19 accepted papers
Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single images or set of images, where answers can be inferred from a s
How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However, existing methods rely on uniform precision, ignoring the divers
Recent studies have revealed Neural Collapse (NC) in deep classifiers, where last-layer weights and features align into an equiangular tight frame (ETF), concentrating class information along specific embedding directions. However, conventional fine-tuning typically disregards this structure, initi
What happens when multiple compression methods are combined—does the order in which they are applied matter? Joint model compression has emerged as a powerful strategy to achieve higher efficiency by combining multiple methods such as pruning and quantization. A central but underexplored factor in j…
The existing assessments of planning capabilities of large language models (LLMs) remain largely limited to single-language or specific representation formats. To address this gap, we introduce the Multi-Plan benchmark comprising 204 multilingual and multi-format travel planning scenarios. In experi
Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In real-world applications, however, preceding contexts often trigger t…
Fractional-order (FO) control, which employs non-integer orders of differintegration, has been adopted for its advantages in generalized controller design or reduced modeling complexity. For compliance control, FO impedance is employed as a generalization of conventional integer-order (IO) impedance
How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy…
How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (BCQ) and uniform quantization (UQ) are promising quantization schemes that have strong expressiveness and optimizability,…
We propose the VLR-Bench, a visual question answering (VQA) benchmark for evaluating vision language models (VLMs) based on retrieval augmented generation (RAG). Unlike existing evaluation datasets for external knowledge-based VQA, the proposed VLR-Bench includes five input passages. This allows tes…
Network quantization has proven to be a powerful approach to reduce the memory and computational demands of deep learning models for deployment on resource-constrained devices. However, traditional quantization methods often rely on access to training data, which is impractical in many real-world sc
The current research direction in generative models, such as the recently developed GPT4, aims to find relevant knowledge information for multimodal and multilingual inputs to provide answers. Under these research circumstances, the demand for multilingual evaluation of visual question answering (VQ…
The impressive development of large language models (LLMs) is expanding into the realm of large multimodal models (LMMs), which incorporate multiple types of data beyond text. However, the nature of multimodal models leads to significant expenses in the creation of training data. Furthermore, constr…
Reconfigurable modular robots can dynamically assemble/disassemble to accomplish the desired task better. Magnetic modular cubes are scalable modular subunits with embedded permanent magnets in a 3D-printed cubic body and can be wirelessly controlled by an external, uniform, time-varying magnetic fi
CROSS exchange (CE), a meta-heuristic that solves various vehicle routing problems (VRPs), improves the solutions of VRPs by swapping the sub-tours of the vehicles. Inspired by CE, we propose Neuro CE (NCE), a fundamental operator of \textit{learned} meta-heuristic, to solve various min-max VRPs whi…
This paper examines a family of designs for magnetic cubes and counts how many configurations are possible for each design as a function of the number of modules. Magnetic modular cubes are cubes with magnets arranged on their faces. The magnets are positioned so that each face has either magnetic s…
Magnetic millirobots can be controlled remotely by external magnetic fields, making them promising candidates for biomedical and engineering applications. This letter presents a low-cost millirobot that is simple in design, easy to fabricate, highly scalable, and can be used as modular sub-units wit
This paper proposes a simple model-free joint torque control strategy for hydraulic robots. The undesirable effect called “natural velocity feedback effect” is discussed by introducing mechanical impedance of the system. The proposed model-free joint torque control consists of internal-loop control
This paper proposes a passivity-based nonlinear disturbance observer (DOB) design for a powered upper-limb robot control. The proposed DOB allows for the nonlinearities of the robot dynamics, whereas the typical DOB designs cannot. Moreover, by virtue of the passivity property, human operator and en