7493 papers
This paper introduces RecPilot, a multi-agent framework that shifts the recommender system paradigm from passive item filtering to proactive, user-centric assistance by generating comprehensive, synthesized reports that significantly reduce user effort in item evaluation.
This paper proposes a method to reconstruct high-level creative workflows from low-level system logs by parsing raw data into structured behavioral graphs, thereby enabling future process-aware AI agents to better understand user intent and assist in creative tasks.
This paper argues that relying solely on fixed embedding similarity for analyzing creative processes in AI design tools is insufficient because it fails to capture meaningful creative pivots, and it outlines three key challenges—aligning metrics with creative significance, handling multimodal traces, and evaluating agentic systems—while proposing context-aware LLM interventions to better capture session-specific dynamics.
This paper proposes an unsupervised deep learning method using two neural-field networks with periodic activation functions to model water surface height and reconstruct undistorted underwater images from aerial views, outperforming existing approaches on both simulated and real data.
This paper identifies "overthinking"—the propagation of incorrect intermediate hypotheses across decoder layers—as a primary cause of hallucinations in Vision Language Models and introduces the Overthinking Score, a layer-probing metric that significantly outperforms existing final-output-based detectors.
This paper evaluates the open-source CODECO toolkit, demonstrating that it significantly reduces manual intervention and maintains competitive performance compared to baseline Kubernetes workflows for automating multi-service deployments across heterogeneous Edge-Cloud environments.
GeoLoco is a robust, RGB-only humanoid locomotion framework that leverages geometric priors from a frozen Visual Foundation Model and a specialized cross-attention mechanism to achieve zero-shot sim-to-real transfer on the Unitree G1 without relying on active depth sensors.
The paper proposes Duala, a dual-level alignment framework that enhances cross-subject fMRI decoding by ensuring semantic consistency at the stimulus level and capturing individual neural variations at the subject level, thereby achieving state-of-the-art performance in image-to-brain retrieval and reconstruction with minimal adaptation data.
This paper proposes an automated method for generating task breakpoints in Virtual Reality recordings using an Origin-Centric Graph to analyze spatio-temporal scene changes, enabling adaptive playback and demonstrating high accuracy against user-perceived ground truth.
This paper proposes Mobile GlottisNet, a lightweight and efficient deep learning framework utilizing spatial-decoupled feature learning and adaptive mechanisms to achieve real-time, high-speed glottis detection for nasotracheal intubation on resource-constrained edge devices.
This paper proposes Proof-of-Encryption-Work (PoEW), a novel consensus mechanism that repurposes the energy-intensive process of exhaustive key search to simultaneously secure decentralized networks and achieve data compression by deriving a short key from a lengthy plaintext.
This paper extends opinion dynamics to multiplex networks by modeling them as synchronous coordination games with merged and switching coupling mechanisms, using spectral analysis to demonstrate how cross-layer interactions can uniquely induce, accelerate, or disrupt global consensus compared to single-layer systems.
PanoDP is a communication-free learning framework that integrates panoramic depth perception with differentiable physics-based training signals to enable robust, collision-free autonomous navigation in complex, partially observable environments with both static and dynamic obstacles.
This paper presents the first Registered Attribute-Based Encryption (RABE) schemes that support both certified deletion and certified everlasting security in both privately and publicly verifiable settings, thereby enabling decentralized, fine-grained access control with irreversible data deletion and information-theoretic security against future adversaries.
TempoFit is a training-free, plug-and-play method that enhances frozen Vision-Language-Action policies for long-horizon manipulation by retrieving and injecting layer-wise temporal key-value memory from previous timesteps, thereby improving success rates in non-Markovian environments without increasing inference latency or requiring model retraining.
The paper proposes AtomicVLA, a unified planning-and-execution framework that utilizes a Skill-Guided Mixture-of-Experts architecture to dynamically compose atomic skill abstractions, thereby significantly improving scalability and performance in long-horizon robotic manipulation and continual learning tasks compared to existing monolithic VLA models.
This paper proposes a multi-agent informative path planning framework for off-world exploration that utilizes Gaussian belief mapping and dual-domain coverage to effectively discover sparse, visually ambiguous evidence while balancing information gain with operational safety in hazardous, communication-constrained environments.
GLASS is a novel unsupervised framework that establishes dense 3D shape correspondence across challenging non-isometric and inter-class scenarios by integrating geometric spectral analysis with semantic priors from vision-language foundation models, achieving state-of-the-art performance through view-consistent feature extraction, language-injected vertex descriptors, and a graph-assisted contrastive loss.
This paper proposes a Self-Critical Inference (SCI) framework that enhances the robustness of Large Vision-Language Models against language bias and sensitivity through multi-round counterfactual reasoning with textual and visual perturbations, alongside a new Dynamic Robustness Benchmark (DRBench) for model-specific evaluation.
This paper introduces Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video streams without human intervention, which provides 4 million high-quality 3D semantic annotations and spatial QA pairs to significantly enhance the training and performance of Vision-Language Models on spatial reasoning tasks.