Pokerme/view2space_4b
Image-Text-to-Text • 570k • Updated • 58 • 9
ControlNet
ControlNet
AI & ML interests
Visual Reasoning, Neuro-Symbolic, LLM/VLM
Recent Activity
authored a paper about 14 hours ago
JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments authored a paper about 14 hours ago
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation authored a paper about 14 hours ago
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its MechanismOrganizations
None yet
liked a
model 3 months ago
liked a
dataset 3 months ago