Explaining GPT 5
ai_nerd
Explaining GPT 5
7:13
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
ai_nerd
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
5:31
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
ai_nerd
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
5:48
GPT 5.1
ai_nerd
GPT 5.1
5:30
Titans of AI: Pioneers Discussing the Future of Intelligence
ai_nerd
Titans of AI: Pioneers Discussing the Future of Intelligence
7:52
Hierarchical Reasoning
ai_nerd
Hierarchical Reasoning
5:44
Nested Learning: The Illusion of Deep Learning
ai_nerd
Nested Learning: The Illusion of Deep Learning
7:22
AI Generated Synopsis: NVIDIA GTC 2025 Keynote with Jensen Huang
ai_nerd
AI Generated Synopsis: NVIDIA GTC 2025 Keynote with Jensen Huang
7:55
Training Proactive and Personalized LLM Agents
ai_nerd
Training Proactive and Personalized LLM Agents
5:19
Scaling Agent Learning via Experience Synthesis
ai_nerd
Scaling Agent Learning via Experience Synthesis
6:11
The Nadella Doctrine
ai_nerd
The Nadella Doctrine
6:38
EMNLP 2025: Recap
ai_nerd
EMNLP 2025: Recap
8:23
Context Engineering
ai_nerd
Context Engineering
6:06
Completion ≠ Collaboration
ai_nerd
Completion ≠ Collaboration
4:43
SPICE How AI Teaches Itself
ai_nerd
SPICE How AI Teaches Itself
5:58
Multi Agent Evolve
ai_nerd
Multi Agent Evolve
5:09
The State of AI NeurIPS 2025
ai_nerd
The State of AI NeurIPS 2025
9:41
AI Reshaping Software Development: The Engineer We Need
ai_nerd
AI Reshaping Software Development: The Engineer We Need
6:00
The Maturation of Language Modeling: COLM 2025 Progress Report
ai_nerd
The Maturation of Language Modeling: COLM 2025 Progress Report
7:56
Prompt-MII: Meta-Learning Instruction Induction for LLMs
ai_nerd
Prompt-MII: Meta-Learning Instruction Induction for LLMs
5:45
BAYESIAN INFLUENCE FUNCTIONS FOR HESSIAN-FREE DATAATTRIBUTION
ai_nerd
BAYESIAN INFLUENCE FUNCTIONS FOR HESSIAN-FREE DATAATTRIBUTION
5:26
Reasoning with Sampling:Your Base Model is Smarter Than You Think
ai_nerd
Reasoning with Sampling:Your Base Model is Smarter Than You Think
7:48
Missing Premise exacerbates Overthinking:Are Reasoning Models losing Critical Thinking Skill?
ai_nerd
Missing Premise exacerbates Overthinking:Are Reasoning Models losing Critical Thinking Skill?
7:09
Agent Learning Early Experience
ai_nerd
Agent Learning Early Experience
5:40
The Art of Scaling Reinforcement Learning Compute for LLMs
ai_nerd
The Art of Scaling Reinforcement Learning Compute for LLMs
6:11
RLP: Reinforcement as a Pretraining Objective
ai_nerd
RLP: Reinforcement as a Pretraining Objective
5:53
Less is More: Recursive Reasoning with Tiny Networks
ai_nerd
Less is More: Recursive Reasoning with Tiny Networks
6:36
Agentic Context Engineering: Evolving Contexts for Self-ImprovingLanguage Models
ai_nerd
Agentic Context Engineering: Evolving Contexts for Self-ImprovingLanguage Models
7:11