From Routing Signals to Selective Review: Visual regrounding in MoE VLMs

arXiv:2609.38111 · cs.CL, cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CL, cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Accuracy — 59× in this paper · explained in 1 episode
• AUC — 46× in this paper · explained in 2 episodes
• Hallucination — 19× in this paper · explained in 3 episodes
• Linear probe — 11× in this paper · explained in 2 episodes
• Grounding — 9× in this paper · explained in 3 episodes
• Calibration — 6× in this paper · explained in 7 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Steering — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Hallucination Detection — 3× in this paper · explained in 2 episodes
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Advances in Language and Vision Research — 1× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Attention Entropy — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Mixtral of Experts
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
• Real-Time Detection of Hallucinated Entities in Long-Form Generation
• AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
• Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering