Search Results for author:
Found 7 papers, 6 papers with code
Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
In this paper, we deeply explore the mechanisms employed by Transformer-based language models in factual recall tasks.
Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples.
Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection
Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint.
Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse
Recent studies have highlighted a phenomenon in large language models (LLMs) known as "the reversal curse," in which the order of knowledge entities in the training data biases the models' comprehension.
A Push-Relabel Based Additive Approximation for Optimal Transport
Interestingly, unlike the Sinkhorn algorithm, our method also readily provides a compact transport plan as well as a solution to an approximate version of the dual formulation of the OT problem, both of which have numerous applications in Machine Learning.
SRPCN: Structure Retrieval based Point Completion Network
Besides, the missing patterns are diverse in reality, but existing methods can only handle fixed ones, which means a poor generalization ability.
Attention-based Transformation from Latent Features to Point Clouds
The points generated by AXform do not have the strong 2-manifold constraint, which improves the generation of non-smooth surfaces.
