8 papers
Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Weilun Xu, Zipeng Sun
Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it…
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Jiahong Liu, Ram Samarth B B, Xinyu Fu +4
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients…
Revisiting Degree-Corrected Spectral Clustering: a Condition-Free Spectral Analysis and Extension
Wei Li, Xiaojian Li, Meng Qin +4
Spectral clustering is a representative graph clustering technique with strong interpretability and theoretical guarantees. Degree-corrected spectral clustering (DCSC) has emerged…
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
Xueyan Niu, Bo Bai, Wei Han +1
Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimiz…
PilotANN: Memory-Bounded GPU Acceleration for Vector Search
Yuntao Gui, Peiqi Yin, Xiao Yan +3
Approximate Nearest Neighbor Search (ANNS) has become fundamental to modern deep learning applications, having gained particular prominence through its integration into recent gene…
Towards Faster Graph Partitioning via Pre-training and Inductive Inference
Meng Qin, Chaorui Zhang, Yu Gao +5
Graph partitioning (GP) is a classic problem that divides the node set of a graph into densely-connected blocks. Following the IEEE HPEC Graph Challenge and recent advances in pre-…
Pre-train and Refine: Towards Higher Efficiency in K-Agnostic Community Detection without Quality Degradation
Meng Qin, Chaorui Zhang, Yu Gao +2
Community detection (CD) is a classic graph inference task that partitions nodes of a graph into densely connected groups. While many CD methods have been proposed with either impr…
RaftGP: Random Fast Graph Partitioning
Yu Gao, Meng Qin, Yibin Ding +6
Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides the node set of a graph into densely-connected blocks. Following prior work on the IEEE HPEC…