A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
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
DeepSeekMoE introduces a novel MoE architecture with fine-grained expert segmentation and shared experts to achieve ultimate expert specialization in language models.
Unknown
This paper introduces a Graph RAG approach for automated short answer grading that provides fine-grained, explainable feedback by returning explicitly linked facts, contrasting with coarse Vector-RAG passages.
Unknown
This survey provides a fine-grained analysis of diffusion model design fundamentals, categorizing design factors for different purposes and implementation strategies.
Unknown
MedPRMBench introduces a fine-grained benchmark for evaluating process reward models in medical reasoning, focusing on question informativeness.
Zongyi Chen, Yu Liang, Jie Lin, et al.
PathVU is a vision-anchored benchmark for fine-grained multiscale visual understanding in pathology, with 14 VQA tasks, 61,673 images, and 308,070 samples, revealing substantial limitations in current MLLMs.
Dongyu Ru, Lin Qiu, Xiangkun Hu, et al.
RAGChecker is a fine-grained evaluation framework with diagnostic metrics for retrieval and generation modules in RAG systems, showing better correlation with human judgments.
Juncheng Wu, Sheng Liu, Haoqin Tu, et al.
This paper introduces a fine-grained evaluation framework decomposing LLM reasoning into knowledge correctness and reasoning quality, revealing that SFT improves accuracy but degrades reasoning, while RL enhances medical reasoning by pruning inaccura
Unknown
LongCite enables LLMs to generate fine-grained sentence-level citations in long-context QA, improving trustworthiness via a new benchmark, pipeline, dataset, and trained models.
Yubin Hong, Chaofan Li, Jingyi Zhang, et al.
FG-RAG introduces a context-aware fine-grained graph retrieval-augmented generation framework to improve query-focused summarization.
Unknown
This paper proposes perception-centric process reward models to improve vision-language models by providing fine-grained feedback during reasoning.