+179%
66/43
VLA
小方向 小方向
Subdirections
方法族趨勢來源於 field-state-*.json（機械化，零 LLM）。加速度 = (近 7d − 前 7d) / max(前值, 1)。
方法族趋势来源于 field-state-*.json（机械化，零 LLM）。加速度 = (近 7d − 前 7d) / max(前值, 1)。
速度榜 · 前 8 名 速度榜 · 前 8 名 / Velocity Top 8
- 01 VLA VLA Generalist +179% 66/43
- 02 AI Agentic Coding +170% 17/10
- 03 VLA VLA Post-Training RL +132% 32/14
- 04 AI Agent Infra +125% 5/4
- 05 VLA World Model Dynamics +115% 28/23
- 06 AI Frontier Models +114% 16/14
- 07 AI Context Engineering +100% 2/2
- 08 AI Agent Eval +100% 2/2
新冒頭新冒头 · EMERGING · prior volume = 0
VLA · 15
+132%
32/14
VLA
VLA Post-Training RL vla.policy.robot_rl.vla_post_training_rl
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+115%
28/23
+78%
19/13
VLA
Tactile Sensing vla.manipulation.tactile_sensing
佐證論文佐证论文 MuxGel: Simultaneous Dual-Modal Visuo-Tactile Sensing via Spatially Multiplexing and Deep Reconstruction VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation Scalable Open-Source Visuotactile Sensor for 6-Axis Contact Wrench Estimation in Tensegrity Robots
+74%
18/17
VLA
VLA Generalist vla.foundation.vla_generalist
+70%
17/16
VLA
Imitation Learning vla.policy.imitation_learning
佐證論文佐证论文 More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
+62%
15/11
VLA
Hierarchical Planning vla.reasoning.hierarchical_planning
+53%
13/12
+41%
10/14
VLA
Dexterous Manipulation vla.manipulation.dexterous_manipulation
佐證論文佐证论文 VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos
+29%
7/6
VLA
Diffusion Policy vla.action.diffusion_policy
+21%
5/4
VLA
Cross-Embodiment Foundation Models vla.foundation.cross_embodiment_fm
+21%
5/0
VLA
Mobile Manipulation vla.manipulation.mobile_manipulation
+21%
5/5
VLA
Sim-to-Real vla.sim_data.sim_to_real
佐證論文佐证论文 Difference-Based Relational Learning for Zero-Shot Object-Goal Visual Navigation With Direct Sim-to-Real Transfer Where to Touch, How to Contact: A Hierarchical RL-MPC Framework for Geometry-Aware Sim-to-Real Manipulation A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer
+12%
3/2
VLA
3D Representation vla.perception.representation_3d
佐證論文佐证论文 Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
0%
0/2
VLA
Imitation Learning vla.policy.imitation_learning
佐證論文佐证论文 More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
AI App · 11
+170%
17/10
AI App
Agentic Coding ai.coding.agentic_coding
頂尖實驗室：顶尖实验室： Qwen
+114%
16/14
AI App
Frontier Models ai.frontier.frontier_model
+125%
5/4
AI App
Agent Infra ai.infra.agent_infra
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+80%
4/5
AI App
MCP (Model Context Protocol) ai.tools.mcp_protocol
+999%
2/0
AI App
Voice & Multimodal ai.frontier.voice_multimodal
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+100%
2/2
AI App
Context Engineering ai.context.context_engineering
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+100%
2/2
AI App
Agent Eval ai.eval.agent_eval
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+50%
2/4
AI App
Vertical Agents ai.vertical.vertical_agent
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+999%
1/0
AI App
Multi-Agent Teams ai.multi_agent.multi_agent
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
+100%
1/1
AI App
Explicit Reasoning (CoT / Search) ai.reasoning.reasoning_planning
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.
0%
0/0
AI App
Agent Safety ai.safety.agent_safety
No evidence papers matched in the last 90 days. This family is tracked mechanically — when the threshold fires, papers will appear here.