Asia
Towards Global Optimal Visual In-Context Learning Prompt Selection
Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query samples.
LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction Di Liu Qilong Zhangli Y unhe Gao Dimitris N. Metaxas Rutgers University
Reconstructing the 3D articulated shape of an animal from a single in-the-wild image is a challenging task.
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation Ziyi Wang Y anbo Wang
Subsequently, the generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.
Task-aware world model learning with meta weighting via bi-level optimization
Aligning the world model with the environment for the agent's specific task is
TableRAG: Million-Token Table Understanding with Language Models Si-An Chen
This enables more efficient data encoding and precise retrieval, significantly reducing prompt lengths and mitigating information loss. We have developed two new million-token benchmarks from the Arcade and BIRD-SQL datasets to thoroughly evaluate TableRAG's effectiveness at scale.
Scattering Vision Transformer: Spectral Mixing Matters-Supplementary
SVT incorporates the scattering network utilizing the DTCWT for image decomposition into low and high-frequency components. Our primary focus is to analyze the low-frequency and high-frequency filter components to emphasize SVT's exceptional directional orientation capabilities.
