Singapore

The increasing demand for AR/VR applications has highlighted the need for high-quality content, such as 360$\\degree$ live wallpapers. 
However, generating high-quality 360$\\degree$ panoramic contents remains a challenging task due to the severe distortions introduced by equirectangular projection (ERP).
Existing approaches either fine-tune pretrained diffusion models on limited ERP datasets or adopt tuning-free methods that still rely on ERP latent representations, often resulting in distracting distortions near the poles.
In this paper, we introduce *SphereDiff*, a novel approach for synthesizing 360$\\degree$ static and live wallpaper with state-of-the-art diffusion models without additional tuning. 
We define a spherical latent representation that ensures consistent quality across all perspectives, including near the poles.
Then, we extend MultiDiffusion to spherical latent representation and propose a dynamic spherical latent sampling method to enable direct use of pretrained diffusion models.
Moreover, we introduce distortion-aware weighted averaging to further improve the generation quality.
Our method outperforms existing approaches in generating 360$\\degree$ static and live wallpaper, making it a robust solution for immersive AR/VR applications.

AAAI 2026 Main Conference

SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation

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.

Social bot detection is pivotal for safeguarding the integrity of online information ecosystems. Although recent graph neural network (GNN) solutions achieve strong results, they remain hindered by two practical challenges: (i) severe class imbalance arising from the high cost of generating bots, and (ii) topological noise introduced by bots that skillfully mimic human behavior and forge deceptive links. We propose the Reinforcement-guided graph Augmentation social Bot detector (RABot), a multi-granularity graph-augmentation framework that addresses both issues in a unified manner. RABot employs a neighborhood-aware oversampling strategy that linearly interpolates minority-class embeddings within local subgraphs, thereby stabilizing the decision boundary under low-resource regimes. Concurrently, a reinforcement-learning-driven edge-filtering module combines similarity-based edge features with adaptive threshold optimization to excise spurious interactions during message passing, yielding a cleaner topology. Extensive experiments on three real-world benchmarks and four GNN backbones demonstrate that RABot consistently surpasses state-of-the-art baselines. In addition, since its augmentation and filtering modules are orthogonal to the underlying architecture, RABot can be seamlessly integrated into existing GNN pipelines to boost performance with minimal overhead.

RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection

Autonomous agents in safety-critical applications must continuously adapt to dynamic conditions without compromising performance and reliability. Traditional approaches that rely on policy adaptation mechanisms have inherent limitations: symbolic approaches lack flexibility due to rigid structures, while reinforcement learning approaches incur costly retraining. The more recent approaches use end-to-end large language models (LLMs), which, despite enhanced adaptiveness, suffer from unacceptable inference latency and vulnerabilities, such as hallucinations that undermine real-time reliability. This work proposes $\textbf{TAPA}$ ($\textbf{T}$raining-free $\textbf{A}$daptation of $\textbf{P}$rogrammatic $\textbf{A}$gents), a framework that re-positions LLMs as intelligent action space moderators rather than direct decision-makers, enabling training-free action adaptation in evolving environments. TAPA decouples strategic intent from execution through logical primitive abstraction, allowing meta-agents to operate in an interpretable way over abstract, high-level actions. In the meantime, LLMs dynamically synthesize and adapt programs for the high-level actions, in order to respond promptly and correctly to environmental changes. In particular, our framework constructs program pools via a multi-scenario simulation with provenance chains, mitigating the scarcity of program samples in safety-critical domains, thereby facilitating program retrieval for familiar scenarios and generation for unseen situations. Extensive experiments across diverse complex domains validate TAPA's effectiveness, achieving optimal network uptime in cybersecurity and maintaining formation consensus in swarm intelligence tasks. This work promotes a paradigm shift for autonomous system design in evolving environments, from policy adaptation to dynamic action adaptation.

Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments

Surrogate-Assisted Evolutionary Algorithms (SAEAs) are widely used for expensive Black-Box Optimization. However, their reliance on rigid, manually designed components such as infill criteria and evolutionary strategies during the search process limits their flexibility across tasks. To address these limitations, we propose Dual-Control Bi-Space Surrogate-Assisted Evolutionary Algorithm (DB-SAEA), a Meta-Black-Box Optimization (MetaBBO) framework tailored for multi-objective problems. DB-SAEA learns a meta-policy that jointly regulates candidate generation and infill criterion selection, enabling dual control. The bi-space Exploratory Landscape Analysis (ELA) module in DB-SAEA adopts an attention-based architecture to capture optimization states from both true and surrogate evaluation spaces, while ensuring scalability across problem dimensions, population sizes, and objectives. Additionally, we integrate TabPFN as the surrogate model for accurate and efficient prediction with uncertainty estimation. The framework is trained via reinforcement learning, leveraging parallel sampling and centralized training to enhance efficiency and transferability across tasks. Experimental results demonstrate that DB-SAEA not only outperforms state-of-the-art baselines across diverse benchmarks, but also exhibits strong zero-shot transfer to unseen tasks with higher-dimensional settings. This work introduces the first MetaBBO framework with dual-level control over SAEAs and a bi-space ELA that captures surrogate model information.

Meta-Black-Box Optimization with Bi-Space Landscape Analysis and Dual-Control Mechanism for SAEA

Augmented Reality (AR) navigation has emerged as a transformative tool for spatial intelligence, enabling users to interactively explore complex environments through wearable and mobile AR devices. However, current AR navigation systems struggle with low indoor localization accuracy, weak semantic understanding, and limited long-term memory, which severely limits their adaptability in dynamic, multi-floor, and large-scale real-world settings. To address these challenges, we present AR-Nav benchmark, a novel dataset with corresponding suite that leverages vision and language for AR navigation. First, to construct this benchmark, we proposed an Augmented Reality Visual-Language Memory Model (AR‑VLM²), which generates structured, semantically rich, and temporally indexed representations for long-term AR navigation. Second, we design a lightweight navigation intent recommending module with hierarchical topological reasoning and language-grounded path planning, called ARN‑Pilot, enabling low-latency and personalized route selection. Third, we introduce a closed-loop AR interaction module that supports real-time multi-modal feedback, dynamic memory updates, and human-in-the-loop query refinement. Extensive experiments in indoor multi-floor and outdoor parking scenarios show that AR-Nav suite significantly outperforms state-of-the-art AR navigation methods.

AR-Nav Benchmark: Augmented Reality Navigation with Vision and Language

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the user query, which degrades answer quality and robustness in real-world settings with noisy or irrelevant retrieved content. Moreover, the prevailing single-pass paradigm struggles to deliver optimal answers in long-form generation that requiring multiple citations. To address these limitations, we propose FineRef, a framework based on Fine-grained error Reflection, which explicitly teaches the model to self-identify and correct two key citation errors—mismatch and irrelevance—on a per-citation basis. FineRef follows a two-stage training strategy. The first stage instills an “attempt–reflect–correct” behavioral pattern via supervised fine-tuning, using fine-grained and controllable reflection data constructed by specialized lightweight models. An online self-reflective bootstrapping strategy is designed to improve generalization by iteratively enriching training data with verified, self-improving examples. To further enhance the self-reflection and correction capability, the second stage applies process-level reinforcement learning with a multi-dimensional reward scheme that promotes reflection accuracy, answer quality, and correction gain. Experiments on the ALCE benchmark demonstrate that FineRef significantly improves both citation performance and answer accuracy. Our 7B model outperforms GPT-4 by up to 18\% in Citation F1 and 4\% in EM Recall, while also surpassing the state-of-the-art model across key evaluation metrics. FineRef also exhibits strong generalization and robustness in domain transfer settings and noisy retrieval scenarios.

FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations

Exploring how genetic sequences shape phenotypes is a fundamental challenge in biology and a key step toward scalable, hypothesis-driven experimentation. The task is complicated by the large modality gap between sequences and phenotypes, as well as the pleiotropic nature of gene–phenotype relationships. Existing sequence-based efforts focus on the degree to which variants of specific genes alter a limited set of phenotypes, while general gene knockout-induced phenotype abnormality prediction methods heavily rely on curated genetic information as inputs, which limits scalability and generalizability. As a result, the task of broadly predicting the presence of multiple phenotype abnormalities under gene knockout directly from gene sequences remains underexplored. We introduce GenePheno, the first interpretable multi-label prediction framework that predicts knockout-induced phenotypic abnormalities from gene sequences. GenePheno employs a contrastive multi-label learning objective that captures inter-phenotype correlations, complemented by an exclusive regularization that enforces biological consistency. It further incorporates a gene function bottleneck layer, offering human-interpretable concepts that reflect functional mechanisms behind phenotype formation. To support progress in this area, we curate four datasets with canonical gene sequences as input and multi-label phenotypic abnormalities induced by gene knockouts as targets. Across these datasets, GenePheno achieves state-of-the-art gene-centric $F_{max}$ and phenotype-centric AUC, and case studies demonstrate its ability to reveal gene functional mechanisms.

GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences

Hierarchical goal networks (HGNs) provide a framework for goal-directed planning by decomposing high-level goals into ordered subgoals. While prior work has examined non-determinism for hierarchical planning (specifically, HTNs), scant work studies how HGNs can help in stochastic settings. We introduce a formalism for probabilistic HGN planning with task-insertion semantics, enabling probabilistic planners to incorporate domain knowledge from goal decomposition methods. We design and evaluate two UCT-based algorithms for solving probabilistic HGN planning problems: an asymptotically optimal approach and a "tree-compression" approach that optimizes separately for the goals within the goal-subgoal hierarchy. We compare our two UCT-based HGN search algorithms experimentally on modified benchmark domains from the FOND-HTN literature. Our results demonstrate that on larger problems, the compressed search converges more quickly and outperforms the asymptotically optimal search. This suggests that HGNs can be effective in probabilistic planning and tree compression may yield better performance on large problems in anytime settings with stochastic action outcomes.

Probabilistic Hierarchical Goal Network Planning with UCT

Accurate multi-turn intent classification is essential for advancing conversational AI systems. Yet, it remains challenging due to the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder progress. This paper presents two novel approaches leveraging Large Language Models (LLMs) to enhance scalability and reduce latency in production dialogue systems. First, we introduce Symbol Tuning, which simplifies intent labels to reduce task complexity and improve performance in multi-turn dialogues. Second, we propose C-LARA (Consistency-aware, Linguistics Adaptive Retrieval Augmentation), a framework that employs LLMs for data augmentation and pseudo-labeling to generate synthetic multi-turn dialogues. These enriched datasets are used to fine-tune a small, efficient model suitable for deployment. Experiments conducted on multilingual dialogue datasets demonstrate significant improvements in classification accuracy and resource efficiency. Our methods enhance multi-turn intent classification accuracy by 5.09%, reduce annotation costs by 40%, and enable scalable deployment in low-resource multilingual industrial systems, highlighting their practicality and impact.

Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production

This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact finite state automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton, so that the generation of a control policy by deep reinforcement learning is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse or non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge, known to be challenging. Compared to approaches that rely solely on deep reinforcement learning, we obtain a reduction of two orders of magnitude in the iterations required for policy synthesis, and a significant improvement in scalability.

Symbolic Task Inference in Deep Reinforcement Learning

Large language models have revolutionized textual reasoning, yet their ability to act meaningfully in multimodal, real-world environments remains limited. They struggle to ground their decisions in visual context, adapt to changing goals, and plan actions over time—shortcomings that stem from a lack of structured, goal-driven reasoning and insufficient representations of the physical world.

In this talk, I present a unified framework for building embodied agents that can see, simulate, and reason. I begin by introducing methods for learning world simulators from data, arguing that visual reasoning—like textual reasoning—benefits from step-by-step processing. Inverting a physics simulator becomes key: agents must infer structured 3D neural representations of objects, parts, motions, and scenes directly from raw video. I describe methods for extracting such representations using generative priors, injecting them into vision-language models (VLMs), and scaling up their supervision via generative 3D simulation and fast, modular physics engines. These simulators enable agents to anchor their predictions in grounded physical reality, reducing hallucinations and improving control.

Complementing this simulation capability, I explore techniques that enable agents to reason over time and adapt their behavior. By integrating structured memory systems, agents learn to retain and retrieve relevant experiences to inform long-horizon plans. Language-based reflective feedback allows them to refine their strategies beyond what sparse rewards offer, forming abstractions that generalize across tasks. When trained to ground their reasoning directly in the visual environment, agents gain the ability to set subgoals, explore effectively, and verify their own hypotheses.

Together, these advances point toward autonomous systems that simulate before they act, reflect after they fail, and maintain an ongoing awareness of goals, constraints, and context. I will illustrate these capabilities across web automation, robotics, and interactive assistance, showing how agents that see, simulate, and reason offer a promising path toward general-purpose embodied intelligence.

Downloads

Next from AAAI 2026 Main Conference

RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES