A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Zhuowan Li, Cheng Li, Mingyang Zhang, et al.
Compares RAG and long-context LLMs, finding long-context outperforms RAG but at higher cost, and proposes Self-Route to route queries based on model self-reflection.
Jinyang Wu, Feihu Che, Mingkuan Feng, et al.
Defines seven noise types in RAG, builds NoiserBench benchmark, and shows some noise can benefit LLMs while other noise harms them.
Fei Wang, Xingchen Wan, Ruoxi Sun, et al.
Astute RAG adaptively elicits internal knowledge from LLMs and iteratively consolidates it with external sources to overcome imperfect retrieval in RAG.
Alexandria Leto, Cecilia Aguerrebere, I. Bhati, et al.
This paper investigates how retrieval accuracy affects RAG pipeline performance for QA tasks, finding that lowering search accuracy minimally impacts downstream quality while improving speed and memory.
Zhengren Wang, Jiayang Yu, Dongsheng Ma, et al.
RARE decouples knowledge storage from reasoning by externalizing domain knowledge to retrievable sources and internalizing reasoning patterns, enabling lightweight models to surpass GPT-4 and DeepSeek-R1 by ~20% accuracy.
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, et al.
Proposes a data distribution lens to understand when and why Chain-of-Thought reasoning succeeds or fails, revealing it as a brittle mirage beyond training distributions.
Kaiwen Wei, Rui Shan, Dongsheng Zou, et al.
MIRAGE enhances test-time scaling for medical QA by combining multi-path parallel inference with structured knowledge graph retrieval to reduce error accumulation and improve traceability.
Nadeem Mehmood, Rosario Culmone, Leonardo Mostarda
Proposes a middleware-based schema model for temporal sensor data storage in MongoDB, enabling flexible schema evolution without losing big data advantages.
Soren Kejser Jensen, Torben Bach Pedersen, Christian Thomsen
A survey classifying Time Series Management Systems by architecture, storage, querying, stream processing, and approximate query processing, with a vision for next-generation systems.
Boncz, Peter, Manegold, Stefan, Martin Kersten
This paper optimizes large main-memory joins on modern hardware using vertically fragmented data structures and a radix-cluster partitioning algorithm to improve cache and CPU performance.
Martin Schoeberl, Sahar Abbaspour, Benny Åkesson, et al.
T-CREST proposes a time-predictable multi-core architecture optimized for worst-case execution time (WCET) rather than average-case performance, enabling static WCET analysis for real-time systems.
A.W.M. Smeulders, Dung M. Chu, Rita Cucchiara, et al.
This paper presents a large-scale experimental survey evaluating 19 visual trackers on 315 video fragments to systematically assess their performance under diverse challenging conditions.