Related papers: ExperienceWeaver: Optimizing Small-sample Experien…
Large language models (LLMs) have demonstrated impressive performance across various domains. However, for clinical diagnosis, higher expectations are required for LLM's reliability and sensitivity: thinking like physicians and remaining…
The rapid advancement of large language models (LLMs) in biological-medical applications has highlighted a gap between their potential and the limited scale and often low quality of available open-source annotated textual datasets. In…
Large language models exhibit superior capabilities in processing and understanding language, yet their applications in educational contexts remain underexplored. Learnersourcing enhances learning by engaging students in creating their own…
The paper investigates using a Large Language Model (LLM) to automatically perform web software tasks using click, scroll, and text input operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are…
Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data…
Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased…
To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of…
The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent…
Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…
We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…
Recent virtual try-on approaches have advanced by finetuning pre-trained text-to-image diffusion models to leverage their powerful generative ability. However, the use of text prompts in virtual try-on remains underexplored. This paper…
From grading papers to summarizing medical documents, large language models (LLMs) are evermore used for evaluation of text generated by humans and AI alike. However, despite their extensive utility, LLMs exhibit distinct failure modes,…
Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…
Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with prior studies suggesting that LLM-based agents exhibit no sensitivity to experimental…
Clinical document classification is essential for converting unstructured medical texts into standardised ICD-10 diagnoses, yet it faces challenges due to complex medical language, privacy constraints, and limited annotated datasets. Large…
Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving…
This paper introduces a system that integrates large language models (LLMs) into the clinical trial retrieval process, enhancing the effectiveness of matching patients with eligible trials while maintaining information privacy and allowing…
Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…
Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…