Singapore

Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic potential for complex diseases. However, identifying effective reprogramming strategies through classical wet-lab experiments is hindered by lengthy time commitments and high costs.

Although computational methods have been proposed to address this challenge, exact state-of-the-art techniques suffer from limited scalability owing to the notorious state space explosion problem. To overcome this limitation, we explore the use of deep reinforcement learning (DRL) for controlling holistic Boolean network models of complex biological systems, such as gene regulatory and signalling pathway networks. We formulate a novel control problem for Boolean network models operating under the asynchronous update mode, specifically tailored to the context of cellular reprogramming. To solve it, we devise GATTACA – a DRL-based computational framework explicitly designed for scalability, capable of handling large and complex network models where exact methods fall short.

To facilitate scalability of our framework, we consider our previously introduced concept of a pseudo-attractor and improve the procedure for effective identification of pseudo-attractor states. We incorporate graph neural networks with graph convolution operations into the artificial neural network approximator of the DRL agent’s action-value function. The new architecture allows us to leverage the available knowledge on the structure of a biological system and to indirectly, yet effectively, encode the system’s modelled dynamics into a latent representation.

Experiments on several large-scale, real-world biological networks from the literature demonstrate the scalability and effectiveness of our approach.

AAAI 2026

The GATTACA Framework: Graph Neural Network-Based Reinforcement Learning for Controlling Biological Networks

network control

boolean networks

cellular reprogramming

biological networks

deep reinforcement learning

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

AAAI 2024

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. 

technical 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.

Air pollution is a leading global health threat, yet many developing countries lack the dense monitoring infrastructure needed for accurate exposure assessment and informed policy. Optimal Sensor Placement (OSP) is a foundational challenge in expanding monitoring capacity. While mutual information (MI) offers a principled criterion for selecting informative sensor locations, its computational cost grows with both the number of placements and the density of the candidate grid. We present a scalable, continuous optimization framework that treats sensor coordinates as differentiable parameters and directly maximizes MI. Unlike standard approaches, our method is computationally efficient—its runtime is independent of both the number of placements and the size of the search grid—making MI-based acquisition feasible over large spatial domains. On a continental-scale PM$_{2.5}$ dataset, our method outperforms random placement and the widely-used Maximum Predictive Variance heuristic. In a focused regional study, it approaches the performance of greedy MI while being orders of magnitude faster. Our framework enables practical, information-theoretic sensor placement for real-world environmental monitoring.

Scalable Air-Quality Sensor Placement via Gradient-Based Mutual Information Maximization

Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, Test-Time Counterattack (TTC), improves robustness by generating perturbations that maximize the embedding deviation of adversarial inputs using PGD, pushing them away from their adversarial representations. However, due to the fundamental difference in optimization objectives between adversarial attacks and counterattacks, generating counterattacks solely based on gradients with respect to the adversarial input confines the search to a narrow space. As a result, the counterattacks can overfit limited adversarial patterns and lack the diversity to fully neutralize a broad range of perturbations. In this work, we argue that enhancing the diversity and coverage of counterattacks is crucial to improving adversarial robustness in test-time defense. Accordingly, we propose Directional Orthogonal Counterattack (DOC), which augments counterattack optimization by incorporating orthogonal gradient directions and momentum-based updates. This design expands the exploration of the counterattack space and increases the diversity of perturbations, which facilitates the discovery of more generalizable counterattacks and ultimately improves the ability to neutralize adversarial perturbations. Meanwhile, we present a directional sensitivity score based on averaged cosine similarity to boost DOC by improving example discrimination and adaptively modulating the counterattack strength. Extensive experiments on 16 datasets demonstrate that DOC improves adversarial robustness under various attacks while maintaining competitive clean accuracy.

Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference

The Leaky Integrate-and-Fire (LIF) neuron model remains a staple in spiking neural networks (SNNs), yet its oversimplified dynamics lead to unstable gradients and limit scalability. We introduce a polarization-aware spiking architecture (POLARA) that models depolarization, repolarization, and hyperpolarization through analytically defined membrane dynamics. POLARA unifies biologically grounded design with stable gradient propagation—formulating both forward and backward paths directly, and applying gradient shaping solely for numerical control, without requiring learnable gates or surrogate tuning. By bounding membrane potentials within realistic voltage ranges, POLARA avoids vanishing and exploding gradients, enabling scalable training in deeper architectures. Experiments show consistent gains over LIF and competitive results against optimized SNNs, positioning POLARA as a principled alternative to surrogate-driven or reset-based designs.

Stabilizing Spiking Neurons Through Biologically Inspired Polarization

Teaching large language models (LLMs) to be faithful in the provided context is crucial for building reliable information-seeking systems. Therefore, we propose a systematic framework, CANOE, to reduce faithfulness hallucinations of LLMs across different downstream tasks without human annotations. Specifically, we first synthesize short-form question-answering (QA) data with four diverse tasks to construct high-quality and easily verifiable training data without human annotation. Also, we propose Dual-GRPO, a rule-based reinforcement learning method that includes three tailored rule-based rewards derived from synthesized short-form QA data, while simultaneously optimizing both short-form and long-form response generation. Notably, Dual-GRPO eliminates the need to manually label preference data to train reward models and avoids over-optimizing short-form generation when relying only on the synthesized short-form QA data. Experimental results show that CANOE greatly improves the faithfulness of LLMs across 11 different tasks, even outperforming the most advanced LLMs, e.g., GPT-4o and OpenAI o1.

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning

Continual learning (CL) aims to enable models to incrementally learn from a sequence of tasks without forgetting previously acquired knowledge. While most prior work focuses on closed-world settings, where all test instances are assumed from the set of learned classes, real-world applications require models to handle both CL and out-of-distribution (OOD) samples. A key insight from recent studies on deep neural networks is the phenomenon of Neural Collapse (NC), which occurs in the terminal phase of training when the loss approaches zero. Under NC, class features collapse to their means, and classifier weights align with these means, enabling effective prototype-based strategies such as nearest class mean, for both classification and OOD detection. However, in CL, catastrophic forgetting (CF) prevents the model from naturally reaching this desirable regime. In this paper, we propose a novel method called Analytical Neural Collapse (ANC) that analytically creates the NC properties in the feature space of a frozen pre-trained model with no training, overcoming CF. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in continual OOD detection and learning, highlighting the effectiveness of our method in this challenging scenario.

Continual Out-of-Distribution Detection with Analytic Neural Collapse

The Weighted First-Order Model Counting Problem (WFOMC) asks to compute the weighted sum of models of a given first-order logic sentence over a given domain. Conditioning WFOMC on evidence—fixing the truth values of a set of ground literals—has been shown impossible in time polynomial in the domain size (unless $\mathsf{\sharp P \subseteq FP}$) even for fragments of logic that are otherwise tractable for WFOMC without evidence. In this work, we address the barrier by restricting the binary evidence to the case where the underlying Gaifman graph has bounded treewidth. We present a polynomial-time algorithm in the domain size for computing WFOMC for the two-variable fragments $\text{FO}^2$ and $\text{C}^2$ conditioned on such binary evidence. Furthermore, we show the applicability of our algorithm in combinatorial problems by solving the stable seating arrangement problem on bounded-treewidth graphs of bounded degree, which was an open problem. We also conducted experiments to show the scalability of our algorithm compared to the existing model counting solvers.

Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary Evidence

A perfect clone in an ordinal election (i.e., an election where the voters rank the candidates in a strict linear order) is a set of candidates that each voter ranks consecutively. We consider different relaxations of this notion: *independent* or *subelection clones* are sets of candidates that only some of the voters recognize as a perfect clone, whereas *approximate clones* are sets of candidates such that every voter ranks their members close to each other, but not necessarily consecutively. We establish the complexity of identifying such imperfect clones, and of partitioning the candidates into families of imperfect clones. We also study the parameterized complexity of these problems with respect to a set of natural parameters such as the number of voters, the size or the number of imperfect clones we are searching for, or their level of imperfection.

Identifying Imperfect Clones in Elections

Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, and significant inference costs. We propose DSFedMed, a dual-scale federated framework that enables mutual knowledge distillation between a centralized foundation model and lightweight client models for medical image segmentation. To support knowledge distillation, a set of high-quality medical images is generated to replace real public datasets, and a learnability-guided sample selection strategy is proposed to enhance efficiency and effectiveness in dual-scale distillation. This mutual distillation enables the foundation model to transfer general knowledge to lightweight clients, while also incorporating client-specific insights to refine the foundation model. Evaluations on five medical imaging segmentation datasets show that DSFedMed achieves an average 2\% improvement in Dice score while reducing communication costs and inference time by nearly 90\% compared to existing federated foundation model baselines. These results demonstrate significant efficiency gains and scalability for resource-limited federated deployments. The code will be made publicly available upon acceptance.

DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Models

Ordinal classification has been widely applied in many high-stakes applications, e.g., medical imaging and diagnosis, where reliable uncertainty quantification (UQ) is essential for decision making. Conformal prediction (CP) is a general UQ framework that provides statistically valid guarantees, which is especially useful in practice. However, prior ordinal CP methods mainly focus on heuristic algorithms or restrictively require the underlying model to predict a unimodal distribution over ordinal labels. Consequently, they lack either a comprehensive understanding of the it coverage optimality and predictive efficiency, or a model-agnostic and distribution-free nature favored by CP methods. To this end, we fill this gap by proposing the first ordinal-CP method that is both model-agnostic and provably optimal. Specifically, we formulate conformal ordinal classification as an expected minimum-length covering problem over the underlying distribution. To solve this problem, we develop a sliding-window algorithm that is optimal for each calibration example, with only a linear time complexity in K, the number of label candidates. The local optimality per instance further yields global optimality in expectation.
Moreover, we propose a length-regularized variant that shrinks prediction set size while preserving coverage. Extensive experiments on three benchmark datasets from diverse domains have been conducted to demonstrate the significantly improved predictive efficiency of the proposed methods over baselines (by 18% on average over three datasets).

Minimum-Length Conformal Prediction Sets for Ordinal Classification

Domain Generalization (DG) requires models to generalize across unseen data distributions. Kernel-based theory reveals a No-Free-Lunch problem: any model with a fixed representation is fundamentally sub-optimal for all possible shifts. While large ensembles mitigate this, they are computationally expensive and remain static once trained, inheriting the same theoretical limitation. We introduce MoE$^2$ (Mixture-of-Mixtures of Experts), a framework that uses a single frozen backbone to dynamically synthesize a bespoke adapter for each input, allowing it to continuously adapt its effective kernel. We provide a theoretical grounding for this process, proving our routing mechanism is a principled non-parametric estimator for the optimal Bayes mixture of experts. We derive a generalization bound that cleanly separates the router's estimation error from the reduction in a kernel-mismatch penalty achieved via synthesis. MoE$^2$ matches or exceeds state-of-the-art ensemble baselines on major DG benchmarks while using only a single, compact model. MoE$^2$ thus provides a theoretically-grounded and lightweight alternative to large-scale ensembles for robust domain generalization.

Downloads

Next from AAAI 2026

Scalable Air-Quality Sensor Placement via Gradient-Based Mutual Information Maximization

Similar lecture

Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning | VIDEO

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES