TBD-VLA: Temporal Block Diffusion Vision Language Action Model
About
Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively on prior context. While effective, this paradigm incurs high inference latency and largely ignores the temporal structure inherent in action trajectories. Recent efforts introduce parallel decoding to improve efficiency, enabling faster inference, but lack explicit mechanisms for modeling token dependencies. We introduce TBD-VLA, a discrete token-based VLA framework that incorporates block diffusion to enable temporal action generation. We partition action sequences into temporal blocks and perform masked discrete diffusion within each block, while maintaining autoregressive generation across blocks. This design unifies temporal autoregression and parallel action decoding, achieving both strong temporal coherence and improved inference speed. In addition, the explicit temporal modeling enables asynchronous execution of action chunks (e.g., Real-Time Chunking) via temporal in-painting. TBD-VLA significantly outperforms prior VLA approaches in both simulation and real-world manipulation tasks, offering a scalable path toward fast, temporally aware, discrete VLA models. Project webpage: https://tbd-vla.github.io/
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Robot Manipulation | LIBERO | Spatial Success Rate97.6 | 223 | |
| Robotic Manipulation | SimplerEnv WidowX | Spoon Success Rate52 | 17 | |
| Action Generation | LIBERO | Latency (s)0.117 | 10 | |
| Robotic Manipulation | SimplerEnv Google Robot Visual Matching | Pick Can Success Rate99.2 | 7 | |
| Robotic Manipulation | SimplerEnv Google Robot Variant Aggregation | Pick Can Success Rate97.2 | 7 | |
| Bread in Toaster | Real-world | ID Success Count95 | 4 | |
| Everything in Bin | Real-world | ID Success Rate85 | 4 | |
| Transfer the Liquid | Real-world | Success Rate (ID Condition)80 | 4 |