Singapore

AAAI 2026

Online Independent Low-Rank Matrix Analysis as a Lightweight and Trainable Model for Real-Time Multichannel Music Source Separation

independent low-rank matrix analysis

independent vector analysis

online blind source separation

nonnegative matrix factorization

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

workshop paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Deep learning for time-series anomaly detection (TSAD) 
has gained significant attention over the past decade. 
Despite the reported improvements in several papers, 
the practical application of these models remains limited. 
Recent studies have cast doubt on these models, 
attributing their results to flawed evaluation techniques. 
However, the impact of initialization has largely been 
overlooked. This paper provides a critical analysis of the 
initialization effects on TSAD model performance. 
Our extensive experiments reveal that TSAD models are 
highly sensitive to hyperparameters such as window size, 
seed number, and normalization. This sensitivity often leads 
to significant variability in performance, which can be 
exploited to artificially inflate the reported efficacy of these 
models. We demonstrate that even minor changes in 
initialization parameters can result in performance variations 
that overshadow the claimed improvements from novel 
model architectures. Our findings highlight the need for 
rigorous evaluation protocols and transparent reporting 
of preprocessing steps to ensure the reliability and fairness 
of anomaly detection methods. This paper calls for a more 
cautious interpretation of TSAD advancements and 
encourages the development of more robust and 
transparent evaluation practices to advance the field 
and its practical applications.

Unveiling the Flaws:

The progress of Anomaly Detection (AD) in safety-critical 
domains, such as transportation, is severely constrained 
by the lack of large-scale, real-world benchmarks. 
To address this, we introduce EngineAD, a novel, 
multivariate dataset comprising high-resolution sensor 
telemetry collected from a fleet of 25 commercial vehicles 
over a six-month period. Unlike synthetic datasets, 
EngineAD features authentic operational data labeled 
with expert annotations, distinguishing normal states from 
subtle indicators of incipient engine faults. We preprocess 
the data into 300-timestep segments of 8 principal 
components and establish an initial benchmark using 
nine diverse one-class anomaly detection models. 
Our experiments reveal significant performance variability 
across the vehicle fleet, underscoring the challenge of 
cross-vehicle generalization. Furthermore, our findings 
corroborate recent literature, showing that simple 
classical methods (e.g., K-Means and One-Class SVM) 
are often highly competitive with, or superior to, deep 
learning approaches in this segment-based evaluation. 
By publicly releasing EngineAD, we aim to provide a 
realistic, challenging resource for developing robust 
and field-deployable anomaly detection and anomaly 
prediction solutions for the automotive industry.

EngineAD: A Real-World Vehicle Engine Anomaly Detection Dataset

Global climate change has increased the frequency of 
rainfall-induced disasters, such as landslides, even in regions 
previously considered safe, highlighting the need for accurate 
and region-generalizable prediction systems.
Landslide datasets are inherently imbalanced and regionally 
heterogeneous, as events are rare and local factors such as 
rainfall patterns, soil properties, and vegetation strongly 
influence occurrence.
Existing approaches either rely on physically grounded 
anomaly detection models, which ensure reasonable 
predictions in data-scarce regions but may not capture 
complex spatiotemporal patterns, or on deep learning 
models, which excel at representing complex patterns but 
often misinterpret rare yet safe conditions.
To leverage the complementary strengths of these 
approaches, we propose a hybrid framework that distills 
knowledge from physical anomaly detection models and 
incorporates region-conditioned supervised contrastive 
learning to learn latent representations that generalize across 
regions.The framework employs a three-layer tank model to 
simulate the Soil Water Index and quantify rainfall deviations, 
and jointly trains a prediction model with both physical outputs 
and actual disaster labels.
By integrating physically interpretable cues with deep 
representations, the system effectively addresses the scarcity 
and regional heterogeneity of landslide data.
We evaluated the framework on rainfall and terrain data from 
22 regions across Japan using a Leave-K-Region-Out scheme.
The proposed method achieved a 50\% higher PR-AUC in unseen 
regions compared to state-of-the-art baselines, demonstrating its 
potential for region-agnostic and physically grounded 
landslide prediction.

Leveraging Physics Anomaly 
Knowledge and Contrastive 
Learning for Region-Agnostic 
Landslide Prediction

Surveillance video captioning aims to generate natural language 
descriptions for security video and plays a crucial role in 
applications such as anomaly detection and behavior analysis. 
While vision-language models (VLMs) perform well on general 
video captioning, they often struggle in surveillance scenarios 
due to domain discrepancies in visual style and content 
emphasis. Moreover, reliable evaluation of caption quality in 
this domain also remains challenging. We propose a 
comprehensive framework that addresses both domain 
adaptation and evaluation. For domain adaptation, we enhance 
VLMs via reinforcement fine-tuning, exploring multiple reward 
designs to optimize relevance and accuracy while helping to
improve out-of-domain generalization. For evaluation, we 
develop an LLM-as-a-Judge process that assesses generated 
descriptions from two complementary perspectives: a local 
semantic score capturing fine-grained action fidelity and a global 
quality score evaluating linguistic fluency and temporal 
coherence. Experimental results show that our domain adaptation 
approach outperforms both zero-shot and supervised fine-tuning
baselines. Ablation studies further validate the effectiveness of 
our reward design, training strategy, and out-of-domain 
generalization. In addition, empirical analyses show that the 
proposed LLM-as-a-Judge framework aligns closely with human 
evaluations and exhibits stable and robust performance across 
different conditions.

Domain-Adaptive Video 
Captioning for Surveillance 
Videos

Learning additional reward signals---beyond the intrinsic rewards 
from the environment---can guide the agent more quickly toward 
optimal policies during training.
Recent work suggested training autoregressive models to 
maximize the likelihood of states observed in expert trajectories.
States that are likely then render a positive reward.
Such methods closely align with anomaly detection (AD), where 
the task is to find observations that deviate significantly from 
typical behavior.
We frame reward generation as an AD problem, generalizing 
existing techniques and proposing a novel methodology for 
learning reward signals. 
Specifically, we train state-of-the-art AD models capable of 
recognizing normal behavior from expert observations while 
actively learning to detect anomalous behavior from the agent's
sub-optimal observations, thus improving the reward learning 
process. We show that recent autoregressive reward-learning 
methods are, in fact, implementations of basic AD methods. 
Empirically, we show the effectiveness of the proposed reward
function across various tasks.


Anomaly-driven 
Reinforcement Learning

Anomaly detection (AD) for safety-critical IoT time series should be 
judged at the event level—by reliability and earliness under 
realistic perturbations. Yet many studies still emphasize point-level 
results on base form of curated public datasets, which limits their
value for model selection in practice. We introduce a unified 
evaluation protocol that adds event-level augmentation simulating 
real-world problems by (i) adds a calibrated sensor dropout stress, 
linear/log drift, additive noise, and window shifts, and (ii) 
performs sensor-level probing via mask-as-missing zeroing with 
per-channel influence estimation to support root-cause analysis.

We evaluate 14 representative models on five public anomaly 
datasets (SWaT, WADI, SMD, SKAB, TEP) and two industrial 
datasets (steam turbine, nuclear turbogenerator) under unified 
splits and event aggregation. There is no universal winner: 
graph-structured models transfer best under dropout and long 
events, for example on SWaT with additive noise a graph 
autoencoder falls from 0.804 to 0.677 (-16\%) while a 
graph-attention variant goes from 0.759 to 0.680 (-10\%) and 
a hybrid graph attention stays nearly flat at 0.762 to 0.756 
(-0.8\%); density or flow models work well on clean, stationary 
plants yet can be fragile to monotone drift, as log drift collapses 
a flow-based detector on SKAB and nuclear power plant (NPP) 
dataset while on SWaT the drop is mild at 0.795 to 0.783 
(-1.5\%); spectral CNNs lead when periodicity is strong; 
reconstruction autoencoders become competitive after basic 
sensor vetting; predictive or hybrid dynamics help when faults 
break temporal dependencies but remain window-sensitive. 
The same protocol also informs architecture choices, for example 
on SWaT under log perturbations replacing normalizing flows with 
a Gaussian density estimator reduces F1 to about 0.57 at high 
stress versus about 0.75 originally, and fixing the learned DAG 
yields a small clean-set gain of about 0.5 to 1.0 points but 
increases drift sensitivity by roughly eight times.


Benchmarking IoT 
Time-Series AD with Event-
Level Augmentations

Reliable anomaly detection (AD) in photovoltaic (PV) modules is 
critical for maintaining solar energy efficiency. However, the 
development of robust computer vision models for PV inspection is 
limited by the scarcity of large-scale, diverse, and balanced datasets.
In this study, we introduce a spatially conditioned denoising diffusion 
probabilistic model, PV-DDPM, designed to generate anomalous 
electroluminescence (EL) images across four PV cell types: 
multi-crystalline silicon (multi-c-Si), mono-crystalline silicon 
(mono-c-Si), half-cut multi-c-Si, and interdigitated back contact 
(IBC) with dogbone interconnect. 
PV-DDPM enables the controlled synthesis of both multi-defect and 
single-defect scenarios by conditioning on binary masks that 
represent structural features and defect positions.
To the best of our knowledge, this is the first framework that jointly 
models multiple PV cell types while allowing simultaneous 
generation of diverse anomaly types.
We also introduce E-SCDD dataset, an enhanced version of the 
SCDD dataset, comprising 1,000 pixel-wise annotated EL images 
spanning 30 semantic classes, and 1,768 unlabeled synthetic 
samples. Quantitative evaluation shows our generated images 
achieve a Fréchet Inception Distance (FID) of 4.10 and Kernel 
Inception Distance (KID) of 0.0023 ± 0.0007 across all categories. 
Furthermore, compared to training on the original SCDD dataset, 
training the vision–language anomaly detection model AA-CLIP 
on E-SCDD improves pixel-level AUC and average precision by 
1.70 and 8.34 points, respectively. Code and data are publicly 
released to ensure reproducibility.

Bridging the Data Gap: Spatially Conditioned Diffusion Model for Anomaly Generation in Photovoltaic Electroluminescence Images

This article introduces Attuned Design Practice (ADP), a design vocabulary and conceptual framework for producing embodied knowledge at the intersection of artistic and scientific inquiry, to inform the development of computational models that generate body-based interpretations and articulations. The convergence of Robotics, AI, HRI, and HCI in Industry 5.0 demand bold experimentation in artistic-scientific inquiry to interpret embodied knowledge beyond quantifiable data. In ADP, we propose the concept of ‘attunement’ to examine how alternative design vocabularies for embodied knowledge can be produced in reciprocity with the development of computational models that direct and facilitate expression and attunement over optimization or efficiency. Attunement is seen as a tuning fork to incrementally investigate the phenomena, relationships and patterns that inherently exist in tensions in-between tangible-intangible, or palpable-impalpable forms of materiality in human-computer connections, partnerships, and shared experiences. We propose Open Rehearsals, where-in alternative experiential understandings unfold in three areas of expertise: (1) preparing of tools and instruments, (2) performative practice, and (3) composition and choreography and notation methods. Our aim is to reinvent design innovation by cultivating integrative, reflective, and adaptive modes of collaborative design-making, from embodied discovery to embodied transformation.

Attuned Design Practice: towards Open Rehearsals for Embodied Knowledge and Computational Design.

Despite remarkable advances in machine learning, real-time, online inference of agents’ intentions remains one of the enduring grand challenges in AI. Plan, activity, intent, and goal recognition involve making inferences about actors from observations of their behavior, whether they are software agents, robots, or humans. This tutorial targets AI students and researchers interested in exploring these recognition tasks to enhance their ongoing research or identify new research directions.
Attendees will leave with a clear understanding of core concepts, tasks, and relationships among plan, activity, intent, and goal recognition, as well as exposure to the state-of-the-art computational representations, algorithms, and empirical methodologies. The tutorial is innovative in its unification of fragmented research across multiple AI subfields and its use of live demonstrations to connect theory with practice. Building on the successful 2019 AAAI tutorial on the same topic (Keren, Mirsky, and Geib 2019), this session offers an updated and expanded perspective. It incorporates new material from the presenters’ co-authored book (Mirsky, Keren, and Geib 2021), along with the latest developments and advances in the field. Prerequisite knowledge: Familiarity with general AI concepts, probabilistic reasoning, and planning is recommended. Basic knowledge of Bayesian inference and logic-based reasoning will be helpful but not required.

Plan, Activity, and Intent Recognition (PAIR)

As notoriously opaque deep neural networks (DNNs) become commonplace in powerful Artificial Intelligence (AI) systems, Interpretable Deep Learning (IDL) has emerged as a promising direction for designing interpretable-by-construction neural architectures. At their core, IDL models learn a latent space where some of their representations are aligned with high-level units of information, or concepts, that domain experts are familiar with (e.g., “stripped texture”,  “round object”, etc.). By introducing inductive biases that encourage predictions to be made based on these interpretable representations, IDL models enable the construction of expressive yet highly transparent architectures that can be vetted, analysed, and intervened on.

This tutorial aims to capitalise on the surge of interest in IDL by exposing AI researchers and engineers to the core foundations necessary to understand the general principles behind existing IDL models. By doing so, we aim to equip attendees with the knowledge necessary to comprehend the current state of this extensive body of literature, enabling them to build upon it for their research. Specifically, this tutorial will provide an overview of (1) core interpretability principles, (2) seminal works in the field, and (3) recent directions in IDL. Our tutorial will include hands-on demonstrations throughout our session and will conclude with a discussion of the key open questions in the field.

Our material will assume a basic knowledge of ML (e.g., foundations of supervised learning, experimental design, basic probabilistic modelling, etc.), with particular emphasis on a solid Deep Learning foundation (e.g., tensor calculus, neural networks, backpropagation, etc.). Concepts that may require mathematical tools/expertise beyond those one would expect to be shared among the AAAI community will be (re)introduced in our tutorial.

For further details and material, please refer to our tutorial’s site found at https://interpretabledeeplearning.github.io/.

Downloads

Next from AAAI 2026

Unveiling the Flaws:

Similar lecture

A Joint Matrix Factorization Analysis of Multilingual Representations