↓Skip to main content

🏢 National University of Defense Technology

Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
·2435 words·12 mins· loading · loading
Natural Language Processing Large Language Models 🏢 National University of Defense Technology
LLMs struggle with genuine causal reasoning; new benchmark CausalProbe-2024 reveals limitations, and G2-Reasoner method improves causal reasoning by integrating general knowledge and goal-oriented pro…
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
·1414 words·7 mins· loading · loading
AI Theory Generalization 🏢 National University of Defense Technology
Sharper ASGD generalization bounds achieved by leveraging on-average model stability, even without Lipschitz and smoothness assumptions; validated with diverse machine learning models.
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
·3487 words·17 mins· loading · loading
Computer Vision 3D Vision 🏢 National University of Defense Technology
LoD-Loc: A novel aerial visual localization method uses lightweight LoD 3D maps & neural wireframe alignment for accurate and efficient 6-DoF pose estimation, surpassing state-of-the-art methods.
Goal-Conditioned On-Policy Reinforcement Learning
·2363 words·12 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 National University of Defense Technology
GCPO: a novel on-policy goal-conditioned reinforcement learning framework tackles limitations of existing HER-based methods by effectively addressing multi-goal Markovian and non-Markovian reward prob…
Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
·1993 words·10 mins· loading · loading
Machine Learning Knowledge Graph Embedding 🏢 National University of Defense Technology
RecPiece: Relational Clustering for Better Knowledge Graph Embedding Anchors
Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
·1873 words·9 mins· loading · loading
Machine Learning Unsupervised Learning 🏢 National University of Defense Technology
AIMC-CVR: A novel approach that alleviates anchor-shift in incomplete multi-view clustering via cross-view reconstruction, improving accuracy and scalability.