3 papers
cs.GR2026
Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes
Ashwath Shetty, Zihan Zhu, Soeren Pirk +1
This work proposes an adaptation of the attention mechanism for triangle meshes. The core observation is that endowing the attention mechanism with critical properties for learning…
cs.CV2026
Text-conditioned Segmentation for Tomato Phenotyping via Procedural Synthetic Data
Samy Mounir, Mikolaj Cieslak, Najmeddine Dhieb +8
Vision-based automation is an excellent candidate for reducing manual labor in greenhouse crop production and phenotyping. However, progress is constrained by the lack of annotated…
cs.CV2025
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Yujun Wang, Aniri, Jinhe Bi +2
Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mi…