3836 papers
This paper proposes a scalable, structured multitask variational Gaussian Process framework for full-body human motion prediction that achieves competitive accuracy with significantly fewer parameters and provides well-calibrated, interpretable uncertainty estimates essential for safe real-time human-robot collaboration.
NuNext reframes nucleus detection in histopathology as a next-point prediction task using a multimodal large language model trained with spatial-aware soft supervision and reinforcement fine-tuning to achieve superior performance across nine benchmarks.
This paper empirically investigates whether large language models can synthesize executable Unity game code from Goal Playable Patterns under strict structural constraints, revealing that while intermediate representations improve performance, project-level grounding and hygiene failures remain primary bottlenecks in achieving high compilation success rates.
This paper presents AutoUE, a novel multi-agent system that leverages retrieval-augmented generation and game design patterns to automatically generate, code, and test complete 3D games within Unreal Engine, effectively addressing the complexities of tool usage and workflow orchestration.
This paper proposes the Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework, which utilizes a semi-autoregressive teacher model and a User Profile Network to balance generation quality with low-latency inference while enhancing user-item interactions, thereby outperforming state-of-the-art baselines in both ranking performance and efficiency.
This paper introduces ConservationBench to demonstrate that current Vision Language Models systematically fail to reason about physical transformations and maintain invariant representations of physical quantities, often performing near chance levels despite strong textual priors favoring invariance.
The paper proposes Failure Episodic Memory Alert (FEMA), a technique that stores and retrieves short-horizon failure experiences to prevent robots from relapsing into unstable states, thereby significantly improving sample efficiency and enabling successful long-horizon exploration in challenging contact-rich reinforcement learning tasks.
This paper introduces Semantic-Partitioned Contrastive Learning (S-PCL), a streamlined self-supervised pre-training framework for Chest X-rays that achieves superior accuracy and computational efficiency by enforcing agreement between randomly partitioned semantic subsets, thereby eliminating the need for heavy augmentations, auxiliary decoders, or momentum encoders.
This paper introduces aCAPTCHA, a novel security protocol that verifies whether an entity is a capable AI agent by leveraging the asymmetric processing speed between humans and machines to solve the Agentic Capability Verification Problem (ACVP) through time-constrained, multi-round natural language challenges.
This paper introduces TIQA, a human-aligned text quality assessment task and dataset for generated images, along with the ANTIQA method that significantly outperforms existing OCR and VLM-based metrics in predicting text rendering fidelity and improving downstream generation selection.
This paper proposes Inter-image Pixel Shuffling (IPS), a novel multi-focus image fusion method that synthesizes training data by shuffling pixels between clear and low-pass filtered images to enable deep learning models to learn fusion without real multi-focus datasets, while utilizing a hybrid cross-image network combining CNNs and state space models to achieve superior fusion quality.
This paper proposes a data-driven initialization strategy for autonomous racing trajectory optimization that utilizes a neural network trained on Formula 1 telemetry to predict expert-like raceline offsets, thereby significantly accelerating solver convergence and reducing runtime compared to traditional geometric baselines while maintaining optimal lap times.
This paper introduces a comprehensive multimodal dataset comprising audio and vibration signals from a single-speed chain conveyor system, designed to benchmark robust industrial fault detection and classification under diverse operating conditions and noise levels through standardized evaluation protocols and baseline models.
This paper introduces EyExIn, a data-efficient framework that enhances retinal Vision Language Models by employing a dual-stream encoding strategy and a deep expert injection mechanism to bridge perception and reasoning gaps, thereby achieving state-of-the-art precision in ophthalmic diagnosis while preventing hallucinations.
This paper argues that human-AI alignment in early developmental communities should be treated as a community-governed process involving layered collaboration between families and professionals, rather than an individual optimization problem, by establishing expert-grounded structures, professional guardrails, and family-level adaptations for multimodal LLM outputs.
The paper introduces AutoSelect, a training-free token pruning method for vision-language models that reformulates token selection as capacity-constrained communication using a noise-gating mechanism to identify and retain only the most informative visual tokens, thereby significantly accelerating inference while preserving nearly all model accuracy.
DexKnot is a generalizable visuomotor framework that combines keypoint affordances with diffusion policies to enable robots to reliably knot plastic bags across diverse, unseen instances by learning shape-agnostic representations from real-world manual deformations.
This paper proposes and experimentally validates a model-based method that links actuator expansion to surface temperatures to compensate for thermal drift in high-precision hexapod robots, achieving a reduction in thermally induced errors of over 80%.
The paper proposes PDD, a novel framework that unifies global contextual and local structural priors from dual frozen encoders into a shared manifold to distill diverse knowledge into complementary student networks, achieving state-of-the-art performance in medical image anomaly detection across multiple datasets.
This tutorial provides a control-oriented introduction to aided inertial navigation systems by utilizing a Lie-group formulation based on the extended Special Euclidean group SE(2,3) to establish a clear, geometric framework for fusing inertial and aiding measurements while explicitly leveraging invariance and symmetry principles.