Related papers: Improving Front-end Performance through Modular Re…

Inference on large-language models (LLMs) is constrained by GPU memory capacity. A sudden increase in the number of inference requests to a cloud-hosted LLM can deplete GPU memory, leading to contention between multiple prompts for limited…

Industrial recommender systems usually employ multi-source data to improve the recommendation quality, while effectively sharing information between different data sources remain a challenge. In this paper, we introduce a novel Multi-View…

Detecting human actions is a crucial task for autonomous robots and vehicles, often requiring the integration of various data modalities for improved accuracy. In this study, we introduce a novel approach to Human Action Recognition (HAR)…

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented…

With the increasing computational capability of mobile devices, deploying agentic retrieval-augmented generation (RAG) locally on heterogeneous System-on-Chips (SoCs) has become a promising way to enhance LLM-based applications. However,…

This paper proposes a two-level hierarchical matching framework for Integrated Hybrid Resources (IHRs) with grid constraints. An IHR is a collection of Renewable Energy Sources (RES) and flexible customers within a certain power system…

This paper presents a hybrid approach to predict the evolution of technological maturity in R and D projects, using the oil and gas sector as an example. Integrating System Dynamics (SD) and Agent Based Modelling (ABM) allows the proposed…

Modern recommender systems face critical challenges in handling information overload while addressing the inherent limitations of multimodal representation learning. Existing methods suffer from three fundamental limitations: (1) restricted…

Neural Radiance Field (NeRF) based rendering has attracted growing attention thanks to its state-of-the-art (SOTA) rendering quality and wide applications in Augmented and Virtual Reality (AR/VR). However, immersive real-time (> 30 FPS)…

Sequential recommender systems (SRS) have become a research hotspot due to its power in modeling user dynamic interests and sequential behavioral patterns. To maximize model expressive ability, a default choice is to apply a larger and…

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in…

Reaction feasibility prediction, as a fundamental problem in computational chemistry, has benefited from diverse tools enabled by recent advances in artificial intelligence, particularly large language models. However, the performance of…

Numerical simulations of two-phase flow and fluid structure interaction problems are of great interest in many environmental problems and engineering applications. To capture the complex physical processes involved in these problems, a high…

Is there a way for a designer to evaluate the performance of a given hood frame geometry without spending significant time on simulation setup? This paper seeks to address this challenge by developing a multimodal machine-learning (MMML)…

A key strategy in societal adaptation to climate change is using alert systems to prompt preventative action and reduce the adverse health impacts of extreme heat events. This paper implements and evaluates reinforcement learning (RL) as a…

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model…

Due to the limited availability of paired multi-modal data, multi-modal trackers are typically built by adopting pre-trained RGB models with parameter-efficient fine-tuning modules. However, these fine-tuning methods overlook advanced…

The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-efficient tuning methods, such as learning adapter layers or…

Recent advances in Visual Question Answering (VQA) have demonstrated impressive performance in natural image domains, with models like LLaVA leveraging large language models (LLMs) for open-ended reasoning. However, their generalization…