Search Results for author:
Found 5 papers, 2 papers with code
Traversal Verification for Speculative Tree Decoding
We theoretically prove that the probability distribution obtained through Traversal Verification is identical to that of the target model, guaranteeing lossless inference while achieving substantial acceleration gains.
DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding
Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction.
CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter
Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model.
Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i. e., accuracy on natural samples has reduced significantly.
Progressive Domain Expansion Network for Single Domain Generalization
A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains.
