Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models

arXiv:2607.02575 · cs.CV, cs.AI · Submitted 2026-06-30 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-06-30

Updated: 2026-08-31

Comments: Accepted by ICML 2026. Code is available at https://github.com/MegviiAlgo-Team/CC-ICL

Code: https://github.com/MegviiAlgo-Team/CC-ICL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 60× in this paper · explained in 1 episode
• In-Context Learning — 45× in this paper · explained in 4 episodes
• Benchmark — 30× in this paper · explained in 2 episodes
• Generalization — 16× in this paper · explained in 13 episodes
• Adaptability — 10× in this paper · explained in 1 episode
• Ablation — 9× in this paper · explained in 1 episode
• Robustness — 8× in this paper · explained in 5 episodes
• Multi-Criterion Training — 7× in this paper
• Accuracy — 6× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Core — 5× in this paper · explained in 2 episodes
• Transferability — 5× in this paper · explained in 4 episodes
• Modality Gap — 4× in this paper · explained in 4 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• In-Context Learning (ICL) — 2× in this paper · explained in 5 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Dynamic Adaptation — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Semantic Gap — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• GPT-4 Technical Report
• LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
• Qwen3-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Qwen2.5-VL Technical Report
• CL-bench: A Benchmark for Context Learning
• The Llama 3 Herd of Models
• GPT-4o System Card
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Qwen3 Technical Report
• OPT: Open Pre-trained Transformer Language Models
• DeepSeek-V3 Technical Report

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