Related papers: LeMat-Synth: a multi-modal toolbox to curate broad…
Emerging topics in biomedical research are continuously expanding, providing a wealth of information about genes and their function. This rapid proliferation of knowledge presents unprecedented opportunities for scientific discovery and…
Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…
Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence…
Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming…
The capacity of Large Language Models (LLMs) to generate valid scientific hypotheses for materials synthesis remains largely unquantified, hindered by the absence of benchmarks probing physicochemical logics reasoning. To address this, we…
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,…
Large Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectories still hinders the development of stronger LLM agents.…
Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created…
The design of sustainable materials requires access to materials performance and sustainability data from literature corpus in an organized, structured and automated manner. Natural language processing approaches, particularly large…
Scientific literature is growing exponentially, creating a critical bottleneck for researchers to efficiently synthesize knowledge. While general-purpose Large Language Models (LLMs) show potential in text processing, they often fail to…
Student modeling is central to many educational technologies as it enables predicting future learning outcomes and designing targeted instructional strategies. However, open-ended learning domains pose challenges for accurately modeling…
Automated testing plays a crucial role in ensuring software security. It heavily relies on formal specifications to validate the correctness of the system behavior. However, the main approach to defining these formal specifications is…
Large Language Models (LLMs) are transforming language sciences. However, their widespread deployment currently suffers from methodological fragmentation and a lack of systematic soundness. This study proposes two comprehensive…
We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of…
The demand for Large Language Models (LLMs) at multiple scales, capable of sophisticated and sound mathematical reasoning, continues to grow. However, the development of performant mathematical LLMs is often bottlenecked by the scarcity of…
Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of…
Two-dimensional (2D) materials have shown broad application prospects in fields such as energy, environment, and aerospace owing to their unique electrical, mechanical, thermal and other properties. With the development of artificial…
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context…
Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional…
The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely…