Visual Abstention in Unified Multimodal Models
cs.CL, cs.AI, cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Project page: https://visual-abstention.github.io
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Emu3.5: Native Multimodal Models are World Learners
- Emerging Properties in Unified Multimodal Pretraining
- SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
- Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
- Learning the Boundary of Solvability: Aligning LLMs to Detect Unsolvable Problems
- TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Kimi K3: Open Frontier Intelligence
- InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
- UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
- Qwen-Image Technical Report
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