Checkpoints and datasets for "Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts" [ECCV'26]
SNUMPR
SNUMPR
AI & ML interests
CV, Multimodal
Recent Activity
updated a collection 3 days ago
DART updated a dataset 3 days ago
SNUMPR/dart-libero-viewpoints updated a model 3 days ago
SNUMPR/dart-pi05-viewpoint-largeOrganizations
None yet
HIMA
Respository for COLM 2025 paper "Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning"
ISR-DPO
FedMosaic
Benchmark proposed (and used) in FedMosaic (ICLR 2026)
VLM-RLAIF
Respository for ACL 2024 paper "Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI feedback"
ReALFRED
Respository for ECCV 2024 paper "ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments"
DART
Checkpoints and datasets for "Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts" [ECCV'26]
FedMosaic
Benchmark proposed (and used) in FedMosaic (ICLR 2026)
HIMA
Respository for COLM 2025 paper "Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning"
VLM-RLAIF
Respository for ACL 2024 paper "Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI feedback"
ISR-DPO
ReALFRED
Respository for ECCV 2024 paper "ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments"