相关论文: BioReason: Incentivizing Multimodal Biological Rea…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Higher-level cognition includes logical reasoning and the ability of question answering with common sense. The RatioLog project addresses the problem of rational reasoning in deep question answering by methods from automated deduction and…

Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question…

Recent breakthroughs in large language models (LLMs), particularly in reasoning capabilities, have propelled Retrieval-Augmented Generation (RAG) to unprecedented levels. By synergizing retrieval mechanisms with advanced reasoning, LLMs can…

While large multimodal models (LMMs) have demonstrated strong performance across various Visual Question Answering (VQA) tasks, certain challenges require complex multi-step reasoning to reach accurate answers. One particularly challenging…

In contrast to their remarkable performance on general knowledge QA, the true abilities of Large Language Models (LLMs) in tasks demanding deep, specialized reasoning, such as in protein biology, have yet to be thoroughly investigated.…

Vision-Language Models (VLMs) are advancing computational pathology with superior visual understanding capabilities. However, current systems often reduce diagnosis to directly output conclusions without verifiable evidence-linked…

In recent years, large language models (LLMs) have achieved state-of-the-art results in various biological sequence analysis tasks, such as sequence classification, structure prediction, and function prediction. Similar to advancements in…

Large language models (LLMs) have recently shown remarkable performance in language tasks and beyond. However, due to their limited inherent causal reasoning ability, LLMs still face challenges in handling tasks that require robust causal…

While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they genuinely perform actual step-by-step reasoning or just rely on superficial visual…

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels,…

Bacteriophages, often referred to as the dark matter of the biosphere, play a critical role in regulating microbial ecosystems and in antibiotic alternatives. Thus, accurate interpretation of their genomes holds significant scientific and…

Deep learning based automated pathological diagnosis has markedly improved diagnostic efficiency and reduced variability between observers, yet its clinical adoption remains limited by opaque model decisions and a lack of traceable…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…

Retrieval-augmented generation has gained significant attention due to its ability to integrate relevant external knowledge, enhancing the accuracy and reliability of the LLMs' responses. Most of the existing methods apply a dynamic…

Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn generalizable representations of diverse…

While large language models (LLMs) have demonstrated impressive capabilities across various natural language processing tasks by acquiring rich factual knowledge from their broad training data, their ability to synthesize and logically…

Large language models (LLMs) in biomedicine face a fundamental conflict between static parameter knowledge and the dynamic nature of clinical evidence. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external…