8 accepted papers
Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate whether fewer but more informative queries can yield simila…
In recent years, the field of heterogeneous graph learning has garnered significant interest. Various efforts have been made towards learning heterogeneous graph representations, such as designing meta-paths to mine implicit graph knowledge or directly applying Graph Neural Networks (GNNs) for graph…
Enhancing the numerical and logical reasoning capabilities of Large Language Models (LLMs) has become a prominent research focus. Existing approaches exhibit notable limitations: inference-phase techniques, such as Chain of Thought, depend on prompt engineering and pretrained knowledge; sentence-lev
In this work, we propose FoRA-UA, a novel method that, using only 1–5% of the standard LoRA’s parameters, achieves state-of-the-art performance across a wide range of tasks. Specifically, we explore scenarios with extremely limited parameter budgets and derive two key insights: (1) fix-sized sparse
Rewards serve as proxies for human preferences and play a crucial role in Reinforcement Learning from Human Feedback (RLHF). However, if these rewards are inherently imperfect, exhibiting various biases, they can adversely affect the alignment of large language models (LLMs). In this paper, we colle…
Recent progress has propelled the development of realistic talking-face videos for avatars. Yet, animating 3D cartoon avatars remains intricate due to the imprecise nature of facial-driven data. This often manifests as inconsistent mouth configurations and rigid facial expressions, curbing the anima…
Generative self-supervised learning, represented by graph autoencoders (GAEs), has begun to exhibit significant potential in addressing graph tasks. However, GAEs often rely on Graph Neural Networks (GNNs) for encoding and decoding, this can pose a computation challenge due to the inherent complexit…
In the existing spectral GNNs, polynomial-based methods occupy the mainstream in designing a filter through the Laplacian matrix. However, polynomial combinations factored by the Laplacian matrix naturally have limitations in message passing (e.g., over-smoothing). Furthermore, most existing spectra…