VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
cs.CV, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/THU-BPM/Vigor
Terminology
Sources
- DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
- GPT-4 Technical Report
- Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
- AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs