More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training
cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Training Verifiers to Solve Math Word Problems
- Emu3.5: Native Multimodal Models are World Learners
- VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
- SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
- Measuring Massive Multitask Language Understanding
- Training Compute-Optimal Large Language Models
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- Scaling Laws for Neural Language Models
- Kimi K2.5: Visual Agentic Intelligence
- Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- DeepSeek-V3 Technical Report
- Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
- Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities
- SocialIQA: Commonsense Reasoning about Social Interactions
- StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
- Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering