Related papers: LDGuid: A Framework for Robust Change Detection vi…
Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in well-lit scenarios,…
Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors (errors) that are challenging to prevent from reaching users during deployment. Recent research leverages large…
Recent advances in large language models (LLMs) have empowered AI agents capable of performing various sequential decision-making tasks. However, effectively guiding LLMs to perform well in unfamiliar domains like web navigation, where they…
Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet…
Lane detection plays a crucial role in autonomous driving by providing vital data to ensure safe navigation. Modern algorithms rely on anchor-based detectors, which are then followed by a label-assignment process to categorize training…
Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled…
Recent works have achieved great success in improving the performance of multiple computer vision tasks by capturing features with a high channel number utilizing deep neural networks. However, many channels of extracted features are not…
Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…
There are many real-world knowledge based networked systems with multi-type interacting entities that can be regarded as heterogeneous networks including human connections and biological evolutions. One of the main issues in such networks…
Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. However, these methods often overlook the importance of considering degradation representations, which can…
Deep learning models for medical image analysis easily suffer from distribution shifts caused by dataset artifacts bias, camera variations, differences in the imaging station, etc., leading to unreliable diagnoses in real-world clinical…
Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they…
Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level…
We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to…
Semantic Shift Detection (SSD) is the task of identifying, interpreting, and assessing the possible change over time in the meanings of a target word. Traditionally, SSD has been addressed by linguists and social scientists through manual…
Preventing machine failure is inherently superior to reactive remediation, particularly for critical assets like gas turbines, where early fault detection (FD) is a cornerstone of industrial sustainability. However, modern deep…
Nowadays, time series forecasting is predominantly approached through the end-to-end training of deep learning architectures using error-based objectives. While this is effective at minimizing average loss, it encourages the encoder to…
Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the…
We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model…
Methods addressing Learning with Noisy Labels (LNL) and multi-source Domain Generalization (DG) use training techniques to improve downstream task performance in the presence of label noise or domain shifts, respectively. Prior work often…