Singapore

The computational cost of large language models (LLMs) is
a primary obstacle to sustainable deployment. Static
resource
allocation is inefficient, as not all inputs require the
same
depth of processing. We propose a framework for adaptive,
compute-efficient learning via conceptual criticality, which
dynamically tailors computation to the assessed difficulty
of an input. A lightweight criticality prediction module es-
timates conceptual complexity on a continuous scale, and
this score governs the LLM’s inference pathway, selectively
activating token pruning, layer skipping, and quantization.
Simple inputs are processed with minimal FLOPs and la-
tency, while complex inputs use the model’s full capacity
to preserve accuracy. We benchmark our framework and in-
troduce metrics to quantify sensitivity to input criticality
and per-sample computational savings. Results demonstrate
an improved accuracy-efficiency trade-off, paving the way
for more resource-aware systems.

AAAI 2026

Adaptive Compute Efficient Learning via Conceptual-Criticality (Student Abstract)

conceptual criticality

green ai

adaptive computation

efficiency

large language models

[![](https://assets.underline.io/uploads/markdown_image/1/image/359fc42963be9dbef8d1acac451d7c3e.png)](https://www.ada-europe.org/conference2021)

### Welcome Message from our Co-Chairs

Through this message, we want to give you our warmest welcome to the 25th Ada-Europe International Conference on Reliable Software Technologies (AEiC 2021). The special circumstances we all go through have made the conference a virtual event. Nonetheless, this will allow us to take advantage of the benefits of this format by using the Underline.io platform that allows remote participation of speakers and attendees and a virtual exhibition.
The platform will also provide a virtual space through Gather.Town to facilitate social interaction among participants, which, in addition to presenting state of the art research results, is one of the most important goals of a conference. This platform will hold various social events together with breaks and a poster session. 

The conference schedule includes a four-day program and exhibition from Monday to Thursday, with parallel tutorials on Monday, and keynotes, technical sessions and a Work-in-Progress session on the remaining three days. The technical sessions include the presentations of 13 journal-track papers, 5 industrial presentations and 6 invited talks on leading topics on reliable software technologies. The program will be completed with three outstanding keynotes that will delight the participants.

The main conference activities will be from 13:00 to 18:00 Central European Summer Time (CEST) to allow participants from America to Central Asia to attend to the conference sessions. Virtual social events are scheduled at the beginning and the end of each day. We encourage you to participate in these activities as well as visiting the exhibition. We look forward to meeting you virtually in June 2021!

**J. Javier Gutiérrez and Mario Aldea Rivas**
 // AEiC 2021 Program Co-Chairs

![](https://assets.underline.io/uploads/markdown_image/1/image/609207a715bd5da2ea56e9a32b0d17ae.png)
![](https://assets.underline.io/uploads/markdown_image/1/image/5bd0a9396b4c6903d0ca52825b81fbe6.png)




Please register with AEiC to be able to enter the conference on Underline.io. If you have already registered, please login to Underline.io to be able to see full conference content. In case you do not have an Underline account, please create one. Thank you 

Please login to your Underline account

AEiC 2021 - 25th Ada-Europe International Conference on Reliable Software Technologies

poster

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.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>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.

The dependency of stock prices on a multitude of factors
makes the task of prediction exceedingly challenging. Given
the volatile nature of stock data, it is imperative to
integrate multiple sources of information to accurately
encompass the various factors that influence market trends.
To capture these complex dynamics, several multimodal
methodologies have been proposed, integrating market data,
technical indicators, and textual information. However, it
is claimed that these coarse-grained information sources do
not offer a holistic view of the market. Furthermore, these
sources are stock-specific and do not elucidate the
interconnections between various stocks. To address this
deficiency, we propose a multimodal approach that
incorporates this relational aspect alongside fine-grained
information sources. The applicability of our framework is
underscored by empirical results, which demonstrate the
superiority of our approach.

An Approach Towards Developing Relationally Intelligent Multimodal Framework for Stock Movement Prediction (Student Abstract)

This work explores Liquid Time-Constant Networks (LTCs) and
Closed-form Continuous-time Networks (CfCs) for modeling
retinal ganglion cell activity in tiger salamanders across
three datasets. Compared to a convolutional baseline and an
LSTM, both architectures achieved lower MAE, faster
convergence, smaller model sizes, and favorable query
times, though with slightly lower Pearson correlation.
Their efficiency and adaptability make them well suited for
scenarios with limited data and frequent retraining, such
as edge deployments in vision prosthetics.

Modeling Retinal Ganglion Cells with Neural Differential Equations (Student Abstract)

Estimating causal effects under network interference is
challenging especially when edges are heterogeneous and
nodes share latent dependencies. We study this realistic
setting and propose MVDR, a targeted maximum likelihood
(TMLE) framework that learns multi-view representations of
covariates and exposure on heterogeneous networks while
achieving double robustness: consistency holds if either
the outcome model or the exposure density is correctly
specified. MVDR supports multiple network interventions
using only the observed network structure. On three
semi-synthetic datasets, MVDR reduces intervention-level
prediction error against baselines, and remains stable
under misspecification.

Doubly Robust Causal Estimation Under Multi-View Network Interference (Student Abstract)

Dataset distillation methods learn a representative summary
of the full dataset such that training on the distilled
data is
more efficient in terms of time and space. The current
state-of-the-art methods exploit the correspondence between
infinitely wide neural networks (NNs) and kernel ridge
regression to design distillation methods that result in
high-quality summaries of the data. In this work, we
leverage the correspondence between infinitely wide
networks and Gaussian Processes(GPs) for learning a
distilled dataset. We investigate the feasibility of using
the inducing points method for Gaussian Processes, as a
data distillation method. While most of the existing
dataset distillation methods are based on loss or gradient
matching, our method looks at the function space
approximation, facilitated by the NN-GP correspondence.
Additionally, using recent theoretical results on GP
regression and neural tangent kernels(NTKs), we also
provide an upper bound on the size of the distilled data.
We demonstrate the utility of inducing points as distilled
data on a set of datasets empirically.

How Good Are Inducing Points for Dataset Distillation? (Student Abstract)

Traditional intercultural communication training often lacks safe spaces for open practice, leading to self-censorship and limited skill development. The ICC Tutor, an AI-powered
conversational system, addresses this by offering a private, nonjudgmental environment for reflection and dialog. Using retrieval-augmented generation (RAG), the system grounds its prompts and feedback in course materials. We conducted a mixed-methods study (N = 25) with Beginner/Intermediate and expert learners. Preliminary findings suggest that the tutor helped reduce feelings of nervousness. While many beginners reported increased confidence in intercultural communication, expert learners’ confidence temporarily decreased,
suggesting the AI’s role in fostering deeper self-reflection rather than just boosting perceived competence. These findings underscore the potential of AI tutors in supporting communication education and highlight the need for experience-adaptive designs to support nuanced learning trajectories.

Adaptive AI for Personalized Intercultural Communication Education: A Conversational Agent Powered by Retrieval-Augmented Generation (Student Abstract)

In this paper, we study the adversarial robustness of deep
neural networks (DNN) for classification against optimal
classifiers. We look at the smallest magnitude of possible
additive perturbations that can change a classifier's
output. We provide a matrix-theoretic explanation of the
adversarial fragility of DNNs for classification. In
particular, our theoretical results show that the
adversarial robustness of a neural network can degrade as
the input dimension d increases. Analytically, we show
that the adversarial robustness of neural networks can be
only 1/√d of the best possible adversarial
robustness of optimal classifiers. Our theories match
remarkably well with empirical results. The
matrix-theoretic explanation aligns with an earlier
information-theoretic feature-compression-based explanation
for the adversarial fragility of neural networks.

Feature Compression May Be the Root Cause of Adversarial Fragility in Neural Network Classifiers (Student Abstract)

Large Language Models (LLMs) are increasingly employed for literature reviews, academic drafting, and scholarly writing. While their fluency accelerates knowledge synthesis, they frequently produce fabricated or erroneous references, known as citation hallucinations (CHs). Recent studies report hallucination rates ranging from 18% in GPT-4 to over 70% in other frontier models, with domain-specific rates as high as 88% in legal contexts. Benchmarks such as CiteME further highlight the gap between LLMs (4.2–18.5% accuracy) and human annotators (69.7%), while retrieval-augmented systems like CiteAgent demonstrate partial progress. This study examines methods for automatically detecting hallucinated citations. We present a benchmark of machine-generated references labelled with three fine-grained categories (valid, partially valid, and hallucinated), and propose a hybrid detection pipeline combining bibliographic retrieval, fuzzy similarity, and LLM-based verification. Preliminary experiments indicate improvements over exact matching baselines. We argue that scalable, real-time citation verification is a crucial step toward developing trustworthy LLM-based scholarly assistants and generating reproducible scientific knowledge, and outline directions for multilingual and domain-specific extensions.

Detecting Citation Hallucinations in Large Language Model Outputs (Student Abstract)

Encrypted traffic classification has become increasingly
important in network security. To address the difficulty of
existing architectures in collaboratively modeling
spatio-temporal features, we propose BiST-Mamba, a novel
dual-branch spatio-temporal Mamba network that
synchronously extracts spatio-temporal features. To the
best of our knowledge, this is the first work to introduce
VMamba into encrypted traffic classification. Preliminary
experiments on a small-scale dataset show that our accuracy
and F1 scores reach 92.74% and 83.43%, respectively. The
method achieves promising classification performance,
demonstrating the potential of the model for effective
spatio-temporal modeling.

BiST-Mamba: A Dual-branch Spatio-Temporal Mamba Network for Encrypted Traffic Classification (Student Abstract)

Current video understanding models struggle with temporal
reasoning and efficient processing while balancing detail
preservation with computational efficiency. We propose a
hierarchical memory system that segments videos into action
and scene units, combined with question-aware agentic
keyframe selection. Our method achieves 70.3% overall
accuracy on VideoMME short video benchmarks.

HARK: Hierarchical Agentic Retrieval with Keyframing for Video Understanding (Student Abstract)

We identify a jailbreaking vulnerability in multiple open-source LLMs: by augmenting dangerous requests using certain ``distractors" to obfuscate their intent, we elicit specific, actionable responses on a wide variety of harmful topics. We find that such an attack noticeably alters the contents of these models' chains of thought, including changed frequencies of seemingly unrelated $n$-grams and heightened ethical scrutiny about harmful requests even when their response is ultimately jailbroken.

Downloads

Next from AAAI 2026

An Approach Towards Developing Relationally Intelligent Multimodal Framework for Stock Movement Prediction (Student Abstract)

Similar lecture

Machine learning and high criticality applications

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

An Approach Towards Developing Relationally Intelligent Multimodal Framework for Stock Movement Prediction (Student Abstract)

Similar lecture

Machine learning and high criticality applications

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads