Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Project page: https://qwenlm.github.io
Sources
- ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
- BabyVision: Visual Reasoning Beyond Language
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
- VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
- Towards Cross-View Point Correspondence in Vision-Language Models
- LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
- TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
- Multimodal Chain-of-Thought Reasoning in Language 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