DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning
cs.CV, cs.AI
Submitted: 2026-05-06
Updated: 2026-11-02
Code: https://github.com/wyclike/DiffCap-Bench
Terminology
Sources
- Qwen3-VL Technical Report
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Seed1.5-VL Technical Report
- STEP3-VL-10B Technical Report
- HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
- VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- OmniCaptioner: One Captioner to Rule Them All
- Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
- OpenAI GPT-5 System Card
- Kimi K2.5: Visual Agentic Intelligence
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- MiMo-VL Technical Report
- CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
- TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
- Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation
- ImgEdit: A Unified Image Editing Dataset and Benchmark
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs