6933 papers
SAIL is a test-time scaling framework that enhances one-shot robot imitation learning by reframing trajectory generation as an iterative refinement process guided by Monte Carlo Tree Search, an automated retrieval archive, and a vision-language model-based scoring mechanism, thereby significantly improving success rates across diverse manipulation tasks.
This paper introduces a prototype-guided approach that leverages the intrinsic embedding geometry of diffusion models to identify and cluster concept representations, enabling the reliable erasure of broad, multi-faceted concepts while preserving overall image quality.
This paper demonstrates that explicitly reducing observation dimensionality and implementing locality-aware credit assignment in a communication-free multi-agent system enhances robustness and performance in asymmetric 3D pursuit-evasion tasks within cluttered environments.
The paper proposes OSCAR, a label-free method that utilizes coupled latent spaces and neural implicit representations to accurately reconstruct complete 3D vertebral anatomy from partial ultrasound images by implicitly modeling acoustic shadowing and signal transmission, achieving an 80% improvement in HD95 score over state-of-the-art techniques.
This paper presents BladeChain, a blockchain-based system that integrates multi-stakeholder endorsement, automated scheduling, and AI model provenance to provide immutable, auditable traceability for aircraft engine blade inspections across the entire component life cycle.
The paper introduces SP-CLIP, a lightweight zero-shot action recognition framework that significantly improves performance on fine-grained and compositional actions by augmenting frozen vision-language models with structured, multi-level semantic prompts without requiring any additional parameter training or visual encoder modifications.
This paper systematically reviews recent advancements in Multimodal Mathematical Reasoning by proposing a unified Perception-Alignment-Reasoning paradigm, categorizing existing approaches around four fundamental questions regarding information extraction, representation, reasoning, and evaluation, while outlining future research challenges.
This paper introduces Silicone Ethernet (SEth), a wireless, battery-free system that embeds sensing, communication, and power transfer capabilities directly into a conductive silicone substrate to overcome the cabling limitations of fine-grained robotic touch sensing.
This paper presents the first systematic analysis of Attack Graph and Intrusion Detection System integration, proposing a novel unifying lifecycle framework that establishes a continuous feedback loop to enhance threat detection and incident response.
This paper demonstrates that Large Vision Language Models (LVLMs) develop human-aligned visual representations by quantifying their correspondence with EEG signals, revealing that intermediate layers, multimodal architecture, and downstream visual performance are key drivers of this neural alignment.
This paper proposes a retrieval-augmented framework for text-to-CT generation that leverages a 3D vision-language encoder to retrieve semantically related clinical cases and their anatomical annotations as structural proxies, thereby enhancing image fidelity and spatial controllability in a realistic inference setting without requiring ground-truth annotations.
This paper proposes an adaptive control framework for Euler-Lagrange systems that guarantees user-defined time-varying state and input constraints under uncertainties and disturbances by integrating a time-varying barrier Lyapunov function with a saturated control law, supported by an offline feasibility condition and validated through real-time helicopter experiments.
HDR-NSFF is a novel framework that reconstructs dynamic high dynamic range (HDR) radiance fields from monocular videos by shifting from 2D pixel alignment to 4D spatio-temporal modeling, utilizing exposure-invariant motion estimation and generative priors to achieve state-of-the-art view synthesis while introducing the first real-world HDR-GoPro dataset for evaluation.
This paper presents a large-scale comparative study using the Epic ReduAct dataset and over 3,000 human participants to demonstrate that while humans rely on sparse, semantically critical cues for egocentric action recognition, state-of-the-art AI models degrade more gradually by depending on contextual and low-level features, revealing fundamental divergences in how humans and machines process spatial and spatiotemporal information.
CORE-Acu is a neuro-symbolic framework for acupuncture clinical decision support that integrates structured reasoning traces, a knowledge graph-based safety verification system, and a specialized loss function to ensure interpretable, hallucination-free, and strictly safe treatment recommendations, outperforming standard LLMs with zero observed safety violations.
EndoSERV is a novel vision-based navigation system for endoluminal robots that overcomes challenges like tissue deformation and label scarcity by combining segment-to-structure odometry with real-to-virtual transfer learning to achieve accurate localization without requiring real-world pose labels.
This paper investigates the computational complexity of context-free, pushdown, and one-counter automata based on the number of "turns" (switches between increasing and decreasing stack height) in accepting computations, proving that determining whether this number is bounded is undecidable, establishing non-recursive trade-offs between automata types, and demonstrating an infinite hierarchy of complexity classes defined by sublinear turn bounds.
The paper proposes DS-DGA-GCN, an adaptive graph learning model that integrates diversity- and similarity-aware dynamic graph attention with a Network Feature Scoring system to effectively detect organized fake reviewer groups in dynamic networks, achieving state-of-the-art performance on real-world datasets.
This paper reviews and analyzes various coordination schemes between Transmission and Distribution System Operators (TSOs and DSOs) to effectively integrate Distributed Energy Resources, aiming to maintain system balance and prevent network congestion while overcoming technical and market challenges associated with the ongoing energy transition.
This paper introduces HIMoS, a hierarchical multi-modal planning framework that enables Autonomous Underwater Vehicles to efficiently search for and sample sparse benthic targets like coral colonies at a fixed altitude by integrating a global topological route optimizer with a local differentiable belief propagation planner, thereby outperforming traditional exhaustive and adaptive sampling strategies in high-fidelity simulations.