A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene

Pre-trained vision-language (V-L) models such as CLIP have shown excellent performance in many downstream cross-modal tasks. However, most of them are only applicable to the English context. Subsequent research has focused on this problem and proposed improved models, such as CN-CLIP and AltCLIP, to facilitate their applicability to Chinese and even other languages. Nevertheless, these models suffer from high latency and a large memory footprint in inference, which limits their further deployment on resource-constrained edge devices. In this work, we propose a conceptually simple yet effective multilingual CLIP Compression framework and train a lightweight multilingual vision-language model, called DC-CLIP, for both Chinese and English context. In this framework, we collect high-quality Chinese and English text-image pairs and design two training stages, including multilingual vision-language feature distillation and alignment. During the first stage, lightweight image/text student models are designed to learn robust visual/multilingual textual feature representation ability from corresponding teacher models, respectively. Subsequently, the multilingual vision-language alignment stage enables effective alignment of visual and multilingual textual features to further improve the model's multilingual performance. Comprehensive experiments in zero-shot image classification, conducted based on the ELEVATER benchmark, showcase that DC-CLIP achieves superior performance in the English context and competitive performance in the Chinese context, even with less training data, when compared to existing models of similar parameter magnitude. The evaluation demonstrates the effectiveness of our designed training mechanism.

Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark

The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these models predominantly excel in text-based tasks, overlooking the complexity of real-world multimodal information. This study introduces MultiAPI, a pioneering comprehensive large-scale API benchmark dataset aimed at expanding LLMs' proficiency in multimodal contexts. Developed collaboratively through ChatGPT, MultiAPI consists of 235 diverse API calls and 2,038 contextual prompts, offering a unique platform evaluation of tool-augmented LLMs handling multimodal tasks. Through comprehensive experiments, our findings reveal that while LLMs demonstrate proficiency in API call decision-making, they face challenges in domain identification, function selection, and argument generation. What's more, we surprisingly notice that auxiliary context can actually impair the performance. An in-depth error analysis paves the way for a new paradigm to address these challenges, suggesting a potential direction for future LLM research.

A Bioinspired Bidirectional Stiffening Soft Actuator for Multimodal, Compliant, and Robust Grasping

The stiffness modulation mechanism for soft robotics has gained considerable attention to improve deformability, controllability, and stability. However, for the existing stiffness soft actuator, high lateral stiffness and a wide range of bending stiffness are hard to be provided at the same time. This paper presents a bioinspired bidirectional stiffening soft actuator (BISA) combining the air-tendon hybrid actuation (ATA) and a bone-like structure (BLS). The ATA is the main actuation of the BISA, and the bending stiffness can be modulated with a maximum stiffness of about 0.7 N/mm and a maximum magnification of 3 times when the bending angle is 45 deg. Inspired by the morphological structure of the phalanx, the lateral stiffness can be modulated by changing the pulling force of the BLS. The lateral stiffness can be modulated by changing the pulling force to it. The actuator with BLSs can improve the lateral stiffness about 3.9 times compared to the one without BLSs. The maximum lateral stiffness can reach 0.46 N/mm. And the lateral stiffness can be modulated decoupling about 1.3 times (e.g., from 0.35 N/mm to 0.46 when the bending angle is 45 deg). The test results show the influence of the rigid structures on bending is small with about 1.5 mm maximum position errors of the distal point of actuator bending in different pulling forces. The advantages brought by the proposed method enable a soft four-finger gripper to operate in three modes: normal grasping, inverse grasping, and horizontal lifting. The performance of this gripper is further characterized and versatile grasping on various objects is conducted, proving the robust performance and potential application of the proposed design method.

A Soft-rigid Hybrid Actuator with Multi-direction Tunable Stiffness Property

The ability to maintain compliance during interaction with the human or environments while avoiding the undesired destabilization could be extremely important for further application in practicality for soft actuators. In this paper, a soft-rigid hybrid actuator with multi-direction tunable stiffness property was proposed. The multi-direction tunable stiffness property, which means that the stiffness of multiple directions can be decoupled for modulation, was achieved in two orthogonal directions, the bending direction (B direction) and the direction perpendicular to bending (PB direction). In the B direction, the stiffness was modulated through the antagonistic effect of the tendon-air hybrid driven; In the PB direction, the jamming effect brought by a novel structure, the bone-like structure (BLS), reinforces the PB-direction stiffness. Meanwhile, in this paper, the corresponding fabrication method to ensure airtightness was designed, and the working principle for the two mechanisms of the actuator was evaluated. Finally, a series of experiments have been conducted to characterize the performance of the actuator and analyze the stiffness variation in two orthogonal directions. According to the tests, the maximum fingertip force reached 7.83N. And the experiments showed that stiffness in two directions can be tuned respectively. The B-direction stiffness can be tuned 1.5-4 times with a maximum stiffness of 1.24 N/mm. The PB-direction stiffness was enhanced about 4 times compared with the actuator without the mechanism, and it can be tuned decoupling with a range of 1.5 times.