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

Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…

Recent advances in visual reasoning (VR), particularly with the aid of Large Vision-Language Models (VLMs), show promise but require access to large-scale datasets and face challenges such as high computational costs and limited…

Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache…

This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL…

Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level),…

We present a new implementation of radiation hydrodynamics (RHD) in the adaptive mesh refinement (AMR) code RAMSES. The multi-group radiative transfer (RT) is performed on the AMR grid with a first-order Godunov method using the M1 closure…

While Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge, conventional single-agent RAG remains fundamentally limited in resolving complex queries demanding coordinated reasoning across…

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can…

This report presents the development and results of an advanced SPH (Smoothed Particle Hydrodynamics) simulation framework, designed for high fidelity fluid dynamics modeling. Our framework, accessible at…

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

We present a framework for achieving end-to-end management objectives for multiple services that concurrently execute on a service mesh. We apply reinforcement learning (RL) techniques to train an agent that periodically performs control…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

With the rapid growth of user historical behavior data, user interest modeling has become a prominent aspect in Click-Through Rate (CTR) prediction, focusing on learning user intent representations. However, this complexity poses…

Developing robotic manipulation policies is iterative and hypothesis-driven: researchers test tactile sensing, gripper geometries, and sensor placements through real-world data collection and training. Yet even minor end-effector changes…

With advancements in computer vision and deep learning, video-based human action recognition (HAR) has become practical. However, due to the complexity of the computation pipeline, running HAR on live video streams incurs excessive delays…

Recent advancements in 3D Gaussian Splatting (3DGS) have enabled photorealistic rendering of complex scenes, yet widespread adoption on mobile and Extended Reality (XR) devices is hindered by substantial computational and bandwidth…

Memory systems for LLM agents struggle to determine what information deserves retention. Existing approaches rely on predefined heuristics such as importance scores, emotional tags, or factual templates, encoding designer intuition rather…

Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training dynamics across modalities often lead to suboptimal accuracy…

Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enabling a favorable trade-off between computational speed and…