Podcast Episodes
Back to Search
Language Models Can Control Their Own Attention
Researchers have introduced Declarative Attention (DA), a protocol that enables large language models to autonomously manage their own focus during l…
15 hours ago
AI Finds A Way
This paper introduces a comprehensive collection of anecdotes documenting instances where artificial intelligence systems developed innovative yet un…
1 day, 16 hours ago
Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
This research paper investigates how feature entanglement in large language models prevents precise, localized interventions on specific concepts. Th…
2 days, 12 hours ago
TTPO: Test-Time Policy Optimization
This paper introduces Test-Time Policy Optimization (TTPO), a novel method for improving the mathematical reasoning of large language models without …
3 days, 6 hours ago
Demystifying Reinforcement Learning Post-Training of Language Models
This paper deconstructs the mechanics of reinforcement learning (RL) post-training for large language models to determine how different factors influ…
4 days, 19 hours ago
Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
Recuris is a recursive architectural framework designed to enhance the performance of large language model agents during complex, long-horizon tasks.…
5 days, 15 hours ago
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Researchers introduce TailSFT, a modified supervised fine-tuning algorithm designed to better prepare language models for subsequent reinforcement le…
6 days, 10 hours ago
SPADE: Self-Play in Adaptive Synthetic Executable Environments
This paper introduces SPADE, a reinforcement learning framework that enables a single large language model to achieve open-ended self-improvement by …
1 week ago
Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills
This paper introduces ACES (Agentic Continuous Evaluation of Skills), a comprehensive framework developed by NVIDIA to move beyond static document sc…
1 week, 3 days ago
Impression Share Prediction: An Offline Evaluation Task for Ranking Systems
Researchers from Meta Platforms propose a novel offline evaluation task called impression share prediction to better anticipate how new ranking model…
1 week, 4 days ago