Checkpoints of VaLR (Jeon et al., ICML 26') and its variants
Byungwoo Jeon
rooty2020
AI & ML interests
Multi-modal representations, Robot Learning, Generative models
Recent Activity
upvoted a paper 1 day ago
Trust Region Q Adjoint Matching upvoted a paper 1 day ago
Benchmarking Visual State Tracking in Multimodal Video UnderstandingOrganizations
None yet
models 42
rooty2020/GR00T-N1.6-3B-VaLR
3B • Updated • 1
rooty2020/OpenEagle3-VL-stage2
2B • Updated • 2
rooty2020/3DRS-Qwen3-VL-4B
572k • Updated • 1
rooty2020/3DRS-Qwen3-VL-8B
774k • Updated • 2
rooty2020/VQGAN-Qwen2.5-FT
2B • Updated • 2
rooty2020/VG-LLM-Qwen3-VL-4B
5B • Updated • 4
rooty2020/VG-LLM-Qwen3-VL-8B
10B • Updated • 1
rooty2020/OpenEagle3-VL-v2
2B • Updated • 2
rooty2020/OpenEagle3-VL
Updated • 2
rooty2020/VaLR-Cosmos-Reason-Embodied-2B
2B • Updated • 4
datasets 0
None public yet