Targeted Visual Counterfactual Explanations for Contrastive Vision-Language ModelResearchSep 30, 2026
Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning ModelsResearchSep 30, 2026
VoxelSage: Tool-Augmented 3D CT Analysis and Simulator-Shielded Sequential Resection Planning for Liver TumorsResearchSep 30, 2026
Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent CodingResearchSep 30, 2026
Tracing the Evidence: Faithful Token Attribution Through Vision-Language ReasoningResearchSep 30, 2026
Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference SupervisionResearchSep 30, 2026