Singapore

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR&#39;s applicability in large games, researchers use neural networks to approximate its behavior. However, existing methods are mainly based on vanilla CFR and struggle to effectively integrate more advanced CFR variants. In this work, we propose an efficient model-free neural CFR algorithm, overcoming the limitations of existing methods in approximating advanced CFR variants. At each iteration, it collects variance-reduced sampled advantages based on a value network, fits cumulative advantages by bootstrapping, and applies discounting and clipping operations to simulate the update mechanisms of advanced CFR variants. Experimental results show that, compared with model-free neural algorithms, it exhibits faster convergence in typical imperfect-information games and demonstrates stronger adversarial performance in a large poker game.

AAAI 2026

Deep (Predictive) Discounted Counterfactual Regret Minimization

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers use neural networks to approximate its behavior. However, existing methods are mainly based on vanilla CFR and struggle to effectively integrate more advanced CFR variants. In this work, we propose an efficient model-free neural CFR algorithm, overcoming the limitations of existing methods in approximating advanced CFR variants. At each iteration, it collects variance-reduced sampled advantages based on a value network, fits cumulative advantages by bootstrapping, and applies discounting and clipping operations to simulate the update mechanisms of advanced CFR variants. Experimental results show that, compared with model-free neural algorithms, it exhibits faster convergence in typical imperfect-information games and demonstrates stronger adversarial performance in a large poker game.

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.<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.

Selecting an appropriate look-back horizon remains a fundamental challenge in time series forecasting (TSF), particularly in federated learning scenarios where data is decentralized, heterogeneous, and often non-independent. While recent work has explored horizon selection by preserving forecasting-relevant information in an intrinsic space, these approaches are primarily restricted to centralized and independently distributed settings. This paper presents a principled framework for adaptive horizon selection in federated time series forecasting through an intrinsic space formulation. We introduce a synthetic data generator that captures essential temporal structures in client data, including autoregressive dependencies, seasonality, and trend, while incorporating client-specific heterogeneity. Building on this model, we define a transformation that maps time series windows into an intrinsic representation space with well-defined geometric and statistical properties. We then derive a decomposition of the forecasting loss into a Bayesian term, which reflects irreducible uncertainty, and an approximation term, which accounts for finite-sample effects and limited model capacity. Our analysis shows that while increasing the look-back horizon improves the identifiability of deterministic patterns, it also increases approximation error due to higher model complexity and reduced sample efficiency. We prove that the total forecasting loss is minimized at the smallest horizon where the irreducible loss starts to saturate, while the approximation loss continues to rise. This work provides a rigorous theoretical foundation for adaptive horizon selection for time series forecasting in federated learning.

Optimal Look-back Horizon for Time Series Forecasting in Federated Learning

Generalization to unseen environments is a significant challenge in the field of robotics and control. In this work, we focus on contextual reinforcement learning, where agents act within environments with varying contexts, such as self-driving cars or quadrupedal robots that need to operate in different terrains or weather conditions than they were trained for. We tackle the critical task of generalizing to out-of-distribution (OOD) settings, without access to explicit context information at test time. Recent work has addressed this problem by training a context encoder and a history adaptation module in separate stages. While promising, this two-phase approach is cumbersome to implement and train. We simplify the methodology and introduce SPARC: single-phase adaptation for robust control. We test SPARC on varying contexts within the high-fidelity racing simulator Gran Turismo 7 and wind-perturbed MuJoCo environments, and find that it achieves reliable and robust OOD generalization.

Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy

Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personalized settings. Specifically, we identify two core challenges for personalization: 1) user expression styles are inherently diverse, making it difficult for standard expansions to preserve personalized intent. 2) user corpora induce heterogeneous semantic structures—varying in topical focus and lexical organization—which hinders the effective anchoring of expanded queries within the user’s corpora space. To address these challenges, we propose Personalize Before Retrieve (PBR), a framework that incorporates user-specific signals into query expansion prior to retrieval. PBR consists of two components: P-PRF, which generates stylistically aligned pseudo feedback using user history for simulating user expression style, and P-Anchor, which performs graph-based structure alignment over user corpora to capture its structure. Together, they produce personalized query representations tailored for retrieval. Experiments on two personalized benchmarks show that PBR consistently outperforms strong baselines, with up to 10% gains on PersonaBench across retrievers. Our findings demonstrate the value of modeling personalization before retrieval to close the semantic gap in user-adaptive RAG systems.

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval

Recent advances in controllable text-to-image (T2I) generation have shown promising results in natural image generation. However, controllable remote sensing (RS) T2I generation remains a challenging task due to the unique characteristics and requirements of geospatial data. Existing methods struggle to effectively integrate diverse spatial control condition (e.g., edge maps, segmentation masks) into a coherent generation process. They often fail to model the complex spatial relationships among different geographic elements and maintain semantic consistency with textual descriptions, which are typically vague or incomplete in RS applications. Additionally,
constrained by the small scale, low description quality, and limited scene variety of existing datasets, these models tend
to produce outputs with structurally inconsistent layouts and visually unrealistic content. To address these issues, we propose
Any2RSI, a flexible framework for controllable RS T2I generation that supports the flexible combination of various control
conditions. At its core, Any2RSI introduces a Cross-Modal Multi-Control Adapter capable of extracting modality-agnostic
embeddings from heterogeneous inputs, enabling precise spatial guidance. Furthermore, to overcome the limitations of sparse and
ambiguous textual prompts commonly found in RS tasks, we design a Vision Language Model (VLM)-Empowered Enriched
Description Generation module. This module enhances input descriptions by integrating cross-modal semantic information,
generating richer and more accurate textual representations that guide the generation of semantically coherent images. Finally, to
mitigate the data scarcity in RS T2I generation task, we construct RST2I-110K, a new large-scale, multi-scene dataset containing
over 115,000 high quality RS images paired with detailed textual descriptions. Extensive experiments on both existing and newly
proposed datasets demonstrate that Any2RSI achieves state-of-the-art performance, significantly improving both the realism and
structural accuracy of generated RS imagery.

Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description

Human artists can continuously refine their coarse sketches during artistic creation. This is quiet different from existing autoregressive generation, where a token is determined once sampled.
Aiming to flexibly refine the generated contents, this paper presents a Self-Calibrated AutoregressioN (SCAN) model capable of self-evaluating and refining generation quality without regenerating the entire image.
We unify image token generation and quality evaluation into a single autoregressive model, formulating both tasks as categorical prediction problems. 
During inference, the model first generates a coarse initial image, then iteratively refines the lowest-quality patches until satisfactory image quality is achieved. 
Experimental results demonstrate that SCAN effectively handles diverse real-world generation errors and achieves a promising balance between image quality and speed. For example, SCAN-XL achieves an FID of 2.10 and an IS of 326.1, surpassing the LlamaGen-XL by 1.29 (+38\%) in FID and 99.0 (+43.6\%) in IS, with a 5.6× speedup (19.76s → 3.56s).
Compared to recent works, SCAN improves FID and speed by +18.3\% and +23\% over VAR-d20, and by +7\% and +46\% over RandAR-XL. 
Code and models will be released to facilitate further exploration in self-calibrated content generation.

SCAN: Self-Calibrated AutoregressioN for High-Quality Visual Generation

We present VisAssist, the first large-scale video question-answering dataset with 13,413 real-world videos captured by visually impaired users, addressing a critical gap in assistive vision research. Unlike existing benchmarks relying on third-person footage, VisAssist provides authentic first-person perspectives that uniquely capture challenges in blind photography—including unconventional framing, motion artifacts, and frequent information omission. Benchmark evaluations of SOTA multimodal models reveal systematic limitations: severe deficiencies in spatial reasoning when processing dynamic first-person viewpoints, an inability to distinguish missing information from poor capture quality leading to hazardous hallucinations, and fragile text understanding especially for non-Latin scripts under suboptimal conditions. This work establishes a vital real-world benchmark and underscores the need for specialized architectures in visual assistance systems.

VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems

Multi-objective molecular optimization is a fundamental yet inherently challenging task in drug discovery, as it requires simultaneously optimizing multiple, often conflicting, molecular properties. Although recent deep learning methods have shown promise, they often lack objective-specific specialization and dynamic coordination, making them ineffective in handling competing objectives and difficult to scale in complex, high-dimensional molecular design tasks. Inspired by the division of labor among domain experts in medicinal chemistry, we propose MAMO, a multi-agent framework for molecular design that simulates expert collaboration. Each agent specializes in optimizing a single objective, and their interactions are orchestrated by a central scheduling module that dynamically reallocates tasks based on evaluation feedback. This coordination mechanism enables interpretable and goal-conditioned optimization while adaptively balancing conflicting objectives. Extensive experiments on benchmark datasets demonstrate that MAMO consistently achieves superior performance in both objective quality and Pareto diversity, particularly in scenarios with strong inter-objective conflict. Our results highlight the potential of multi-agent coordination strategies for scalable and conflict-aware molecular design.

Expert-Inspired Multi-Agent Coordination for Multi-Objective Molecular Optimization

Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have shown promise in enhancing spatial reasoning and task planning through learned semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges characteristic of mobile platforms. Second, current manipulation strategies exhibit insufficient generalization when confronted with the diverse object configurations encountered in open-world environments. Third, while crucial for practical deployment, the dual requirement of maintaining high platform maneuverability alongside precise end-effector control in unstructured settings remains understudied in the literature.

In this work, we present ODYSSEY, a unified mobile manipulation framework for agile quadruped robots equipped with manipulators, which seamlessly integrates high-level task planning with low-level whole-body control. To address the challenge of egocentric perception in language-conditioned tasks, we introduce a hierarchical planner powered by a vision-language model, enabling long-horizon instruction decomposition and precise action execution. At the control level, our novel whole-body policy achieves robust coordination of locomotion and manipulation across challenging terrains. We further present the first comprehensive benchmark for long-horizon mobile manipulation, evaluating diverse indoor and outdoor scenarios. Through successful sim-to-real transfer, we demonstrate the system’s generalization and robustness in real-world deployments, underscoring the practicality of legged manipulators in unstructured environments. Our work advances the feasibility of generalized robotic assistants capable of complex, dynamic tasks.

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

This paper investigates the problems large-scale distributed composite convex optimization, with motivations from a broad range of applications, including multi-agent systems, federated learning, smart grids, wireless sensor networks, compressed sensing, and so on. Stochastic gradient descent (SGD) and its variants are commonly employed to solve such problems. However, existing algorithms often rely on vanishing step sizes, strong convexity assumptions, or entail substantial computational overhead to ensure convergence or obtain favorable complexity. To bridge the gap between theory and practice, we integrate consensus optimization and operator splitting techniques (see Problem Reformulation) to develop a novel stochastic splitting algorithm, termed the stochastic distributed regularized splitting method (S-D-RSM). In practice, S-D-RSM performs parallel updates of proximal mappings and gradient information for only a randomly selected subset of agents at each iteration. By introducing regularization terms, it effectively mitigates consensus discrepancies among distributed nodes. In contrast to conventional stochastic methods, our theoretical analysis establishes that S-D-RSM achieves global convergence without requiring diminishing step sizes or strong convexity assumptions. Furthermore, it achieves an iteration complexity of $\mathcal{O}(1/\epsilon)$ with respect to both the objective function value and the consensus error. Numerical experiments show that S-D-RSM achieves up to 2--3$\times$ speedup compared to state-of-the-art baselines, while maintaining comparable or better accuracy. These results not only validate the algorithm’s theoretical guarantees but also demonstrate its effectiveness in practical tasks such as compressed sensing and empirical risk minimization. The code will be released after the anonymity period.

S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization Problems

Predicting the tensor properties of crystalline materials is a fundamental task in materials science. Unlike single-value property prediction, which is inherently invariant, tensor property prediction requires maintaining O(3) group tensor equivariance. Such equivariance constraint often requires specialized architecture designs to achieve effective predictions, inevitably introducing tremendous computational costs. Canonicalization, a classical technique for geometry, has recently been explored for efficient learning with symmetry. In this work, we revisit the problem of crystal tensor property prediction through the lens of canonicalization. Specifically, we demonstrate how polar decomposition, a simple yet efficient algebraic method, can serve as a form of canonicalization and be leveraged to ensure equivariant tensor property prediction. Building upon this insight, we propose a general O(3)-equivariant framework for efficient crystal tensor property prediction, referred to as GoeCTP. By utilizing canonicalization, GoeCTP achieves high efficiency without requiring the explicit incorporation of equivariance constraints into the network architecture. Experimental results indicate that GoeCTP achieves the best prediction performance and runs at most 13 times faster compared to existing state-of-the-art methods in benchmarking datasets, underscoring its effectiveness and efficiency.

Downloads

Next from AAAI 2026

Optimal Look-back Horizon for Time Series Forecasting in Federated Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES