Related papers: iMOLSDOCK : induced-fit docking using mutually ort…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often…

In this paper, we propose a physical layer security scheme that exploits a novel index modulation (IM) technique for coordinate interleaved orthogonal designs (CIOD). Utilizing the diversity gain of CIOD transmission, the proposed scheme,…

We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion. Our model comprehensively processes entire pages by generating DocTags, a new universal markup format that captures all page elements…

Potentiostatic impedance spectroscopy (IS) is a well stablished characterization technique for elucidating the electric resistivity and capacitive features of materials and devices. In the case of solar cells, by applying a small voltage…

This paper introduces a novel approach of utilizing the reconfigurable intelligent surface (RIS) for joint data modulation and signal beamforming in a multi-user downlink cellular network by leveraging the idea of backscatter communication.…

This study addresses the generalization limitations commonly observed in large language models under multi-task and cross-domain settings. Unlike prior methods such as SPoT, which depends on fixed prompt templates, our study introduces a…

Soft robots have become increasingly popular for complex manipulation tasks requiring gentle and safe contact. However, their softness makes accurate control challenging, and high-fidelity sensing is a prerequisite to adequate control…

We improved a previously proposed method of using closed-orbit modulation for linear optics correction. Instead of fitting individual closed orbits, the improved method decomposes the orbit oscillation data into two orthogonal modes and…

This paper proposes a hybrid learning and optimization framework for mobile manipulators for complex and physically interactive tasks. The framework exploits an admittance-type physical interface to obtain intuitive and simplified human…

Instruction tuning has become the de facto method to equip large language models (LLMs) with the ability of following user instructions. Usually, hundreds of thousands or millions of instruction-following pairs are employed to fine-tune the…

Accurate registration between a prior model and the real scene is essential for high-precision robotic manipulation, yet optical methods suffer from long calibration chains, line-of-sight constraints, and fabrication errors. We propose a…

Dopants can tune the performance of MoS2 in various applications, but use of molecular dynamics simulations for doped MoS2 materials discovery is limited by the lack of multi-dopant interatomic potentials. Universal machine learning…

Motivation: Prediction of ligands for proteins of known 3D structure is important to understand structure-function relationship, predict molecular function, or design new drugs. Results: We explore a new approach for ligand prediction in…

The instability of embedding spaces across model retraining cycles presents significant challenges to downstream applications using user or item embeddings derived from recommendation systems as input features. This paper introduces a novel…

Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to…

We propose an accurate and robust multi-modal sensor fusion framework, MetroLoc, towards one of the most extreme scenarios, the large-scale metro vehicle localization and mapping. MetroLoc is built atop an IMU-centric state estimator that…

In many applications of advanced robotic manipulation, six degrees of freedom (6DoF) object pose estimates are continuously required. In this work, we develop a multi-modality tracker that fuses information from visual appearance and…

Performing long-term experimentation or large-scale data collection for machine learning in the field of soft robotics is challenging, due to the hardware robustness and experimental flexibility required. In this work, we propose a modular…

Difference arrays are used in applications such as software testing, authentication codes and data compression. Pseudo-orthogonal Latin squares are used in experimental designs. A special class of pseudo-orthogonal Latin squares are the…

Molecular dynamics (MD) simulation is widely used to study protein conformations and dynamics. However, conventional simulation suffers from being trapped in some local energy minima that are hard to escape. Thus, most computational time is…