arXiv:2509.14722v1 Announce Type: new Abstract: Graph condensation (GC) aims to distill the original graph into a small-scale graph, mitigating redundancy and accelerating GNN training. However, conventional GC approaches heavily rely on rigid GNNs and task-specific supervision. Such a dependency severely…
arXiv:2506.10943v2 Announce Type: replace Abstract: Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt…
arXiv:2509.14718v1 Announce Type: new Abstract: While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing learning value as training progresses. Existing dynamic sampling techniques are…
arXiv:2504.20020v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially advanced machine learning research, including natural language processing, computer vision, data mining, etc., yet they still exhibit critical limitations in explainability, reliability, adaptability, and extensibility. In this paper, we…
arXiv:2509.14678v1 Announce Type: new Abstract: We formulate an attention mechanism for continuous and ordered sequences that explicitly functions as an alignment model, which serves as the core of many sequence-to-sequence tasks. Standard scaled dot-product attention relies on positional encodings and…
arXiv:2501.12046v2 Announce Type: replace Abstract: Training machine learning models on decentralized private data via federated learning (FL) poses two key challenges: communication efficiency and privacy protection. In this work, we address these challenges within the trusted aggregator model by introducing…
arXiv:2509.14642v1 Announce Type: new Abstract: Modeling dynamic temporal dependencies is a critical challenge in time series pre-training, which evolve due to distribution shifts and multi-scale patterns. This temporal variability severely impairs the generalization of pre-trained models to downstream tasks. Existing…
arXiv:2408.05160v3 Announce Type: replace Abstract: The rapid growth of graph-structured data necessitates partitioning and distributed storage across decentralized systems, driving the emergence of federated graph learning to collaboratively train Graph Neural Networks (GNNs) without compromising privacy. However, current methods exhibit…
arXiv:2509.14640v1 Announce Type: new Abstract: Existing positional encoding methods in transformers are fundamentally signal-agnostic, deriving positional information solely from sequence indices while ignoring the underlying signal characteristics. This limitation is particularly problematic for time series analysis, where signals exhibit complex,…
arXiv:2509.15219v1 Announce Type: cross Abstract: Trajectory prediction is a critical task in computer vision and autonomous systems, playing a key role in autonomous driving, robotics, surveillance, and virtual reality. Existing methods often rely on complete and noise-free observational data, overlooking…
