Prior Directions: Separating Geometric Identification from Behavioral Efficacy in Visual Revision

arXiv:2607.26913 · cs.CV · Submitted 2026-07-29 · Read on arXiv

cs.CV

Submitted: 2026-07-29

Updated: 2026-09-26

Code: https://github.com/phare111/prior-directions

Terminology

• Alignment — 16× in this paper · explained in 1 episode
• Hallucination — 13× in this paper · explained in 3 episodes
• Grounding — 12× in this paper · explained in 3 episodes
• Steering — 6× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Modality Gap — 2× in this paper · explained in 4 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Directed Capture Rate — 1× in this paper
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Qwen3-VL Technical Report
• Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating
• How Do Vision-Language Models Process Conflicting Information Across Modalities?
• When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
• ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use
• When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
• Steering Vision-Language Models with Joint Sparse Autoencoders
• Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
• Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models
• Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
• Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
• MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

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