2372 papers
This paper demonstrates that a simple exact method can solve nearly all classical benchmark instances of the Traveling Salesman Problem with Time Windows in under ten seconds, revealing that these datasets are no longer representative for evaluating algorithmic performance or training machine learning models due to their exploitable structure.
This paper introduces the first formal framework for Audio-Visual World Models (AVWM), presenting the AVW-4k dataset and the AV-CDiT model to enable high-fidelity, synchronized simulation of binaural audio and visual dynamics that significantly enhances agent performance in continuous navigation tasks.
The paper introduces AFRO, a self-supervised framework that learns dynamics-aware 3D visual representations by modeling state-action-state transitions via a generative diffusion process, thereby significantly improving robotic manipulation performance across diverse simulated and real-world tasks without requiring explicit action or reconstruction supervision.
This paper introduces V-Attack, a novel adversarial attack method for Large Vision-Language Models that achieves precise local semantic manipulation by targeting disentangled value features within transformer attention blocks, thereby overcoming the controllability limitations of existing approaches that rely on entangled patch-token representations.
The paper proposes SPAN, a novel framework for monocular 3D object detection that enhances geometric consistency and performance by introducing Spatial Point Alignment and 3D-2D Projection Alignment within a Hierarchical Task Learning strategy to overcome the limitations of traditional decoupled prediction paradigms.
EgoMI is a framework that bridges the human-robot embodiment gap in imitation learning by capturing synchronized end-effector and active head trajectories from egocentric human demonstrations and utilizing a memory-augmented policy to enable robust whole-body manipulation on semi-humanoid robots.
This paper introduces FRIDA, a lightweight and data-efficient framework that leverages features from pre-trained Stable Diffusion models to achieve state-of-the-art cross-generator fake image detection and source attribution through a training-free k-Nearest Neighbour approach and a compact neural classifier.
This paper demonstrates that selecting an optimal subset of body landmarks combined with spline-based imputation enables isolated Brazilian Sign Language (LIBRAS) recognition that is both 5 times faster and as accurate as state-of-the-art methods, overcoming the speed-accuracy trade-off of previous OpenPose-based approaches.
This paper challenges the conventional assumption that reactive replanning requires updating existing plans by demonstrating that using fast almost-surely asymptotically optimal (ASAO) algorithms to solve a series of independent planning problems offers a more efficient and effective approach for navigating changing environments.
This paper addresses the Connected Unlabeled Multi-Agent Pathfinding (CUMAPF) problem by introducing PULL, a lightweight, complete algorithm that runs in time per step and outperforms both an Integer Linear Programming approach and naive methods in scalability and efficiency for swarm robotics applications.
This paper presents a real-time neural video compression framework that unifies intra and inter coding within a single adaptive model and employs a simultaneous two-frame compression design to effectively handle disocclusion, prevent error propagation, and achieve a 12.1% BD-rate reduction over DCVC-RT while maintaining real-time performance.
NaviGait is a hierarchical framework that combines trajectory optimization and deep reinforcement learning to synthesize robust, intuitive bipedal locomotion by selecting and minimally morphing gaits from an offline library, thereby simplifying reward design and accelerating training while maintaining high fidelity to reference motions.
This paper presents an asset-centric metric-semantic mapping approach that combines detailed object meshes with natural language priors to create accurate, LLM-compatible indoor environment representations, achieving a superior balance between object-level detail and global scene context compared to existing methods.
LARA-Gen introduces a framework for continuous, fine-grained emotion control in music generation by aligning latent affective representations with an external emotion predictor and utilizing a valence-arousal control module, thereby overcoming the limitations of text-based prompting and significantly improving both emotional adherence and music quality.
This paper proposes a real-time MPC-CLF-CBF motion planner based on Bézier curves that enables multi-robot fleets to maintain connectivity, navigate obstacle-rich environments without deadlocks, and recover from connection losses, as validated by simulations and experiments with eight Crazyflie quadrotors.
This study presents a scalable dual-pass deep learning pipeline that successfully extracts the first open-access, nationwide urban footprint dataset for metropolitan France from historical maps (1925–1950), achieving 73% accuracy by effectively mitigating artifacts like text and contour lines to enable quantitative analysis of pre-1970s urban sprawl.
This paper introduces LLaVAShield, a safety auditing framework for multimodal multi-turn dialogues in Vision-Language Models, supported by the MMDS dataset and MMRT red-teaming framework, which collectively address the limitations of existing moderation tools by effectively detecting concealed malicious intent, contextual risk accumulation, and cross-modal joint risks.
This paper proposes an unsupervised method to recover the latent encoding and decoding direction pairs in deep vision networks, enabling the identification of interpretable concepts and facilitating model understanding, debugging, and intervention without relying on feature reconstruction.
This paper introduces the Coral Spawn and Larvae Imaging Camera System (CSLICS), an automated, low-cost computer vision solution that significantly reduces labor-intensive manual counting while accurately monitoring coral spawn and larvae to enhance reef restoration efforts.
This paper analyzes eight real-world AI deployments across seven non-Western countries to identify six key contextual factors and three influencing dimensions, ultimately proposing 12 guidelines for designing culturally aligned, equitable, and safe AI systems through deep collaboration between developers and domain experts.