Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a model is only valuable if it learns semantically meani...
Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapidly. We introduce UNRESTSENT200K, a Bangla crisis...
Rapid extraction of structured information from social media is important for humanitarian response, yet existing disaster tweet resources mainly provide document-level category labels without span-le...
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with...
Upgrading embedding models typically requires expensive database re-indexing, as new query embeddings are incompatible with existing database embeddings. While Backward Compatible Training (BCT) mitig...
Facial Landmark Detection(FLD) is a crucial task in various applications and has achieved significant advancements in recent years. However, current FLD methods still struggle under challenging condit...
Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays the same. These local changes may cancel when r...
Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with wearable physiological signals, which are multichann...
Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remains a key challenge. Existing memory-augmented ap...
Image segmentation remains challenging due to occlusions, poor lighting, and irregular structures. Although transformer-based methods achieve high accuracy, they rely heavily on long-range spatial fea...
A Digital Surface Model (DSM) is a fundamental geospatial data product for representing the elevation of the Earth's surface. Recently, 3D Gaussian Splatting (3DGS) has shown considerable potential fo...
IMU-based human activity recognition (HAR) enables continuous, privacy-friendly monitoring of daily activities using wearable sensors. However, building reliable HAR models that generalize across dive...
With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, especially involving multi-step thinking or inter...
Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: pr...
Continuous-time (CT) machine learning has emerged as a principled framework for modeling temporal dynamics as a continuous process, particularly when observations are sampled at arbitrary time points...
Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritize...
Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution s...
Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, p...
arXiv:2609.14841v1 Announce Type: new Abstract: Scientific machine learning methods such as physics-informed neural networks (PINNs) increasingly rely on domain decomposition for better scalability w...
The paper evaluates deep learning models for electrocardiogram‑based emotion recognition, focusing on generalization across datasets rather than dataset‑specific performance. It introduces two open‑source tools—ARRC for standardized benchmarking and ARDT for inter‑dataset training—to merge three public AER datasets (CUADS, ASCERTAIN, DREAMER) into a more variable benchmark. Using these tools, the authors compare three prominent deep learning architectures and two CNN baselines with hyperparameter tuning and 10‑fold cross‑validation, revealing trade‑offs between accuracy and model complexity and providing a reproducible benchmark for future research.