Search Results for author:
Found 11 papers, 8 papers with code
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
This paper answers this question in the context of tackling hard reasoning tasks (e. g., level 4-5 MATH problems) via learning from human annotations on easier tasks (e. g., level 1-3 MATH problems), which we term as easy-to-hard generalization.
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT).
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Our MetaMath-7B model achieves 66. 4% on GSM8K and 19. 4% on MATH, exceeding the state-of-the-art models of the same size by 11. 5% and 8. 7%.
Ranked #57 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Forward-Backward Reasoning in Large Language Models for Mathematical Verification
Instead of using forward or backward reasoning alone, we propose FOBAR to combine FOrward and BAckward Reasoning for verification.
ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis
In this paper, we propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels.
DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines.
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
We then use hyperspherical uniformity (which characterizes the degree of uniformity on the unit hypersphere) as a unified framework to quantify these two objectives.
Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving
Specifically, DucTeacher consists of two curriculums, i. e., (1) domain evolving curriculum seeks to learn from the data progressively to handle data distribution discrepancy by estimating the similarity between domains, and (2) distribution matching curriculum seeks to estimate the class distribution for each unlabeled domain to handle class distribution shifts.
Continual Learning by Modeling Intra-Class Variation
It has been observed that neural networks perform poorly when the data or tasks are presented sequentially.
Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification
However, distilling knowledge from two teacher models could result in the student model making some redundant predictions.
Memory Replay with Data Compression for Continual Learning
In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer.
