VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
Openhoi: Open-world hand-object interaction synthesis with multimodal large language model
4 Pith papers cite this work. Polarity classification is still indexing.
years
2026 4representative citing papers
Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
Interviews reveal interpretive misalignment in EM systems where supervised individuals and authorities reason differently about the same data streams due to asymmetric access.
TibetCPR is a multimodal feedback CPR trainer that improved rhythm and depth stability in a randomised study of 40 Tibetan laypeople compared to unguided practice.
citing papers explorer
-
VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection
VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
-
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
Adaptive saliency-guided supervoxel tokenization cuts 3D AR token length to 12.8% of uniform voxels while claiming SOTA quality and ~10× speedup on Trellis-500K.
-
Reading the Same Data Differently: Interpretive Labor Across System Boundaries in Electronic Monitoring
Interviews reveal interpretive misalignment in EM systems where supervised individuals and authorities reason differently about the same data streams due to asymmetric access.
-
TibetCPR: A Multimodal Tactile Feedback System to Enhance Cardiopulmonary Resuscitation Training in High-Altitude Regions of Tibet
TibetCPR is a multimodal feedback CPR trainer that improved rhythm and depth stability in a randomised study of 40 Tibetan laypeople compared to unguided practice.