2026
Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
AAAI 2026technical
Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into
4 accepted papers
Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships. In-context learning (ICL) offers a promising avenue for VLMs t
Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a critical challenge. Existing hallucination detection method…
Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CAVs often exhibit inconsistencies, making cross-layer comparisons unreliable. To…