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
LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
NPCs gain spatial awareness via panoramic images turned into JSON scene data for LLMs, enabling dynamic references to nearby objects and improving player preference in user studies.
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.
-
LightAVSeg: Lightweight Audio-Visual Segmentation
LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.
-
Are Candidate Models Really Needed for Active Learning?
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
-
Empowering NPC Dialogue with Environmental Context Using LLMs and Panoramic Images
NPCs gain spatial awareness via panoramic images turned into JSON scene data for LLMs, enabling dynamic references to nearby objects and improving player preference in user studies.