20 accepted papers
Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but often lag in deep reasoning. This divide arises from fundam…
Evaluating the faithfulness of attribution methods remains an open challenge. Standard metrics such as Insertion and Deletion Scores rely on heuristic input perturbations (e.g., zeroing pixels), which often push samples out of the data distribution (OOD). This can distort model behavior and lead to…
In-context learning (ICL) is a practical way to adapt large models, yet under strict context limits it remains unclear how to spend scarce tokens without being misled by noisy, redundant, or conflicting demonstrations. We address this gap by targeting token-budgeted context construction: how to sele…
Graph self-supervised learning aims to mine intrinsic signals from graph data itself to train models. It enables the acquisition of high-quality representations without manual annotations, making it suitable for various label-scarce scenarios and thus garnering substantial interest. Existing graph s
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks primarily evaluate short-horizon behaviors such as localized code generation, scaffolded completion, or repository repair, leaving it unclear whether agents can sustain coherent re…
When deployed on non-stationary data streams, foundation vision-language models require continual updates without access to past data. However, naive fine-tuning undermines their zero-shot recognition capabilities and prompt robustness. We seek a replay-free principle that preserves pre-trained cros…
Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action classification and description. However, when treating LLM as a recognizer, two questions arise: 1) How can LLMs underst
Deep matrix factorization has become a pivotal technique for Point of Interest (POI) recommendations, effectively capturing complex user-POI interactions to improve user experiences. However, these systems often face challenges such as data sparsity and the geographical constraints of POIs. To addre…
Piano-playing tasks, which effectively demonstrate bimanual coordination capabilities in humanoid robots, are increasingly becoming a research focus. However, prior research has predominantly focused on Cartesian space trajectory planning without adequately addressing real-world obstacle avoidance c
Black-box attacks play a pivotal role in adversarial attacks. However, existing approaches often focus predominantly on attacking from a data-centric perspective, neglecting crucial aspects of the models. To address this issue, we propose a novel approach in this paper, coined Decision Boundary Adap
Recent advancements in deep learning have significantly improved multivariate time series forecasting by leveraging powerful modeling techniques. However, the non-stationary nature of time series data, where distributions shift rapidly over time, continues to challenge the effectiveness of existing…
The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex associations between images and text. Despite these advanceme…
Out-of-distribution (OOD) detection is essential for enhancing the robustness and security of deep learning models in unknown and dynamic data environments. Gradient-based OOD detection methods, such as GAIA, analyse the explanation pattern representations of in-distribution (ID) and OOD samples by…
Denoising the corrupted images using an autoencoder is a promising approach to obtain a good performing encoder. This sub-field, known as MIM (Masked Image Modeling), has gained renewed attention with the advent of Masked Autoencoders (MAE). Although MAE and its subsequent work have revealed the sig…
Instruction fine-tuning (IFT) has emerged as a ubiquitous strategy for specializing large language models (LLMs), yet it implicitly assumes a single, coherent "ground-truth" preference behind all human-written instructions. In practice, annotators differ in the styles, emphases, and granularities th…
Functional connectivity (FC) graph analysis is an important method for diagnosing brain disorders using functional magnetic resonance imaging (fMRI). Existing FC graph diagnosis approaches preprocess the brain by dividing it into specific regions using atlases. However, relying on a single atlas exc…
Due to the real-world noise and human-added perturbations, attaining the trustworthiness of deep neural networks (DNNs) is a challenging task. Therefore, it becomes essential to offer explanations for the decisions made by these non-linear and complex parameterized models. Attribution methods are pr…
Vision Transformers (ViTs) have been widely used in various domains. Similar to Convolutional Neural Networks (CNNs), ViTs are prone to the impacts of adversarial samples, raising security concerns in real-world applications. As one of the most effective black-box attack methods, transferable attack…
Deep neural networks (DNNs) have achieved state-of-the-art performance across various applications. However, ensuring the reliability and trustworthiness of DNNs requires enhanced interpretability of model inputs and outputs. As an effective means of Explainable Artificial Intelligence (XAI) researc…
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome. Notably, the attribution methods use the ax- ioms o…