TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
F. Meng, P. Tang, Z. Yao, X. Sun, M. Zhang
NeurIPS-25
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
S. Qiu, S. Guo, Z. Song, .et el, M. Zhang, H. X. Zhu
NeurIPS-25-Benchmark
OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
J. Wang, X. Wang, M. Zhang
NeurIPS-25
LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
Y. Li, F. Meng, M. Zhang, S. Zhu, S. Wang, M. Xu
NeurIPS-25
LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
Z. He, Y. Wang, J. Li, K. Liang, M. Zhang
NeurIPS-25-Benchmark
Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
Y. Hu, S. Kang, H. Yang, H. Xu, M. Zhang
NeurIPS-25
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
Y. Wang, F. Meng, X. Zhang, F. Jiang, P. Tang, M. Zhang
EMNLP-25
Reconsidering the Performance of GAE in Link Prediction
W. Ma, Y. Wang, X. Wang, M. Zhang
CIKM-25
Griffin: Towards a Graph-Centric Relational Database Foundation Model
Y. Wang, X. Wang, Q. Gan, M. Wang, Q. Yang, D. Wipf, M. Zhang
ICML-25
Geometric Representation Condition Improves Equivariant Molecule Generation
Z. Li, C. Zhou, X. Wang, X. Peng, M. Zhang
ICML-25 (Spotlight)
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
F. Meng, P. Tang, F. Jiang, M. Zhang
ICML-25
On the Completeness of Invariant Geometric Deep Learning Models
Z. Li, X. Wang, S. Kang, M. Zhang
ICLR-25
Number Cookbook: Number Understanding of Language Models and How to Improve It
H. Yang, Y. Hu, S. Kang, Z. Lin, M. Zhang
ICLR-25
GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
L. Kong, J. Feng, H. Liu, C. Huang, J. Huang, Y. Chen, M. Zhang
ICLR-25
VACT: A Video Automatic Causal Testing System and a Benchmark
H. Yang, Q. Zheng, Y. Gao, Y. Yang, Y. He, Z. Lin, M. Zhang
SCSL@ICLR-25
Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
X. Wang, P. Li, M. Zhang
JMLR-25