Step1X-Edit
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
- 2.3k
- Python
- Apache-2.0
- 7 mo ago
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, planning and any other topics connecting deep learning and reasoning
Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.
[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding
Unified reproductions, benchmarking & evaluation for perception-aware RLVR and OPD in VLMs, plus multi-turn agentic RL with HTTP, OpenEnv and OpenReward environments. 19 methods · 30+ benchmarks · Official code of CGPO (ACM MM 2026 Oral).
NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment
Official code for "ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning"
This paper introduces BloomBench, a new bilingual (English-Arabic), cognitively-informed benchmark based on Bloom's Taxonomy to systematically evaluate the reasoning abilities of Vision-Language Models across different hierarchical cognitive levels.
Programmatic toolkit and verifiable Chinese data for visual reasoning
🌍 Infer where an image was captured by combining visual evidence, geographic data, terrain geometry, and computational reasoning. 🛰️📍
A benchmark for dual-interpretation synthesis: can a model draw one image that reads as two different faces when rotated 180°? Baselines for 15 models, rubric, harness and judge comparison.