Ranjay Krishna

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

MMMG: A Comprehensive and Reliable Benchmark for Multitask Multimodal Generation

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

Spatial Mental Modeling from Limited Views

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

PointArena: Probing Multimodal Grounding Through Language-Guided Pointing

Spurious Rewards: Rethinking Training Signals in RLVR

MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine

The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains

Convergent Functions, Divergent Forms

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Visual Representations inside the Language Model

Language Model Preference Evaluation with Multiple Weak Evaluators

Diffusion Models are Few-shot Learners for Dense Vision Tasks

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations

Coarse Correspondences Boost 3D Spacetime Understanding in Multimodal Language Model