Song-Chun Zhu

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Aegis: Automated Error Generation and Attribution for Multi-Agent Systems

Generative Actor Critic

G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior

VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video

MIRAGE: MULTI-HOP INTERLEAVED REASONING AND RETRIEVAL-GROUNDED EVIDENCE

Continuous-Time Discrete Markov Bridge

Learning AND–OR Templates for Compositional Representation in Art and Design

SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning

Mindmaster Roleplay: A Social Reasoning and Planning Benchmark

v-HUB: A Visual-Centric Humor Understanding Benchmark for Video LLMs

Social World Model-Augmented Mechanism Design Policy Learning

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting