MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Qwen2.5-VL Technical Report
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
- Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization
- RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format
- Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
- AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
- Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
- Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
- LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection