A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Giorgio Roffo
This tutorial explores advanced LLM techniques including RAG, PAL, ReAct, LangChain, fine-tuning strategies, and transformer architectures to address limitations like temporal cutoffs and mathematical inaccuracies.
Xinze Li, Yixin Cao, Yubo Ma, et al.
This paper compares Long Context and RAG for LLMs, finding LC generally outperforms RAG on QA benchmarks, with summarization-based retrieval matching LC, and highlights context relevance as an overlooked factor.
Yiqun Chen, Ling Yan, Weiwei Sun, et al.
MMOA-RAG uses multi-agent reinforcement learning to jointly optimize all components of a RAG pipeline toward a unified reward, improving QA performance.
Siran Li, Linus Stenzel, Carsten Eickhoff, et al.
This paper systematically investigates RAG system components and configurations, introducing advanced designs including query expansion, novel retrieval strategies, and Contrastive In-Context Learning, providing actionable insights for balancing cont
Ning Li, Qiqiang Lin, Zheng Wu, et al.
ColorAgent is an OS agent that uses step-wise reinforcement learning and a multi-agent framework to achieve state-of-the-art success rates on AndroidWorld and AndroidLab benchmarks.
Gyuwan Kim, Cheoneum Park, Tao Yang
CoinRAG optimizes the Pareto frontier for long-context RAG by reusing fine-grained, query-relevant KV caches to reduce latency and improve answer quality.
Mukhtiar Ali, Harsh Dubey, Sugam Mishra, et al.
Introduces CLIP-CC-Bench, an evaluation suite for long-form video description using 90-second movie clips and expert-written paragraph references, with an ensemble of five LLM embeddings and coarse/fine-grained semantic matching to rank 17 video-lang
Unknown
This paper presents a research agenda for AI for science, focusing on building technical foundations to leverage data for scientific discovery.
Unknown
The paper discusses the shift from traditional storage systems to in situ AI that provides multi-level abstractions for accessing information content from raw bits to learned functions capturing distributions.
Unknown
This paper investigates how pre-training can be leveraged for scientific machine learning, focusing on transfer learning behavior and scaling characteristics.
Unknown
This paper addresses the chicken-and-egg problem in causal representation learning by proposing a weakly supervised approach that leverages auxiliary labels to identify causal variables and graph.
Unknown
This paper proposes a method to transfer exploratory policies from simulation to real-world reinforcement learning, overcoming the sim-to-real gap even when direct transfer fails.