Composition, Not Conversation: VLMs Lose the Scene, Not the Thread

arXiv:2609.38368 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Accuracy — 62× in this paper · explained in 1 episode
• Benchmark — 28× in this paper · explained in 2 episodes
• Grounding — 25× in this paper · explained in 3 episodes
• Alignment — 9× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 8× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Distribution Shift — 3× in this paper · explained in 6 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Abstention — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Pixtral 12B
• Qwen3-VL Technical Report
• Ministral 3
• MileBench: Benchmarking MLLMs in Long Context
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
• When and why vision-language models behave like bags-of-words, and what to do about it?

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