research note
This paper addresses the limitations in existing instruction-based video editing datasets, which largely focus on single-task appearance modifications and overlook complex structural edits and mult…
research note
This paper addresses the challenge of open-world affordance grounding for robot tool use, where a robot must select a suitable tool from a diverse set of objects and precisely localize task-relevan…
research note
LUMOS addresses a critical mismatch between current operating systems optimized for human users and the needs of AI agents interacting with desktop and.
research note
This paper addresses the challenging problem of autonomous UAV navigation for infrastructure inspection, where missions demand safe, energy-efficient, and time-conscious trajectories in dynamically…
research note
This paper examines the problem of detecting a new generation of web bots known as LLM-based Web Agents, which leverage large language models (LLMs) combined with browser automation to perform comp…
research note
This paper addresses a practical bottleneck in large-scale Large Language Model (LLM) pretraining using Pipeline Parallelism (PP)
research note
This paper investigates a widely held assumption in safe language model alignment that conservative offline training provides a safer initialization for subsequent online adaptation
research note
This paper investigates how logical bit errors arise in a driven Kerr-cat qubit, a superconducting nonlinear oscillator encoding quantum information in two stable coherent states (wells)
research note
This paper addresses the expensive and complex task of creating live product demonstrations for software applications, which traditionally require expert.
research note
This paper addresses a key limitation in Vision Transformer (ViT) based video models for facial expression recognition (FER) — the tendency of standard self-attention mechanisms to focus on dominant…
research note
This paper addresses the fundamental statistical difficulty of estimating valid transport maps between probability distributions, motivated by modern generative modeling methods such as diffusion m…
research note
This paper tackles the difficult problem of 3D hand-object pose estimation from challenging in-the-wild egocentric RGB videos, where the hands and objects are heavily occluded and contact regions a…
