Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Paper • 2606.06476 • Published • 15
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
ChaimZhu
submitted a
paper to Daily Papers 4 days ago
zoecitron
updated a
dataset 15 days ago
Axi404
updated a
dataset 20 days ago
wuzhi-hao
authored a
paper 22 days ago
hanqing94
updated a
collection about 1 month ago
2toINF
published a
model about 1 month ago
2toINF
updated a
model about 1 month ago
2toINF
updated a
collection about 1 month ago
Axi404
updated a
dataset about 2 months ago
gordonhu
updated a
model about 2 months ago
gordonhu
published a
model about 2 months ago
YangZhou24
updated a
dataset about 2 months ago
YunsongZhou
updated a
model 2 months ago
gordonhu
authored 3
papers 2 months ago
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
Paper • 2308.09936 • Published • 1
Matryoshka Query Transformer for Large Vision-Language Models
Paper • 2405.19315 • Published • 1
MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
Paper • 2410.08182 • Published