Paper-Conference

BioVITA: Biological dataset, model, and benchmark for visual-textual-acoustic alignment

Gaussian mesh renderer for lightweight differentiable rendering

AnimalCLAP: Taxonomy-aware language-audio pretraining for species recognition and trait inference

Zero-shot hierarchical plant segmentation via foundation segmentation models and text-to-image attention

SimLabel: Similarity-Weighted Semi-supervision for Multi-annotator Learning with Missing Labels

QuMAB: Query-based Multi-annotator Behavior Pattern Learning

Interaction-via-Actions: Cattle interaction detection with joint learning of action-interaction latent space

LLMの光と闇？ 推論エンジンとしてのLLMとバイアス

A Needle in a Haystack: Finding Contextual Knowledge for Video Question Answering

Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown