Singapore

We study the problem of solving one-sided, zero-sum, partially observable stochastic games (POSGs). These games model sequential interactions between two adversaries, where one player has partial observability of the game state. They are applicable to many important domains, such as robotics and cybersecurity. Solving such games is computationally challenging since the solution depends on the first player&#39;s belief about the game state, which belongs to a continuous (and often high-dimensional) belief space. In the literature, only a single method has demonstrated reliable performance for solving these types of games, namely Heuristic Search Value Iteration (HSVI). However, this method is restricted to small games. We address this limitation by presenting a new method with similar approximation and convergence guarantees but improved scalability and flexibility, which we call SAB: Shapley iteration with Aggregated Beliefs. Our method aggregates the belief space into a finite set of representative beliefs and computes their values through Shapley iteration. It then approximates the value function of the POSG through interpolation from these values. We prove that SAB converges and provide a bound on its approximation error. Experiments across several benchmark games show that SAB matches the performance of HSVI on small game instances while also scaling to larger games. Moreover, we find that SAB is up to 79% faster than HSVI at obtaining a near-optimal approximation.

AAAI 2026

Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees

We study the problem of solving one-sided, zero-sum, partially observable stochastic games (POSGs). These games model sequential interactions between two adversaries, where one player has partial observability of the game state. They are applicable to many important domains, such as robotics and cybersecurity. Solving such games is computationally challenging since the solution depends on the first player's belief about the game state, which belongs to a continuous (and often high-dimensional) belief space. In the literature, only a single method has demonstrated reliable performance for solving these types of games, namely Heuristic Search Value Iteration (HSVI). However, this method is restricted to small games. We address this limitation by presenting a new method with similar approximation and convergence guarantees but improved scalability and flexibility, which we call SAB: Shapley iteration with Aggregated Beliefs. Our method aggregates the belief space into a finite set of representative beliefs and computes their values through Shapley iteration. It then approximates the value function of the POSG through interpolation from these values. We prove that SAB converges and provide a bound on its approximation error. Experiments across several benchmark games show that SAB matches the performance of HSVI on small game instances while also scaling to larger games. Moreover, we find that SAB is up to 79% faster than HSVI at obtaining a near-optimal approximation.

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.

Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for large-scale or dynamic environments. Sample-based methods such as Sparse Sampling and Monte Carlo Tree Search (MCTS) are widely adopted for their ability to approximate optimal actions using a generative model. However, in practical settings, the generative model is often learned from limited data, introducing approximation errors that can degrade performance or lead to unsafe behaviors. To address these challenges, Robust MDPs (RMDPs) offer a principled framework for planning under model uncertainty, yet existing approaches are typically computationally intensive and not suited for real-time use. In this work, we introduce Robust Sparse Sampling (RSS), the first online planning algorithm for RMDPs with finite-sample theoretical performance guarantees. Unlike Sparse Sampling, which estimates the nominal value function, RSS computes a robust value function by leveraging the efficiency and theoretical properties of Sample Average Approximation (SAA), enabling tractable robust policy computation in online settings. RSS is applicable to infinite or continuous state spaces, and its sample and computational complexities are independent of the state space size. We provide theoretical performance guarantees and empirically show that RSS outperforms standard Sparse Sampling in environments with uncertain dynamics.

Online Robust Planning Under Model Uncertainty: A Sample-Based Approach

Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in critical domains.
Current research primarily focuses on binary "detection" approaches that, while capable of identifying hallucinations, fail to provide interpretable and actionable feedback for model improvement, thus limiting practical utility.
To address this limitation, a new research paradigm is proposed, shifting from "detection" to "diagnosis". The Hallucination Diagnosis Task is introduced, a task which requires models to not only detect hallucinations, but also perform error localization, causal explanation, and content correction.
We develop the Hallucination Diagnosis Generator (HDG), an automated pipeline that systematically generates high-quality training samples with rich diagnostic metadata from raw corpora through multi-dimensional augmentation strategies including controlled fact fabrication and reasoning chain perturbation.
Using HDG-generated data, we train HDM-4B-RL, a 4-billion-parameter hallucination diagnosis model, employing Group Relative Policy Optimization (GRPO) with a comprehensive reward function incorporating structural, accuracy, and localization signals.
Experimental results demonstrate that our model surpasses previous state-of-the-art detection models on the HaluEval benchmark while achieving comparable performance to advanced general-purpose models.
In comprehensive diagnosis tasks, HDM-4B-RL matches the capabilities of larger general models while maintaining smaller size.
This work validates the feasibility and value of hallucination diagnosis, providing an effective methodology for building more trustworthy and reliable generative AI systems.

From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis

Just recognizable distortion (JRD) has emerged as a promising paradigm for machine-centric video coding. However, existing JRD-guided coding methods are limited by coarse annotation granularity and high computational cost, which hinder their deployment. In this paper, we first investigate the impact of different JRD annotation strategies on downstream task performance. By incorporating both instance-level and contextual information, we construct a new JRD dataset with fine-grained annotations compatible with object detection and instance segmentation tasks. To enhance quantization parameter (QP) map prediction while maintaining computational efficiency, we propose a novel spiking neural network (SNN)-based framework that decomposes video frames into spatial structures, channel interactions, and temporal patterns. Furthermore, we introduce a spiking attention mechanism to aggregate task-relevant features and employ adaptive scaling vectors to suppress machine-perceived redundancy, enabling targeted bitrate allocation aligned with task-critical content. Extensive experiments on multiple datasets and backbones demonstrate that our approach consistently outperforms state-of-the-art codec-based and JRD-guided methods in maintaining task performance at ultra-low bitrates, while significantly reducing computational overhead.

Firing Bits Where It Matters: Spiking-Guided Just Recognizable Distortion Modeling for Machine-Centric Video Coding

Estimating counterfactual outcomes from observational data is critical for informed decision-making in domains such as personalized marketing, healthcare, and online platforms. In these contexts, decision processes frequently involve high-dimensional combinatorial interventions, including bundled channel allocation or product set recommendations. For such scenarios, both causal assessment of historical strategies and optimization of novel interventions necessitate models capable of extrapolating to intervention combinations that are underrepresented or entirely absent in observational data. Specifically, in digital marketing, companies often need to evaluate new combinations of channels or target emerging user segments that have not been previously exposed. Moreover, inherent biases in observational datasets, stemming from prior allocation policies and targeting mechanisms, further aggravate coverage sparsity and compromise off-support counterfactual inference. In this work, we propose Dual-Source Counterfactual Fusion (DSCF), a scalable framework that enables accurate counterfactual prediction under high-dimensional combinatorial interventions, with improved robustness to confounding bias. DSCF jointly models observational data and proxy counterfactual samples through a dual-head mixture-of-experts architecture and domain-guided fusion. This design effectively integrates bias reduction and information diversity while enabling adaptive generalization to counterfactual inputs. Extensive experiments on both synthetic and semi-synthetic datasets demonstrate the effectiveness and robustness of DSCF across diverse scenarios.

DSCF: Dual-Source Counterfactual Fusion for High-Dimensional Combinatorial Interventions

Transformers are the basis of modern large language models, but relatively little is known about their precise expressive power on graphs. We study the expressive power of graph transformers (GTs) by Dwivedi and Bresson (2020) and GPS-networks by Rampásek et al. (2022), both under soft-attention and average hard-attention. Our study covers two scenarios: the theoretical setting with real numbers and the more practical case with floats. With reals, we show that in restriction to vertex properties definable in first-order logic (FO), GPS-networks have the same expressive power as graded modal logic (GML) with the global modality. With floats, GPS-networks turn out to be equally expressive as GML with the counting global modality. The latter result is absolute, not restricting to properties definable in a background logic. We also obtain similar characterizations for GTs in terms of propositional logic with the global modality (for reals) and the counting global modality (for floats).

Expressive Power of Graph Transformers via Logic

Humans exhibit time-inconsistent behavior, in which planned actions diverge from executed actions. Understanding time inconsistency and designing appropriate interventions is a key research challenge in computer science and behavioral economics. Previous work focuses on progress-based tasks and derives a closed-form description of agent behavior, from which they obtain optimal intervention strategies. They model time-inconsistency using the $\beta$--$\delta$ discounting (quasi-hyperbolic discounting), but the analysis is limited to the case $\delta = 1$. In this paper, we relax that constraint and show that a closed-form description of agent behavior remains possible for the general case $0 < \delta \le 1$. Based on this result, we derive the conditions under which agents abandon tasks and develop efficient methods for computing optimal interventions. Our analysis reveals that agent behavior and optimal interventions depend critically on the value of $\delta$, suggesting that fixing $\delta = 1$ in many prior studies may unduly simplify real-world decision-making processes.

Delta Matters: An Analytically Tractable Model for beta–delta Discounting Agents

Deep neural networks (DNNs) are widely and successfully applied in the field of speaker recognition. However, recent studies reveal that these models are vulnerable to backdoor attacks, where adversaries inject malicious behaviors into victim models by poisoning the training process. Existing attack methods often rely on environmental noise or complex voice transformations, which are typically difficult to implement and exhibit poor stealthiness. To address these issues, this paper proposes two modulation-based backdoor attacks that leverage frequency modulation (FM) and amplitude modulation (AM) to construct audio triggers. In real-world scenarios, regular variations in frequency and amplitude are often imperceptible to human listeners, making the proposed attacks more covert. Experimental results show that our methods achieve high attack success rates in both digital and physical settings, while also demonstrating strong resistance to various state-of-the-art backdoor defenses. The code for reproducing main experiments is available at https://github.com/HanboCai/FSMA_ASMA.

Modulation-Based Backdoors: Leveraging Amplitude and Frequency Patterns to Attack Speaker Recognition

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action ac- curacy of these models on complex downstream tasks is unsatisfactory. One important reason is that these models rely solely on the post-training paradigm of imitation learning, which makes it difficult to have a deeper understanding of the distribution properties of data quality, which is exactly what Reinforcement Learning (RL) excels at. In this paper, we theoretically propose an offline RL post-training objective for VLA flow models and induce an efficient and feasible offline RL fine-tuning algorithm −− Adaptive Reinforced Flow Matching (ARFM). By introducing an adaptively adjusted scaling factor in the VLA flow model loss, we construct a principled bias-variance trade-off objective function to optimally control the impact of RL signal on flow loss. ARFM adaptively balances RL advantage preservation and flow loss gradient variance control, resulting in a more stable and efficient fine-tuning process. Extensive simulation and real-world experimental results show that ARFM exhibits excellent generalization, robustness, few-shot learning, and continuous learning performance.

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods that operate effectively. Global counterfactual explanations, expressed as actions to offer recourse, aim to provide succinct explanations and insights applicable to large population subgroups. High effectiveness, measured by the fraction of the population that is provided recourse, ensures that the actions benefit as many individuals as possible. Keeping the cost of actions low ensures the proposed recourse actions remain practical and actionable. Limiting the number of actions that provide global counterfactuals is essential to maximize interpretability. The primary challenge, therefore, is to balance these trade-offs—maximizing effectiveness, minimizing cost, while maintaining a small number of actions. We introduce $\texttt{GLANCE}$, a versatile and adaptive algorithm that employs a novel agglomerative approach, jointly considering both the feature space and the space of counterfactual actions, thereby accounting for the distribution of points in a way that aligns with the model's structure. This design enables the careful balancing of the trade-offs among the three key objectives, with the size objective functioning as a tunable parameter to keep the actions few and easy to interpret. Our extensive experimental evaluation demonstrates that $\texttt{GLANCE}$ consistently shows greater robustness and performance compared to existing methods across various datasets and models.

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook this information when aligning vision and language, thus leading to suboptimal performance. Toward solving this problem, we propose a method that can improve multimodal alignment and fusion based on both semantics and relationships.Specifically, we first extract multilevel semantic features from different vision encoder to capture more visual cues of the relationships. Then, we learn to project the vision features to group related semantics, among which are more likely to have relationships. Finally, we fuse the visual features with the textual by using inheritable cross-attention, where we globally remove the redundant visual relationships by discarding visual-language feature pairs with low correlation. We evaluate our proposed method on eight foundation models and two downstream tasks, visual question answering and image captioning, and show that it outperforms all existing methods.

Downloads

Next from AAAI 2026

Online Robust Planning Under Model Uncertainty: A Sample-Based Approach

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES