SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
Paper • 2306.14610 • Published • 2
Zixian Ma
zixianma
AI & ML interests
Human-AI interaction and collaboration
Recent Activity
authored a paper 2 days ago
SugarCrepe: Fixing Hackable Benchmarks for Vision-Language
Compositionality authored a paper 2 days ago
m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks authored a paper 2 days ago
Task Me AnythingOrganizations
authored 12
papers 2 days ago
m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
Paper • 2403.11085 • Published
Task Me Anything
Paper • 2406.11775 • Published • 9
TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action
Paper • 2412.05479 • Published
ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
Paper • 2412.07012 • Published • 1
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
Paper • 2506.04633 • Published • 21
Synthetic Visual Genome
Paper • 2506.07643 • Published
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Paper • 2508.17298 • Published • 4
Reinforced Visual Perception with Tools
Paper • 2509.01656 • Published • 32
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
Paper • 2512.13874 • Published • 17
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Paper • 2601.10611 • Published • 32
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Paper • 2603.24575 • Published • 16
upvoted 6
papers 4 days ago
MolmoAct: Action Reasoning Models that can Reason in Space
Paper • 2508.07917 • Published • 45
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Paper • 2602.11337 • Published • 8
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Paper • 2603.16861 • Published • 9
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Paper • 2601.10611 • Published • 32
Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
Paper • 2602.23543 • Published • 9
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Paper • 2603.24575 • Published • 16
liked a
Space 4 days ago
submitted a
paper to Daily Papers 4 days ago