AI Papers AcademyMeta AI Empowers LLMs to Reason in Their Own LanguageDiscover how Meta AI’s Chain of Continuous Thought (Coconut) empowers large language models (LLMs) to reason in their own language.5h ago
InTowards Data SciencebyMatthew GuntonHow to Improve Model Quality Without Building Larger ModelsGoing into the Google DeepMind’s “Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters”Oct 84
Nilesh BarlaA short note on Reinforced Fine-Tuning or ReFTLLMs still lack strong reasoning capabilities. How can Reinforced Fine-Tuning (ReFT) can solve it?Sep 3Sep 3
InGoPenAIbyQvickReadMeta COCONUT: Latent Space Reasoning with Large Language ModelsAnalysis of the Research Paper: “Training Large Language Models to Reason in a Continuous Latent Space”. This paper presents a significant…3d ago3d ago
Devmallya KararChain-Of-Thought ( CoT ) in Large Language Models prompting and Concise CoT with Code…Chain-of-Thought (CoT) prompting is a technique in large language models (LLMs) where intermediate reasoning steps are generated to solve…Oct 32Oct 32
AI Papers AcademyMeta AI Empowers LLMs to Reason in Their Own LanguageDiscover how Meta AI’s Chain of Continuous Thought (Coconut) empowers large language models (LLMs) to reason in their own language.5h ago
InTowards Data SciencebyMatthew GuntonHow to Improve Model Quality Without Building Larger ModelsGoing into the Google DeepMind’s “Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters”Oct 84
Nilesh BarlaA short note on Reinforced Fine-Tuning or ReFTLLMs still lack strong reasoning capabilities. How can Reinforced Fine-Tuning (ReFT) can solve it?Sep 3
InGoPenAIbyQvickReadMeta COCONUT: Latent Space Reasoning with Large Language ModelsAnalysis of the Research Paper: “Training Large Language Models to Reason in a Continuous Latent Space”. This paper presents a significant…3d ago
Devmallya KararChain-Of-Thought ( CoT ) in Large Language Models prompting and Concise CoT with Code…Chain-of-Thought (CoT) prompting is a technique in large language models (LLMs) where intermediate reasoning steps are generated to solve…Oct 32
ShaipChain-of-Thought Prompting — Everything You Need To Know About ItProblem-solving has been one of the innate capabilities of humans. Ever since our primitive days, when our major challenges in life were…4d ago
Don LimReasoning tokens and techniques used in System 2 LLMs such as OpenAI o1What is the System 2 model?Sep 162
