Browsing: Hugging Face
The study evaluates various LLMs on diverse text tasks using a new dataset, revealing distinct personality traits and improving model…
We’re excited to share our latest work, “Language Surgery in Multilingual Large Language Models”. We proposed a method, named Inference-Time…
PatchInstruct enhances LLM forecasting quality through specialized prompting methods that include time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation.…
A new field, AI Agent Behavioral Science, is proposed to systematically study the behaviors of AI agents in diverse contexts,…
A novel benchmark and dataset are proposed for multi-modal summarization of UI instructional videos, addressing the need for step-by-step executable…
Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as…
A diffusion-based framework generates aligned novel views of images and geometry using warping-and-inpainting with cross-modal attention distillation and proximity-based mesh…
LLMs perform well on implementation-heavy competitive programming problems but struggle with nuanced algorithmic reasoning, as highlighted by LiveCodeBench Pro. Recent…
Configurable Preference Tuning enables language models to dynamically adjust their behavior based on human-interprettable directives, using rubric-guided preference data for…
InterSyn, a large-scale dataset with tightly interleaved image-text outputs and automated quality refinement, improves multimodal understanding and generation through the…