Knowledge catalogue
arXiv:2605.08504v1 Announce Type: new Abstract: We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the extbf{Massive Emergence Layer
arXiv:2605.08513v1 Announce Type: cross Abstract: Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expr
arXiv:2605.10668v1 Announce Type: new Abstract: We propose a closed-form spectral framework for relative log-density estimation in linearly parameterized probabilistic models, including unnormalized a
arXiv:2605.10076v1 Announce Type: cross Abstract: Generative (diffusion) priors demonstrate remarkable performance in addressing inverse problems in imaging. Yet, for scientific and medical imaging, i
arXiv:2605.09094v1 Announce Type: new Abstract: In recent years, bilevel optimization (BLO) has attracted significant attention for its broad applications in machine learning. However, most existing w
arXiv:2605.08530v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for human perception due to its robustness under challenging environmental co
arXiv:2605.08488v1 Announce Type: cross Abstract: We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization
arXiv:2605.06375v1 Announce Type: cross Abstract: Large language model (LLM) alignment via reinforcement learning from human preferences (RLHF) suffers from unstable policy updates, ambiguous gradient
arXiv:2512.17593v3 Announce Type: replace Abstract: In this paper we consider the limiting case of neural networks (NNs) architectures when the number of neurons in each hidden layer and the number of
arXiv:2605.06226v2 Announce Type: replace Abstract: Accurate and timely diagnosis is essential for effective treatment, particularly in the context of rare diseases. However, current diagnostic workfl
arXiv:2605.08757v1 Announce Type: new Abstract: We present a visuo-tactile data-collection system that generates temporally structured, contact-rich demonstrations for imitation learning. Conventional
arXiv:2605.08692v1 Announce Type: cross Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference. Existing PTQ
arXiv:2605.09811v1 Announce Type: new Abstract: Multi-robot simultaneous localization and mapping (SLAM) is a fundamental task in multi-robot operations. Robots must have a common understanding of the
arXiv:2605.09678v1 Announce Type: new Abstract: While extremely powerful and versatile at various tasks, the thinking capabilities of large language models (LLMs) are often put under scrutiny as they
arXiv:2605.09755v1 Announce Type: cross Abstract: The power method is one of the most fundamental tools for extracting top principal components from data through low-rank matrix approximation. Yet, wh
arXiv:2605.09034v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization has become increasingly popular and important in fine-tuning large language models (LLMs), especially on edge devices due
arXiv:2605.10575v1 Announce Type: cross Abstract: Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject ar
arXiv:2605.06042v2 Announce Type: replace Abstract: Flapping-wing micro aerial vehicles offer quieter and safer operation than rotary-wing drones, yet achieving precise autonomous control of bird-scal
arXiv:2605.08887v1 Announce Type: new Abstract: Self-evolving agents present a promising path toward continual adaptation by distilling task interactions into reusable knowledge artifacts. In practice
arXiv:2602.06457v2 Announce Type: replace Abstract: Online bilevel optimization (OBO) has emerged as a powerful framework for many machine learning problems. Prior works have developed several algorit
arXiv:2603.01743v2 Announce Type: replace Abstract: Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of la
arXiv:2510.18184v3 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse aut
arXiv:2605.10654v1 Announce Type: cross Abstract: We consider the active learning problem where the goal is to learn an unknown function with low prediction error under an unknown Boltzmann distributi
arXiv:2605.08429v1 Announce Type: cross Abstract: Post-deployment monitoring of healthcare AI requires statistically valid, label-efficient methods, but gold-standard labels from clinician chart revie
arXiv:2605.10162v1 Announce Type: new Abstract: Reducing the annotation cost of oriented object detection in remote sensing remains a major challenge. Recently, sparse annotation has gained attention
arXiv:2605.10315v1 Announce Type: cross Abstract: Generative tabular augmentation is appealing in data-scarce domains, yet the prevailing focus on distributional fidelity does not reliably translate i
arXiv:2605.10075v1 Announce Type: new Abstract: Large language models (LLMs) require reliable evaluation from pre-training to test-time scaling, making evaluation a recurring rather than one-off cost.
arXiv:2605.08567v1 Announce Type: new Abstract: Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely res
arXiv:2605.08408v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a flexible framework for solving forward and inverse problems governed by partial differential equation
arXiv:2605.10741v1 Announce Type: new Abstract: Fine-tuning large language models with LoRA requires choosing a rank r before training starts. Existing approaches either extract rank-1 components sequ
arXiv:2605.08734v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) reparameterizes a weight update as a product of two low-rank factors, but the Jacobian J_{G} of the generator mapping the f
arXiv:2605.09455v1 Announce Type: new Abstract: Remote sensing image fusion aims to create a high-resolution multi/hyper-spectral image from a high-resolution image with limited spectral information a
arXiv:2605.10044v1 Announce Type: cross Abstract: Action chunking emerged as a pivotal technique in imitation learning, enabling policies to predict cohesive action sequences rather than single action
arXiv:2605.10470v1 Announce Type: new Abstract: Super-resolution (SR) is a severely ill-posed problem with inherent ambiguity, as widely recognized in both empirical and theoretical studies. Although
arXiv:2605.09707v1 Announce Type: cross Abstract: Training neural networks to satisfy universal constraints over continuous domains poses unique challenges. Common examples include Lyapunov Neural Net
arXiv:2512.13919v2 Announce Type: replace Abstract: This work shows how adaptivity can enhance value realization of digital twins in civil engineering. We focus on adapting the state transition models
arXiv:2605.09623v1 Announce Type: cross Abstract: In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to DNN p
arXiv:2510.04988v3 Announce Type: replace Abstract: The vast majority of modern deep learning models are trained with momentum-based first-order optimizers. The momentum term governs the optimizer's m
arXiv:2511.06216v4 Announce Type: replace Abstract: Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically r
arXiv:2605.10239v1 Announce Type: new Abstract: This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply comp
arXiv:2410.13181v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality
arXiv:2605.08130v1 Announce Type: new Abstract: We present a framework for the simultaneous symbolic recovery of a function and its antiderivative from data. The framework rests on three ideas. First,
arXiv:2605.08161v1 Announce Type: new Abstract: Tumor segmentation in whole-body PET/CT imaging is crucial for precise disease evaluation and treatment planning. However, it remains challenging due to
arXiv:2605.09902v1 Announce Type: new Abstract: Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risk
arXiv:2605.09337v1 Announce Type: new Abstract: We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--wo
arXiv:2605.10566v1 Announce Type: cross Abstract: Probabilistic linear solvers (PLSs) return probability distributions that quantify uncertainty due to limited computation in the solution of linear sy
arXiv:2605.10555v1 Announce Type: new Abstract: As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD
arXiv:2602.04284v2 Announce Type: replace Abstract: Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent eff
arXiv:2603.22868v2 Announce Type: replace-cross Abstract: Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of
arXiv:2605.10365v1 Announce Type: new Abstract: Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly dra
arXiv:2605.10380v1 Announce Type: new Abstract: LLM-based agents deliver state-of-the-art performance across tasks but incur high end-to-end latency on edge devices. We introduce Agent-X, a software-o
arXiv:2605.08647v1 Announce Type: cross Abstract: Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint,
arXiv:2605.08715v1 Announce Type: cross Abstract: LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and
arXiv:2605.08956v1 Announce Type: new Abstract: A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they alread
arXiv:2605.09186v1 Announce Type: new Abstract: Mixed-integer programming (MIP) research is both mathematically sophisticated and engineering-intensive: testing an algorithmic hypothesis within a bran
arXiv:2605.10384v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is a natural fit for Internet of Things (IoT) and edge systems, but edge deployments are often constrained to model
arXiv:2605.08704v1 Announce Type: new Abstract: Multi-agent reasoning has shown promise for improving the problem-solving ability of large language models by allowing multiple agents to explore divers
arXiv:2406.12708v3 Announce Type: replace Abstract: Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exp
arXiv:2605.10286v1 Announce Type: new Abstract: Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal e
arXiv:2605.08813v1 Announce Type: new Abstract: Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal com