Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
• 18
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
Articles
VLLM?
➕ 5
1
#2 opened 3 days ago
by 
jtvino
YongganFu
updated 3
models about 2 hours ago
Yuchao97
updated 4
models about 12 hours ago
emelryan
updated a
model about 15 hours ago
taesiri
submitted a
paper to Daily Papers about 18 hours ago
NV-DLynch
updated a
collection about 22 hours ago
carmelog
updated a
dataset 1 day ago
shoeybi
authored a
paper 2 months ago
valtsblukis
authored a
paper 6 months ago
Post
1670
We’re excited to share that Llama Nemotron Super v1.5 -- our latest open reasoning model -- is leading the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, for models running on a single NVIDIA H100.
Super v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. Besides leading accuracy, it also delivers high throughput.
Key features:
- Leading accuracy on multi-step reasoning, math, coding, and function-calling
- Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples
- Fully transparent training data on HF (Nemotron-Post-Training-Dataset-v1)
Try Super v1.5 on build.nvidia.com or download from Hugging Face
Super v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. Besides leading accuracy, it also delivers high throughput.
Key features:
- Leading accuracy on multi-step reasoning, math, coding, and function-calling
- Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples
- Fully transparent training data on HF (Nemotron-Post-Training-Dataset-v1)
Try Super v1.5 on build.nvidia.com or download from Hugging Face
moojink
authored 5
papers 11 months ago
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Paper • 2310.08864 • Published • 2
BridgeData V2: A Dataset for Robot Learning at Scale
Paper • 2308.12952 • Published • 2
Vision-Based Manipulators Need to Also See from Their Hands
Paper • 2203.12677 • Published • 1
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis
Paper • 2301.08556 • Published
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Paper • 2502.19645 • Published • 1