LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
VoxScene is a new anchor-conditioned voxel diffusion model that synthesizes collision-free 3D indoor scene arrangements via discrete volumetric occupancies and uses the grids for asset retrieval.
SplAttN uses Gaussian soft splatting and attention to avoid sparse projection collapse in point cloud completion, achieving SOTA results and demonstrating genuine visual cue reliance on KITTI.
citing papers explorer
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement
VoxScene is a new anchor-conditioned voxel diffusion model that synthesizes collision-free 3D indoor scene arrangements via discrete volumetric occupancies and uses the grids for asset retrieval.
-
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
SplAttN uses Gaussian soft splatting and attention to avoid sparse projection collapse in point cloud completion, achieving SOTA results and demonstrating genuine visual cue reliance on KITTI.
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning