13 accepted papers
In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity—akin to chameleons adapting their coloration to environmental cues—that can be *exposed* through token-conditional generation and *stabilized* via reinforcement learning. Specifically, by conditioning g…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), yet its underlying mechanisms remain insufficiently understood. In this work, we undertake a pioneering exploration of RLVR through the no…
Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of gating. In this work, we conduct comprehensive experiments to sy…
Depthwise-separable convolution has emerged as a significant milestone in the lightweight development of Convolutional Neural Networks (CNNs) over the past decade. This technique consists of two key components: depthwise convolution, which captures spatial information, and pointwise convolution, whi…
With the growing significance of network security, the classification of encrypted traffic has emerged as an urgent challenge. Traditional byte-based traffic analysis methods are constrained by the rigid granularity of information and fail to fully exploit the diverse correlations between bytes. To…
Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAMLbased approaches encounter significant challenges when there is a substan…
In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs. We first introduce DARE to set most delta parameters (i.e., the disparity between fine-tuned and pre-trained parameters) to zeros without aff…
Replaying previous training data is the most effective approach for Class-Incremental Learning (CIL), with its performance bounded by data availability. Therefore, many recent studies consider the Data-Free Class-Incremental Learning (DFCIL) problem that requires no previous data. However, the exist…
Information propagation on social networks could be modeled as cascades, and many efforts have been made to predict the future popularity of cascades. However, most of the existing research treats a cascade as an individual sequence. Actually, the cascades might be correlated with each other due to…
Given a sequence of sets, where each set contains an arbitrary number of elements, temporal sets prediction aims to predict which elements will appear in the subsequent set. Existing methods for temporal sets prediction are developed on sophisticated components (e.g., recurrent neural networks, atte…
In many real-world scenarios (e.g., academic networks, social platforms), different types of entities are not only associated with texts but also connected by various relationships, which can be abstracted as Text-Attributed Heterogeneous Graphs (TAHGs). Current pretraining tasks for Language Models…
We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes' historical first-hop interactions by: (1) a neighbor co-occurrence encoding scheme that explores the correlations of the source node and destina…
Privacy protection raises great attention on both legal levels and user awareness. To protect user privacy, countries enact laws and regulations requiring software privacy policies to regulate their behavior. However, privacy policies are written in professional languages with many legal terms and s…