4 papers
Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL
Shu Tong Luo, Wenqin Liu, Rui Liu +2
When a user reveals task-critical information across several conversation turns, LLM accuracy drops by up to 65% despite full context availability. We show that this Lost in Conver…
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
Sensen Gao, Shanshan Zhao, Xu Jiang +7
Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (…
InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting
Jinlong Fan, Shanshan Zhao, Liang Zheng +3
Reconstructing complete and animatable 3D human avatars from monocular videos remains challenging, particularly under severe occlusions. While 3D Gaussian Splatting has enabled pho…
UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation
Lunhao Duan, Shanshan Zhao, Wenjun Yan +7
Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descripti…