Not All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference

arXiv:2610.01640 · cs.CV, cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Benchmark — 99× in this paper · explained in 2 episodes
• Accuracy — 39× in this paper · explained in 1 episode
• Regret — 39× in this paper · explained in 3 episodes
• alpha — 11× in this paper · explained in 1 episode
• Aggregation — 9× in this paper · explained in 1 episode
• Core — 8× in this paper · explained in 2 episodes
• Scaling Laws — 7× in this paper · explained in 4 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Test-time Scaling — 4× in this paper · explained in 2 episodes
• AGN — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Generative AI — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Adaptation — 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
• Consistency — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• VistaHop: Benchmarking Long-Horizon Visual DeepSearch
• Training Compute-Optimal Large Language Models
• Scaling Laws for Neural Language Models
• The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs
• Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

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