Entities · Models
LLaVA-1.5-7B
5 articles tagged with this entity.
-
EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
-
Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering
-
Fine-Tuning Vision-Language Models for Understanding Current Damage and Scoring Priority with Quality Guard Agent
-
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
-
MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models