✨3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
📝 Summary:
3D-VCD is a new inference-time framework that reduces hallucinations in 3D embodied agents. It constructs distorted 3D scene graphs and contrasts predictions to suppress ungrounded tokens. This improves reasoning on 3D benchmarks without retraining.
🔹 Publication Date: Published on Apr 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.08645
• PDF: https://arxiv.org/pdf/2604.08645
• Project Page: https://plan-lab.github.io/projects/3d-vcd
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#3DLLM #EmbodiedAI #HallucinationMitigation #ComputerVision #AIResearch
📝 Summary:
3D-VCD is a new inference-time framework that reduces hallucinations in 3D embodied agents. It constructs distorted 3D scene graphs and contrasts predictions to suppress ungrounded tokens. This improves reasoning on 3D benchmarks without retraining.
🔹 Publication Date: Published on Apr 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.08645
• PDF: https://arxiv.org/pdf/2604.08645
• Project Page: https://plan-lab.github.io/projects/3d-vcd
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#3DLLM #EmbodiedAI #HallucinationMitigation #ComputerVision #AIResearch
arXiv.org
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through...
Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe and ungrounded...