
research note
KVEraser — Learning to Steer KV Cache for Efficient Localized Context Erasing
KVEraser addresses the computational challenge of post-hoc localized context erasing in long-context large language model (LLM) inference

research note
KVEraser addresses the computational challenge of post-hoc localized context erasing in long-context large language model (LLM) inference

research note
LabOSBench addresses the challenge of evaluating computer-use AI agents on scientific instrument GUIs, where controlling sophisticated devices involves complex, procedural, feedback-driven workflows

research note
This survey paper addresses the emerging field of shape space analysis, a mathematical and computational framework for studying datasets whose observations have intrinsic geometric structure

research note
This study tackles the observational gap linking nuclear quasar winds to their extended galactic-scale outflows across parsec-to-kiloparsec scales

research note
MYPCBENCH addresses a significant gap in evaluating personal assistant agents for computers — current benchmarks test agents in impersonal, empty environments, lacking persistent user data, context,…

research note
This work addresses the significant bottleneck in training computer-use agents (CUAs), models that interact with full graphical desktop environments via screenshots and keyboard/mouse actions

research note
This paper addresses a major challenge in robotic Vision-Language-Action (VLA) model post-training, specifically for complex humanoid robots with dexterous hands

research note
This paper provides a comprehensive systematization of the low-level attack surface in modern web browsers, focusing on memory corruption vulnerabilities as the dominant exploit vector

research note
This paper addresses the difficult problem of disentangling overlapping hadronic resonances in the π+π− invariant mass spectrum above the ρ0(770) meson, particularly in ultra-peripheral heavy-ion c…

research note
SurroundNEXO addresses a critical problem in autonomous driving — metric-depth estimation from surround-view multi-camera rigs with extremely low overlapping fields of view (FoV)

research note
This paper studies a critical consistency vulnerability in Polymarket, a leading decentralized prediction market platform, arising from its hybrid architecture that matches orders off-chain but set…

research note
This paper addresses the long-standing challenge of compact third-order spherical aberration correction for continuous low-energy electron beams, especially relevant to scanning electron microscopy…