3.2025 -
Language Model Personalization via Reward Factorization
Publisert: 14.3.2025 -
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
Publisert: 14.3.2025 -
How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
Publisert: 14.3.2025 -
Can Large Language Models Extract Customer Needs as well as Professional Analysts?
Publisert: 13.3.2025 -
Spurlens: finding spurious correlations in Multimodal llms
Publisert: 13.3.2025 -
Improving test-time search with backtrack- Ing Improving test-time search with backtrack- Ing against in-context value verifiersagainst in-context value verifiers
Publisert: 13.3.2025
Men know other men best. Women know other women best. And yes, perhaps AIs know other AIs best. AI explains what you should know about this week's AI research progress.
