2 papers
cs.CV2026
3D Primitives are a Spatial Language for VLMs
Junze Liu, Kun Qian, Florian Dubost +8
Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, class…
cs.LG2025
GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
Jialin Chen, Houyu Zhang, Seongjun Yun +6
Retrieval-Augmented Generation (RAG) has significantly mitigated the hallucinations of Large Language Models (LLMs) by grounding the generation with external knowledge. Recent exte…