SkyworkAI / SkyworkAI/Skywork-R1V
[APEX研究] 🤖 AGI 路线 昆仑 Skywork 前沿技术与 AGI 路线图
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 282
- PR merge metrics
- No merged PRs in 30d
Description
🤖 AGI 路线图 & 前沿技术布局：昆仑 Skywork
前沿方向
- 测试时计算（Test-Time Compute）：是否已有相关研究？
- 合成数据：训练数据的 Scaling Law 突破
- 多模态融合：文本+图像+语音+视频统一模型
- Agent/Tool Use：工具调用、代码执行、自主规划
领域前沿对比
| 方向 | DeepSeek | Qwen 3 | 昆仑 Skywork |
|---|---|---|---|
| 测试时计算 | R1 系列领先 | 已集成 | ? |
| 长上下文 | 128K | 1M (Qwen3-1M) | ? |
| MoE 路由 | DeepSeekMoE | 部分版本 | ? |
| 多模态 | 空白 | VL/Omni/TTS | ? |
建议讨论
- AGI 路线图中，昆仑 Skywork 的长期技术愿景是什么？
- 是否在布局 RLHF/RL 以外的对齐技术？
- 如何应对推理能力（数学/编程）的持续进化需求？
本 Issue 由 AGI 研究者提交，供团队参考讨论。
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue does not mention any repository files, tests, or entry points. Start by reviewing the project structure and existing model or research documentation, then compare the requested areas—test-time compute, synthetic data, multimodal models, and agents—with current project scope. Done would require an agreed AGI roadmap, not a self-contained code change.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100