ResearchTrend.AI
Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent

Bo Chen
Zhenmei Shi
Zhao Song
Jiahao Zhang
ArXiv (abs)PDFHTML

Papers citing "Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent"

5 / 5 papers shown
Title
Minimalist Softmax Attention Provably Learns Constrained Boolean Functions
Minimalist Softmax Attention Provably Learns Constrained Boolean Functions
Jerry Yao-Chieh Hu
Xiwen Zhang
Maojiang Su
Zhao Song
Han Liu
MLT
245
1
0
26 May 2025
T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models
T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models
Xuyang Guo
Jiayan Huo
Zhenmei Shi
Zhao Song
Jiahao Zhang
Jiale Zhao
VGen
507
2
0
08 May 2025
On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective
On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective
Xiaoyu Li
Yingyu Liang
Zhenmei Shi
Zhao Song
Wei Wang
Jiahao Zhang
GNN
110
15
0
11 Jan 2025
HSR-Enhanced Sparse Attention Acceleration
HSR-Enhanced Sparse Attention Acceleration
Bo Chen
Yingyu Liang
Zhizhou Sha
Zhenmei Shi
Zhao Song
276
22
0
14 Oct 2024
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
Yeqi Gao
Yuzhou Gu
Zhao Song
79
0
0
09 May 2024