AI Research Roundup: Video-Based Navigation, Secure LLMs, and Graph-Based Intelligence

Latest research summaries in ML, Robotics, CV, NLP and AI

Contents

1. Biogeochemistry-Informed Neural Network (BINN) for Improving Accuracy of Model Prediction and Scientific Understanding of Soil Organic Carbon

2. Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment

3. Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning

4. ChamaleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters

5. Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

6. Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment

7. Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

8. Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment

9. Value-Based Deep RL Scales Predictably

10. Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

11. OpenRANet: Neuralized Spectrum Access by Joint Subcarrier and Power Allocation with Optimization-based Deep Learning

12. MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification

13. GraphGPT: Generative Pre-trained Graph Eulerian Transformer

14. SMART: Advancing Scalable Map Priors for Driving Topology Reasoning

15. SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning