Alan Yuille

World-In-World: World Models in a Closed-Loop World

Mixture of Contexts for Long Video Generation

Captain Cinema: Towards Short Movie Generation

Play to Generalize: Learning to Reason Through Game Play

KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation

WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark

InfantNet: A Large Scale Dataset for Infant Body Pose and Shape Estimation

Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

TGT: Text-Grounded Trajectories for Locally Controlled Video Generation

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory

EigenLoRAx: Efficient Low Rank Adaptation Using Recycled Principal Subspaces

When Knowledge Hurts: Enriching Domain Knowledge for Causal Scientific Reasoning

Do Neural Networks Learn Similar Subspaces? An Empirical Exploration of Joint Parametric Subspaces in Deep Neural Networks

Autoregressive Video Generation beyond Next Frames Prediction

A Dataset and Benchmark for 3D Part Recognition from 2D Images

Fake it till You Make it: Reward Modeling as Discriminative Prediction

Are Vision Language Models Ready for Clinical Diagnosis? A 3D CT Benchmark for Lesion-centric Visual Question Answering

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning

Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models

Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

GenEx: Generating an Explorable World

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering

Autoregressive Pretraining with Mamba in Vision

DSPart: A Large-scale Diffusion-generated Synthetic Dataset with Annotations from 3D Parts

CycleAug: Cycle-Consistent Visual Augmentation for Large Multimodal Models

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context

EigenLoRA: Recycle trained Adapters for Resource Efficient Adaptation and Inference

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Part321: Recognizing 3D Object Parts from a 2D Image Using 1-Shot Annotations

Scaling 3D Compositional Models for Robust Classification and Pose Estimation

Causal Image Modeling for Efficient Visual Understanding

Mamba-Reg: Vision Mamba Also Needs Registers

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation

CIDA3D: Conformal Inference aided unsupervised Domain Adaptation for 3D-Aware Classification

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning