zero-shot-generalization

PhysLDM 提出了一种用于高保真可变形体物理模拟的时空隐空间扩散框架，采用整体式 VAE 实现约 78 倍 token 压缩与 ~2.48 mm 重建精度，并证明扩散模型比确定性回归更能建模混沌动力学，实现零样本泛化与逆问题求解。

MaSS 通过解耦结构表征与上下文特征并引入场景结构判别目标，使自监督单目深度估计可扩展到多样场景训练，并在零样本评估中展现出强大的跨域泛化能力。

The paper proposes the Graph Dynamics Model (GDM) for learning in graph-structured environments with evolving topologies and stochasticity, and introduces the Graph Distribution Distance (GDD) metric for evaluation.

RelightFormer introduces a feed-forward generative Transformer for direct single- and multi-view image relighting, using cross-attention for illumination injection and permutation-invariant encodings for unordered views, trained on a massive synthetic dataset to achieve state-of-the-art visual quality.

CoToGrasp is a generative framework that synthesizes diverse, stable grasps conditioned on specific contact topologies using a canonical workspace for zero-shot generalization, outperforming existing planners on the DexGraspNet dataset.

GenRouter is a unified routing framework for agentic image generation that adaptively directs prompts to optimal workflows, significantly reducing costs and latency while improving visual alignment through demand profiling and self-evolution.

Qwen-RobotNav is a scalable navigation model with a parameterized interface enabling dynamic task modes and observation parameters, achieving state-of-the-art performance through multi-task training and zero-shot generalization to real-world robotics.

Presents Qwen-RobotManip, a Vision-Language-Action foundation model for robotic manipulation that achieves generalization through unified alignment across representation, motion, and behavior dimensions, enabling large-scale training on diverse data sources. It outperforms prior state-of-the-art models across multiple out-of-distribution benchmarks and demonstrates emergent capabilities like zero-shot instruction following and cross-embodiment transfer.

EgoPhys introduces a framework to construct deformable physical digital twins from egocentric RGB video using generalizable priors and a compact codebook, enabling zero-shot generalization to unseen objects without per-spring optimization. The system is demonstrated on a real robot, showing that egocentric human play video can serve as internal world representation for deformable-object planning.

Introduces PCSP, a single RL policy conditioned on frozen LLM embeddings of persona descriptions, enabling scalable, real-time persona-traceable NPC control in life simulation games. Experiments show zero-shot persona identification and behavioral alignment, with faster inference than LLM baselines.