6340 papers
This letter proposes and evaluates two operating protocols, mode selection and mode combining, for multi-mode pinching-antenna systems to maximize sum rate in multi-user downlink communications via a jointly optimized PSO-KKT algorithm, demonstrating that mode combining offers superior spectral efficiency while mode selection provides a low-complexity alternative with comparable performance.
The paper proposes R2F, an LLM-free framework for zero-shot open-vocabulary object navigation that repurposes ray frontiers as direction-conditioned semantic hypotheses to achieve competitive performance with real-time execution, eliminating the latency and computational overhead of iterative large-model queries.
LAR-MoE is a two-stage framework that decouples unsupervised skill discovery from policy learning by regularizing expert routing to align with a learned latent representation, enabling robots to achieve high success rates in heterogeneous manipulation tasks without requiring manual skill annotations.
This paper demonstrates that large language model-powered generative agents, enhanced by in-context learning, can effectively relax the rigidity of traditional mathematical models to replicate both rational strategies and systematic behavioral deviations in power dispatch and auction scenarios.
This paper synthesizes drivers of human cybersecurity behavior within organizations into a coherent theoretical framework and proposes its application as a blueprint for securing agentic AI systems against manipulation attacks by drawing parallels between human and AI vulnerabilities.
3PoinTr is a novel method that pretrains robust robot manipulation policies from casual, unconstrained human videos by using a transformer architecture to predict 3D point tracks as an embodiment-agnostic intermediate representation, enabling sample-efficient learning with minimal robot demonstrations.
This paper proposes Visual Self-Fulfilling Alignment (VSFA), a label-free fine-tuning method that shapes safety-oriented personas in multimodal large language models by exposing them to threat-related images during neutral VQA tasks, thereby reducing attack success rates and mitigating over-refusal without compromising general capabilities.
This paper introduces an open-source, robot-agnostic surgical robotics platform featuring a deterministic, closed-form RCM controller and full-stack ROS integration, which achieves sub-millimeter precision and expert-level trajectory smoothness in autonomous laparoscopic tasks across phantom, ex vivo, and in vivo porcine models.
Spherical-GOF is a novel geometry-aware panoramic rendering framework that extends Gaussian Opacity Fields to spherical ray space, achieving superior geometric consistency and photometric quality in 3D scene reconstruction by introducing efficient spherical culling and adaptive filtering to overcome the limitations of existing perspective-based adaptations.
This paper introduces OccTrack360, a new benchmark for 4D panoptic occupancy tracking from surround-view fisheye cameras featuring long, diverse sequences and principled voxel visibility annotations, alongside the proposed Focus on Sphere Occ (FoSOcc) framework that effectively addresses fisheye distortion and localization challenges to establish a strong baseline for future research.
RetroAgent is an online reinforcement learning framework that enables LLM-based agents to evolve through a hindsight self-reflection mechanism generating dual intrinsic feedback—numerical progress tracking and retrievable language lessons via a novel SimUtil-UCB strategy—thereby achieving state-of-the-art performance and superior generalization on complex interactive tasks compared to existing methods.
This paper proposes RNDVoC, a scalable and lightweight neural vocoder that bridges classical range-null space decomposition with deep learning to achieve state-of-the-art performance while addressing challenges in model transparency, retraining flexibility, and parameter efficiency.
This paper proposes Online FISTA, a computationally and memory-efficient algorithm that incrementally reconstructs Synthetic Aperture Radar (SAR) images through sparse coding without storing all raw data, thereby enabling real-time downstream tasks like Automatic Target Recognition for autonomous drones.
PRISM introduces a streaming human motion generation framework that employs a joint-factorized latent space and noise-free condition injection within a single foundation model to overcome representation entanglement and error accumulation, thereby unifying text-to-motion, pose-conditioned, and long-horizon sequential synthesis with state-of-the-art performance.
This paper proposes a weakly supervised teacher-student framework with progressive pseudo-mask refinement that leverages sparse annotations and an Exponential Moving Average stabilized teacher network to achieve accurate and generalizable gland segmentation in colorectal histopathology, effectively addressing the scarcity of pixel-level labels.
This paper proposes a reachability-based framework that utilizes Signal Temporal Logic and an STL feasibility filter to verify and decompose LLM-translated human commands, enabling the identification of infeasible subformulas and the generation of informative feedback to ensure reliable and safe human-autonomy teaming.
This paper proposes a unified, real-time carbon-aware building energy management system that integrates a Transformer-based forecasting model with a mixed-integer linear program to co-optimize grid imports, storage, and flexible demand across day-ahead and real-time markets, achieving a 22.5% emission reduction with only a 1.7% cost increase.
This paper demonstrates that Generative AI tools, specifically the open-source CAI framework, have fundamentally disrupted consumer robot cybersecurity by automating the discovery of critical vulnerabilities across diverse devices like lawnmowers, exoskeletons, and window cleaners, thereby exposing a dangerous asymmetry between democratized offensive capabilities and lagging defensive measures.
This paper presents a simplified and fully analyzed sublinear-time algorithm that achieves a -approximation of the average degree in bounded arboricity graphs using queries, thereby recovering logarithmic factors lost in previous work and offering a modified version with query complexity.
This paper reviews and compares various R packages and methods for conducting Sentiment Analysis in educational contexts, demonstrating their practical application in processing student feedback to monitor teaching effectiveness and enhance learning experiences.