GeoPID: Decomposing and Steering Visual Information in Vision-Language Models
cs.CV, cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- A Closer Look at Multimodal Representation Collapse
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
- Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models
- Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
- Hierarchical and Multimodal Data for Daily Activity Understanding
- Information Router for Mitigating Modality Dominance in Vision-Language Models
- AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
- GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation
- LLaVA-OneVision: Easy Visual Task Transfer
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- Query-Dependent Use of Generated Descriptions for Reliable Visual Question Answering
- Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
- Reducing Hallucinations in Vision-Language Models via Latent Space Steering
- One RL to See Them All: Visual Triple Unified Reinforcement Learning
- SmolVLM: Redefining small and efficient multimodal models
- Representation Learning with Contrastive Predictive Coding
- MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models