394138 results (page 4 of 15766)
-
FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators
Fast grasping is critical for mobile robots in logistics, manufacturing, and service applications. Existing methods face fundamental challenges in impact stabilization under high-speed motion, real-time whole-body coordination, and generalization across diverse objects and scenarios, limited by fixed bases, simple grippers, or slow tactile response capabilities. We propose \textbf{FastGrasp}, a le…
-
AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance
The rapid expansion of large language model (LLM) safety evaluation has produced a substantial benchmark ecosystem, but not a correspondingly coherent measurement ecosystem. We present AISafetyBenchExplorer, a structured catalogue of 195 AI safety benchmarks released between 2018 and 2026, organized through a multi-sheet schema that records benchmark-level metadata, metric-level definitions, bench…
-
LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems
The rapid advancement of AI has changed the character of HPC usage such as dimensioning, provisioning, and execution. Not only has energy demand been amplified, but existing rudimentary continual learning capabilities limit ability of AI to effectively manage HPCs. This paper reviews emerging directions beyond monolithic transformers, emphasizing agentic AI and brain inspired architectures as comp…
-
OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation
Object Goal Navigation (ObjectNav) refers to an agent navigating to an object in an unseen environment, which is an ability often required in the accomplishment of complex tasks. While existing methods demonstrate proficiency in isolated single object navigation, their limitations emerge in the restricted applicability of lifelong memory representations, which ultimately hinders effective navigati…
-
Hot blue progenitors of stellar-mass black holes
While the connection between massive stars and supernova explosions is well established observationally, the link between massive stars and black hole formation remains elusive. Some massive stars may collapse directly to black holes without a successful supernova, and may therefore appear as disappearing stars. We investigate the expected photometric properties of such black hole progenitors by c…
-
QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi DeepResearch, a powerful agentic foundation model, we focus on the Chinese medical deep search scenario and propose QuarkMedSearch, systematically exploring a full-pipeline approach spanning medical multi-hop data constru…
-
From edges to meaning: Semantic line sketches as a cognitive scaffold for ancient pictograph invention
Humans readily recognize objects from sparse line drawings, a capacity that appears early in development and persists across cultures, suggesting neural rather than purely learned origins. Yet the computational mechanism by which the brain transforms high-level semantic knowledge into low-level visual symbols remains poorly understood. Here we propose that ancient pictographic writing emerged from…
-
JWST observations of photodissociation regions. IV. Carbonaceous emission band sub-components in NGC 7023 have distinct spatial distributions
We analyze JWST spectroscopy of the northwest filament of NGC7023, where the relatively soft radiation field results in a photodissociation region with an extended atomic hydrogen region, and strongly pronounced variations of the carbonaceous emission band profiles. We focus on the 16.4 and 17.4 um bands and their relation to the main bands at 3.3, 3.4, 5.2, 5.7, 6.2, 7.7, 8.6, 11.3, and 12.7 um, …
-
Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic
Autonomous vehicles (AVs) are now operating on public roads, which makes their testing and validation more critical than ever. Simulation offers a safe and controlled environment for evaluating AV performance in varied conditions. However, existing simulation tools mainly focus on graphical realism and rely on simple rule-based models and therefore fail to accurately represent the complexity of dr…
-
PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination
Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on acoustic-only representations lacking symbolic priors, employ inflexible interaction mechanisms, and are limited to computationally expensive short-sequence generation. To address these limitations, we propose PianoFlow, …
-
Evolving the Complete Muscle: Efficient Morphology-Control Co-design for Musculoskeletal Locomotion
Musculoskeletal robots offer intrinsic compliance and flexibility, providing a promising paradigm for versatile locomotion. However, existing research typically relies on models with fixed muscle physiological parameters. This static physical setting fails to accommodate the diverse dynamic demands of complex tasks, inherently limiting the robot's performance upper bound. In this work, we focus on…
-
PAINT: Partner-Agnostic Intent-Aware Cooperative Transport with Legged Robots
Collaborative transport requires robots to infer partner intent through physical interaction while maintaining stable loco-manipulation. This becomes particularly challenging in complex environments, where interaction signals are difficult to capture and model. We present PAINT, a lightweight yet efficient hierarchical learning framework for partner-agonistic intent-aware collaborative legged tran…
-
EXTree: Towards Supporting Explainability in Attribute-based Access Control
With increasing emphasis on transparency in digital governance, users expect more than silence when their access requests are denied by a system. However, authorization methods are notorious for their inability to provide any form of meaningful feedback under such situations. This paper shows a direction towards how the problem of explainability can be mitigated in the context of Attribute-based A…
-
Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration
The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are often evaluated on different samples, making scores difficult to compare across studies. To address this, we propose a framework based on multidimensional Item Response Theory (IRT) that uses anchor items to calibrate new benchmarks to the evaluati…
-
The role of accretion efficiency, natal kicks, and angular momentum transport in the formation of the Gaia black holes
Gaia has the potential to deliver several tens of new dormant black holes (BHs) with low-mass stellar companions (hereafter, Gaia BHs) in the upcoming fourth data release. Three Gaia BHs are already known, but their formation pathways remain uncertain. Here, we perform a large parametric study to explore the formation of Gaia BHs from isolated binary systems with the population-synthesis code SEVN…
-
GGD-SLAM: Monocular 3DGS SLAM Powered by Generalizable Motion Model for Dynamic Environments
Visual SLAM algorithms achieve significant improvements through the exploration of 3D Gaussian Splatting (3DGS) representations, particularly in generating high-fidelity dense maps. However, they depend on a static environment assumption and experience significant performance degradation in dynamic environments. This paper presents GGD-SLAM, a framework that employs a generalizable motion model to…
-
Rapid LoRA Aggregation for Wireless Channel Adaptation in Open-Set Radio Frequency Fingerprinting
Radio frequency fingerprints (RFFs) enable secure wireless authentication but struggle in open-set scenarios with unknown devices and varying channels. Existing methods face challenges in generalization and incur high computational costs. We propose a lightweight, self-adaptive RFF extraction framework using Low-Rank Adaptation (LoRA). By pretraining LoRA modules per environment, our method enable…
-
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely unexplored. As VLMs are increasingly deployed in real environments, this gap becomes critical, since adversarial perturbations must be physically realizable. Despit…
-
Detecting and refurbishing ground truth errors during training of deep learning-based echocardiography segmentation models
Deep learning-based medical image segmentation typically relies on ground truth (GT) labels obtained through manual annotation, but these can be prone to random errors or systematic biases. This study examines the robustness of deep learning models to such errors in echocardiography (echo) segmentation and evaluates a novel strategy for detecting and refurbishing erroneous labels during model trai…
-
VULCAN: Vision-Language-Model Enhanced Multi-Agent Cooperative Navigation for Indoor Fire-Disaster Response
Indoor fire disasters pose severe challenges to autonomous search and rescue due to dense smoke, high temperatures, and dynamically evolving indoor environments. In such time-critical scenarios, multi-agent cooperative navigation is particularly useful, as it enables faster and broader exploration than single-agent approaches. However, existing multi-agent navigation systems are primarily vision-b…
-
Loop Corrections to the Training and Generalization Errors of Random Feature Models
We investigate random feature models in which neural networks sampled from a prescribed initialization ensemble are frozen and used as random features, with only the readout weights optimized. Adopting a statistical-physics viewpoint, we study the training, test, and generalization errors beyond the mean-kernel approximation. Since the predictor is a nonlinear functional of the induced random kern…
-
The illusory simplicity of the feedforward pass: evidence for the dynamical nature of stimulus encoding along the primate ventral stream
In studying primate vision, a large body of work focuses on the first feedforward sweep. During this initial time window, information is thought to pass through ventral stream regions in a stage-like fashion in an effort to extract high-level information from the retinal input. Consequently, electrophysiological analyses commonly focus on spatial response patterns, either by averaging data in time…
-
RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair
Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for selective removal. While machine unlearning offers a principled solution, existing approaches are provider-centric, requiring retraining pipelines, curated retain datasets, and direct intervention by model service providers …
-
Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory
Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that searches for adversarial inputs within the continuous embedding space of LLMs during AT. While CAT has achieved empirical success, its underlying mechanism, i.e., …
-
The role of System 1 and System 2 semantic memory structure in human and LLM biases
Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates bias, but the cognitive mechanisms that give rise to this phenomenon remain poorly understood. To better understand what underlies this duality in humans, and pos…