✨OSM-based Domain Adaptation for Remote Sensing VLMs

📝 Summary:
A self-contained domain adaptation framework for vision-language models in remote sensing uses OpenStreetMap data and optical character recognition to generate captions without requiring external teac...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11804
• PDF: https://arxiv.org/pdf/2603.11804

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

📝 Summary:
A video diffusion model is repurposed as a latent world simulator to enhance multimodal large language models with implicit 3D structural priors and physical laws through spatiotemporal feature extrac...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19235
• PDF: https://arxiv.org/pdf/2603.19235
• Project Page: https://github.com/H-EmbodVis/VEGA-3D
• Github: https://github.com/H-EmbodVis/VEGA-3D

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

📝 Summary:
SAMA presents a factorized approach to video editing that separates semantic anchoring from motion modeling, enabling instruction-guided edits with preserved motion through pre-trained motion restorat...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19228
• PDF: https://arxiv.org/pdf/2603.19228
• Project Page: https://cynthiazxy123.github.io/SAMA/
• Github: https://github.com/Cynthiazxy123/SAMA

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

📝 Summary:
CubiD is a discrete generation model for high-dimensional representations that enables fine-grained masking and learns rich correlations across spatial positions while maintaining fixed generation ste...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19232
• PDF: https://arxiv.org/pdf/2603.19232
• Github: https://github.com/YuqingWang1029/CubiD

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Memento-Skills: Let Agents Design Agents

📝 Summary:
A generalist language model agent system autonomously designs and improves task-specific agents through memory-based reinforcement learning with stateful prompts and skill libraries. AI-generated summ...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.18743
• PDF: https://arxiv.org/pdf/2603.18743
• Project Page: https://memento.run/
• Github: https://github.com/Memento-Teams/Memento-Skills

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

📝 Summary:
F2LLM-v2 is a multilingual embedding model family trained on 60 million samples across 200+ languages, achieving superior performance through LLM-based training, matryoshka learning, pruning, and dist...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19223
• PDF: https://arxiv.org/pdf/2603.19223
• Project Page: https://huggingface.co/collections/codefuse-ai/f2llm

🔹 Models citing this paper:
• https://huggingface.co/codefuse-ai/F2LLM-v2-8B-Preview
• https://huggingface.co/codefuse-ai/F2LLM-v2-0.6B-Preview
• https://huggingface.co/codefuse-ai/F2LLM-v2-1.7B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/codefuse-ai/F2LLM-v2

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

📝 Summary:
Long-form audio-visual comprehension benchmark reveals significant challenges for current omnimodal large language models in handling extended multi-modal inputs. AI-generated summary Recent advanceme...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19217
• PDF: https://arxiv.org/pdf/2603.19217
• Project Page: https://kd-tao.github.io/LVOmniBench/
• Github: https://github.com/KD-TAO/LVOmniBench

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FASTER: Rethinking Real-Time Flow VLAs

📝 Summary:
Fast Action Sampling for ImmediaTE Reaction (FASTER) reduces real-time reaction latency in Vision-Language-Action models by adapting sampling schedules to prioritize immediate actions while maintainin...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19199
• PDF: https://arxiv.org/pdf/2603.19199
• Project Page: https://innovator-zero.github.io/FASTER
• Github: https://github.com/innovator-zero/FASTER

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

📝 Summary:
Nemotron-Cascade 2 is a 30B parameter Mixture-of-Experts model with 3B activated parameters that achieves exceptional reasoning and agentic capabilities, matching frontier open models despite its comp...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19220
• PDF: https://arxiv.org/pdf/2603.19220

🔹 Models citing this paper:
• https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning

📝 Summary:
Modulated Hazard-aware Policy Optimization introduces a Log-Fidelity Modulator and Decoupled Hazard Penalty to stabilize reinforcement learning by controlling importance ratios and regulating asymmetr...

🔹 Publication Date: Published on Mar 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16929
• PDF: https://arxiv.org/pdf/2603.16929

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research