We present Sketch2Colab, which turns storyboard-style 2D sketches into coherent, object-aware 3D multi-human motion with fine-grained control over agents, joint...
Long-context inference in large language models is bottlenecked by Key--Value (KV) cache loading during the decoding stage, where the sequential nature of gener...
Multi-attribution learning (MAL), which enhances model performance by learning from conversion labels yielded by multiple attribution mechanisms, has emerged as...
The classification of Intangible Cultural Heritage (ICH) images in the Mekong Delta poses unique challenges due to limited annotated data, high visual similarit...
Reservoir expansion can improve online independent component analysis (ICA) under nonlinear mixing, yet top-n whitening may discard injected features. We formal...
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In t...
Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently ...
We introduce GeoDiT, a diffusion transformer designed for text-to-satellite image generation with point-based control. Existing controlled satellite image gener...
Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorl...
While multimodal survival prediction models are increasingly more accurate, their complexity often reduces interpretability, limiting insight into how different...
Retrieval-Augmented Generation (RAG) systems commonly adopt retrieval fusion techniques such as multi-query retrieval and reciprocal rank fusion (RRF) to increa...
The extraction of critical information from crime-related documents is a crucial task for law enforcement agencies. Named-Entity Recognition (NER) can perform t...
