All Posts Page 3 - DataSci Ocean

All Posts

2025

Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents 05-20

MemGPT: Towards LLMs as Operating Systems 05-18

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory 05-13

PLAN-AND-ACT: Improving Planning of Agents for Long-Horizon Tasks 05-11

Intorduction to LangMem 05-06

HuatuoGPT-o1: Towards Medical Complex Reasoning with LLMs 01-31

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face 01-27

EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records 01-26

2024

REPLUG: Retrieval-Augmented Black-Box Language Models 10-31

RAFT: Adapting Language Model to Domain Specific RAG 10-31

Python's Small Integer Cache: Faster Code with a Hidden Trick 10-03

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs 07-29

Better & Faster Large Language Models via Multi-token Prediction 07-18

Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning 07-08

GAIA: A Benchmark for General AI Assistants 06-27

ChatEval: Towards Better LLM-Based Evaluators Through Multi-Agent Debate 06-23

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM 04-24

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints 04-10

The 3 Stages of LLM Training: A Deep Dive into Reinforcement Learning from Human Feedback (RLHF) 02-27

DPO：Direct Preference Optimization 02-27

1
2
3
4