68 citations · 139 across the 12 of their papers we have counts for
13 papers
LEGO-Prover: Neural Theorem Proving with Growing Libraries
Haiming Wang, Huajian Xin, Chuanyang Zheng +11
Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods…
BYOM: Building Your Own Multi-Task Model For Free
Weisen Jiang, Baijiong Lin, Han Shi +3
Recently, various merging methods have been proposed to build a multi-task model from task-specific finetuned models without retraining. However, existing methods suffer from a lar…
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Longhui Yu, Weisen Jiang, Han Shi +7
Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open…
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
Xinchi Deng, Han Shi, Runhui Huang +7
Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, on…
Forward-Backward Reasoning in Large Language Models for Mathematical Verification
Weisen Jiang, Han Shi, Longhui Yu +4
Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performa…
DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks
Jingwei Zhang, Han Shi, Jincheng Yu +2
Generative models can be categorized into two types: explicit generative models that define explicit density forms and allow exact likelihood inference, such as score-based diffusi…
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning
Enze Xie, Lewei Yao, Han Shi +5
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge…
Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
Binbin Yang, Xinchi Deng, Han Shi +6
Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual class…
Revisiting Over-smoothing in BERT from the Perspective of Graph
Han Shi, Jiahui Gao, Hang Xu +5
Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. However, no existing work has delved deeper to further investigate th…
AutoBERT-Zero: Evolving BERT Backbone from Scratch
Jiahui Gao, Hang Xu, Han Shi +5
Transformer-based pre-trained language models like BERT and its variants have recently achieved promising performance in various natural language processing (NLP) tasks. However, t…
SparseBERT: Rethinking the Importance Analysis in Self-attention
Han Shi, Jiahui Gao, Xiaozhe Ren +4
Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attent…
Effective Decoding in Graph Auto-Encoder using Triadic Closure
Han Shi, Haozheng Fan, James T. Kwok
The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph con…
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
Han Shi, Renjie Pi, Hang Xu +3
Neural Architecture Search (NAS) has shown great potentials in finding better neural network designs. Sample-based NAS is the most reliable approach which aims at exploring the sea…