In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based on visual observations and natural language instructions. This task is essential for service robots that operate in human environments, and requires safety, efficiency, and task-level generality. Although Vision-Language-Action models (VLAs) have demonstrated strong performance for this task, their deployment in resource-constrained environments remains challenging because of the computational cost of standard transformer backbones. To overcome this limitation, we propose AnolisVLA, a lightweight VLA that uses a deep state space model to process multimodal sequences efficiently. The model uses lightweight, fast sequential state modeling to process visual and textual inputs. This design enables efficient trajectory generation. We evaluated the proposed method in simulation and on two real robot platforms. Compared with SmolVLA at a comparable parameter scale, AnolisVLA achieved higher task success rates, faster inference, and comparable GPU memory usage. In mobile manipulation, it outperformed the larger, 3-billion-parameter π0.5 model by 21 percentage points in task success rate while achieving approximately three times faster inference.
Figures & tables
Figure 1: Overview of AnolisVLA and real-world performance. (Left) Our deep SSM backbone processes language instructions and robot observations to generate trajectories, leveraging a two-stage training strategy with the acceleration loss to improve temporal consistency in action sequences. (Right) Real-world mobile manipulation experiment results. The horizontal and vertical axes represent inference speed and the average success rate, respectively.
Figure 2: Model architecture of AnolisVLA. Multimodal tokens, including proprioception, state delta, vision, and language, are concatenated and processed by a Mamba backbone, and the final token predicts an H -step action chunk. The two-stage training supervises action commands and their temporal differences. Here, s(t) , Δs(t) , xv(t) , and xl denote the state, state delta, visual observation, and language instruction at time step t , respectively. On the right-hand side, y^ and y denote the predicted future actions and ground truth, while Δy^ and Δy denote their temporal differences.
Method
Total Params
Easy
Medium
Hard
Very Hard
Avg.
π0.5 [ 1 ]
3.0 B
68.20
37.30
41.70
28.00
43.80
VLA-Adapter [ 29 ]
0.5 B
3.75
0.00
0.00
0.00
0.94
TinyVLA [ 30 ]
0.42 B
77.60
21.50
11.40
15.80
31.58
SmolVLA [ 23 ]
0.45 B
82.50
41.80
45.00
60.00
57.33
AnolisVLA
0.47 B
92.86
72.73
91.67
60.00
79.32
Table 1: Quantitative comparison between AnolisVLA and the baseline methods on the Meta-World benchmark. The best results are highlighted in bold , and the second-best results are underlined .
Figure 3: Qualitative results. We display the initial observation xv(0) and the chronological sequence of observations xv(t) during task execution. In each example, the robot executes the task based on the following instructions: (a) “Pick and place a puck onto a shelf.” (b) “Hammer a screw on the wall.” (c) “Push the puck to a goal.”
Model
Backbone
Acceleration loss
Success rate [%]
(i)
SmolLM (Transformer)
✓
76.00
(ii)
Mamba-370M (Mamba)
74.59
(iii)
Mamba-370M (Mamba)
✓
79.32
Table 2: Quantitative results of the ablation studies. The table presents the average success rates on the Meta-World benchmark. The best score is in bold.
Figure 4: (a) Robot platform and experimental environment used in the mobile manipulation experiments. We used the Human Support Robot (HSR) as the robot platform. (b) Everyday objects used in the experiments. We used objects with diverse appearances, shapes, and sizes to emulate common household manipulation scenarios. (c) ALOHA robot platform and experimental setup used in the tabletop manipulation experiments.
Method
Success rate [%]
Mobile move
Mobile pick
Mobile open
Mobile close
Mobile push
Avg.
π0.5 [ 1 ]
15
20
30
100
45
42
VLA-Adapter [ 29 ]
35
20
0
100
45
40
TinyVLA [ 30 ]
5
15
0
90
35
29
SmolVLA [ 23 ]
30
25
55
100
50
52
AnolisVLA
45
40
75
100
55
63
Table 3: Quantitative comparison between AnolisVLA and the baseline methods in mobile manipulation experiments. The best results are highlighted in bold , and the second-best results are underlined .
Method
Success rate [%]
Inference time ↓
VRAM ↓
Stack cup
Put in drawer
Avg.
[ms/chunk]
[GB]
π0.5 [ 1 ]
70
80
75
578
17.05
VLA-Adapter [ 29 ]
50
30
40
101
4.65
TinyVLA [ 30 ]
30
40
35
1290
2.38
SmolVLA [ 23 ]
40
70
55
309
1.56
AnolisVLA
60
80
70
216
1.64
Table 4: Quantitative comparison between AnolisVLA and the baseline methods on the ALOHA robot, including task success rates, inference time, and inference-time VRAM consumption. The ‘VRAM’ column reports the inference-time GPU memory consumption. The best results are highlighted in bold , and the second-best results are underlined .
Figure 5: Successful episodes of AnolisVLA in the real-world experiments. Instructions were as follows: (a) “Open the drawer.” (b) “Put the lemon into the cup.” (c) “Put the object in the drawer.” (d) “Stack the cups.”
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · The Chinese University of Hong Kong · Simplexity Robotics