Papers Zero-shot Generalization
“Zero-shot Generalization” 태그가 달린 논문 1,077편 · 필터 해제
Sensor-Language-Action Models
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize states or predict outcomes, leaving actions modeled…
Zero-shot GeneralizationMotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized training keeps them from benefit…
Zero-shot GeneralizationRobot ManipulationVisual GroundingSentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods often remain dependent on task-specific f…
Zero-shot GeneralizationContrastive LearningDex-X: Learning Visual-Tactile Dexterous Manipulation From Human Videos with Simulated Interaction
Human videos are an abundant source of dexterous manipulation behaviors, but they lack tactile information that is crucial for contact-rich interaction. This raises a fundamental question: can robots learn deployable vis…
Zero-shot GeneralizationRelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting
Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative models that ignore crucial multi-view cues necessary for understandi…
Zero-shot GeneralizationInverse RenderingImage RelightingLightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial pri…
Zero-shot GeneralizationReinforcement LearningInstruction FollowingSpatial ReasoningRetrieval-Augmented Classification of Environmental Mitigations in Hydropower Licensing Documents
Identifying and classifying environmental mitigation obligations in Federal Energy Regulatory Commission hydropower licensing documents is a labor-intensive task requiring deep domain expertise. We formulate this as a mu…
Multi-Label ClassificationZero-shot GeneralizationDiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion
Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstr…
Zero-shot Generalization3D Human Reconstruction3D ReconstructionCoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be grasped rather than how it should be grasped to support downstream functional tasks. However, conditioning …
Zero-shot GeneralizationSelf-supervised In-context Operator Learning for Stochastic Mean-Field Control
Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting agents under uncertainty, with a wide range of applications. Existing numerical and deep-learning met…
Zero-shot GeneralizationGenRouter: Unified Workflow Routing for Agentic Image Generation
The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests…
Zero-shot GeneralizationImage GenerationLearning Generalizable Reconstruction of High-Dimensional Neural Dynamics
Accurate reconstruction of long-duration neural recordings is challenging because local field potentials (LFPs) are high-resolution, multichannel, transient, and variable across subjects. We present PCA-DMD, a scalable o…
Zero-shot GeneralizationPXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation
Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundaries. We attribute this limitation to the prevalent combination of large-…
Monocular Depth EstimationZero-shot GeneralizationZero-Shot Skeleton-Based Action Anticipation
Action anticipation (AA) aims to recognize ongoing human or humanoids actions from partial observations, enabling robots to predict intentions before the actions are completed. Although skeleton-based AA offers efficienc…
Zero-shot GeneralizationAction AnticipationGeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions
Generalist robot policies exhibit strong capabilities, but their robustness in complex and unseen environments remains limited. Scaling robot learning and evaluation in diverse real-world environments remains costly and …
Zero-shot GeneralizationVideo PredictionSeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval
Adapting CLIP for zero-shot sketch-based image retrieval (ZS-SBIR) via prompt learning faces a fundamental tension: the model must bridge the sketch-photo domain gap through task-specific adaptation, yet the added flexib…
Sketch-Based Image RetrievalZero-shot GeneralizationInfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
Single-image feed-forward 3D Gaussian Splatting (3DGS) aims to directly generate a renderable 3D scene representation from one input image, avoiding the cost of multi-view capture and per-scene optimization. However, exi…
Zero-shot GeneralizationWorld Action Planner: Generalizable Decision-Making with Action-Conditioned World Models
Building generalizable agents for diverse applications remains a fundamental challenge. While imitation learning-based policies succeed in specific training environments, they often fail to generalize to novel scenes and…
Zero-shot GeneralizationPLATO: Pointer Learner for Agent and Task Openness
Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a …
Multi-agent Reinforcement LearningZero-shot GeneralizationGraph Neural NetworkSTEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching
Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, collapsing the multimodal distribution mo…
Zero-shot Generalization3D Reconstruction