Singapore

Exploration in sparse-reward tasks remains a fundamental challenge in multi-agent reinforcement learning (MARL) due to complex inter-agent interactions and the expansive exploration space. To address this issue, we propose Targeted Multi-Agent Exploration (TMAE), a novel framework that uncovers the causal relationships between the state space and the reward function, thereby reducing the exploration space and enabling more targeted exploration. Specifically, we construct a structural causal model (SCM) to model the causality between sub-state variables and sparse rewards, providing a robust analytical foundation for subsequent causal inference. Through counterfactual causal intervention, TMAE identifies the most critical subspaces for discovering rare but pivotal events while filtering out confounders. By incorporating these causal insights into the exploration process, TMAE prioritizes subspaces with stronger causal effects on sparse rewards, significantly enhancing exploration efficiency. We evaluate TMAE on a range of MARL benchmarks featuring sparse rewards, consistently demonstrating superior exploration efficiency compared to state-of-the-art methods. Furthermore, visualized causal insights derived from TMAE reveal its ability to effectively capture intricate dependencies and priorities in targeted exploration, showcasing strong alignment with prior domain knowledge.

AAAI 2026

TMAE:Learning Targeted Multi-Agent Exploration via Causal Inference

sparse reward

multi-agent reinforcement learning

exploration

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


AAAI 2023

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.

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.

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.

Proper quantification of predictive uncertainty is essential for the use of machine learning in safety-critical applications. Various uncertainty measures have been proposed for this purpose, typically claiming superiority over other measures. In this paper, we argue that there is no single best measure. Instead, uncertainty quantification should be tailored to the specific application. To this end, we use a flexible family of uncertainty measures that distinguishes between total, aleatoric, and epistemic uncertainty. These measures can be instantiated with specific loss functions, so-called proper scoring rules, to control their characteristics, and we show that different characteristics are useful for different tasks. In particular, we show that, for the task of selective prediction, the scoring rule should ideally match the task loss. On the other hand, for out-of-distribution detection, our results confirm that mutual information, a widely used measure of epistemic uncertainty, performs best. Furthermore, in an active learning setting, epistemic uncertainty based on zero-one loss is shown to consistently outperform other uncertainty measures.

Uncertainty Quantification for Machine Learning: One Size Does Not Fit All

Text-attributed heterogeneous graphs (TAHGs), characterized by nodes interconnected through diverse relationships and enriched with textual descriptions, are prevalent in numerous real-world applications. Recent advancements in integrating pre-trained language models (PLMs) and large language models (LLMs) with heterogeneous graph neural networks (HGNNs) have enhanced learning on TAHGs. However, the absence of standardized benchmark datasets tailored to TAHGs has impeded further progress. To bridge this gap, we propose the Text-attributed Heterogeneous Graphs Benchmark (THGB), a comprehensive collection of heterogeneous graphs from diverse domains, with each node enriched by relevant text attributes. Alongside dataset construction, we conduct extensive benchmark experiments using various graph learning methods, including GNN, PLM-GNN, and LLM-GNN approaches, for node classification and link prediction tasks. We evaluated model performance across supervised, few-shot, and zero-shot learning scenarios to assess their ability to leverage limited and unseen data. Our experiments highlight THGB's potential to improve the integration of heterogeneous structural and textual information. By providing curated datasets, robust evaluation protocols, and baseline implementations, THGB introduces a standardized benchmark and solid groundwork for TAHGs research.

THGB: A Comprehensive Benchmark for Text-attributed Heterogeneous Graphs

Retrieval-augmented generation (RAG) has greatly improved Large Language Models (LLMs) by adding external knowledge. However, current RAG-based methods face difficulties with long-context video understanding due to two main challenges. First, Current RAG-based methods for long-context video understanding struggle to effectively integrate multimodal and long-range temporal information, resulting in fragmented and context-insensitive knowledge representations. Furthermore, their retrieval mechanisms often rely on static textual matching, failing to dynamically align user queries with the most relevant video segments and leading to suboptimal downstream performance. To overcome these issues, we introduce \textbf{ViG-RAG}, a new framework to enhance long-context video understanding through structured textual knowledge grounding and multi-modal retrieval. Specifically, we segment video transcripts into structured units, extract key entities, form temporal connections and confidence for evidence, enabling coherent long-range reasoning. In this way, it utilizes a knowledge-aware grounding mechanism and a context-aware retrieval process that dynamically builds a probabilistic temporal knowledge graph to organize multi-video content. To improve retrieval accuracy, we propose a hybrid retrieval strategy for semantic and temporal features, with an adaptive distribution modeling the relevance. In this way, it achieves the optimal retrieval distribution for each query, enhancing generation efficiency by reducing unnecessary computations. On top of this, ViG-RAG uses a vision-language model to integrate semantic anchors, expanded contextual fields, and selected video frames, generating an accurate response. We evaluate ViG-RAG on several benchmarks, demonstrating that it significantly surpasses current RAG-based methods.

ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning

Recent advancements in multimodal large language models (MLLMs) have shown remarkable progress in video understanding. However, video MLLMs (VideoMLLMs) still suffer from hallucinations, generating nonsensical or irrelevant content. This issue partly stems from over-reliance on pre-trained knowledge, sometimes neglecting the rich visual information present in the video. Additionally, many existing methods rely on uniform frame sampling, which can overlook critical visual cues. To address these challenges, we present EchoBat, a novel approach that leverages audio information as well as video temporal and logical consistency to improve preference data construction and keyframe extraction. Our method integrates Direct Preference Optimization (DPO) to mitigate hallucinations by leveraging high-quality, contextually rich preference feedback. Specifically, we use GPT-4o to generate high-quality video descriptions and integrate visually relevant segments from Whisper-derived transcripts to construct preference responses. Correspondingly, we use the reference model itself to describe the reversed video, and use GPT-4o to flashback the text and fill in the hallucination to produce non-preferred responses. This strategy enhances the model’s ability to better understand visual content and temporal, logical relationships within videos. Furthermore, we propose an echo-layered sampling strategy for keyframe extraction from videos, which can provide more precise visual supervision compared to uniform sampling. Experimental results on the three latest video hallucination benchmarks demonstrate the effectiveness of our approach.

EchoBat: Echo-Vision Enhancement and Echo-Layered Sampling for Video LLMs Hallucination Mitigation

Growing concerns over data privacy underscore the need for deep learning methods capable of processing sensitive information without compromising confidentiality. Among privacy-enhancing technologies, Homomorphic Encryption (HE) stands out by offering post-quantum cryptographic security and end-to-end data protection, safeguarding data even during computation. Prior research on encrypted training has primarily focused on logistic regression, model fine-tuning, or relied on multi-party computation. This is largely due to the substantial computational overhead and algorithmic complexity involved in training deep Neural Networks (NNs) under HE. In this paper, we present ReBoot, the first framework to enable fully encrypted and non-interactive training of Multi-Layer Perceptrons (MLPs) using CKKS bootstrapping. ReBoot introduces a novel HE-compliant NN architecture based on local error signals, specifically designed to minimize multiplicative depth and reduce noise accumulation during training. It employs a tailored packing strategy that leverages real-number arithmetic through CKKS \textit{SIMD} operations, significantly lowering both computational and memory overhead. We evaluate ReBoot on both image and tabular benchmarks, demonstrating up to $+6.83\%$ improvement in test accuracy over existing solutions, while reducing training latency by up to $8.83\times$. ReBoot is made available to the scientific community as a public repository.

ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping

The proliferation of multimodal fake news across various domains presents a significant challenge to information ecosystems. While existing multi-domain fake news detection methods attempt to leverage data from multiple domains to improve generalization, they often suffer from a critical drawback: negative transfer. This problem arises from their common practice of indiscriminately aggregating information, failing to account for the complex, often asymmetric, relationships between domains. Consequently, knowledge from irrelevant or conflicting domains can severely degrade detection performance.

To address this challenge, we propose a novel framework named \textbf{PANDA: Prototype-driven Asymmetric Neighbor-Domain Adaptation}. PANDA is the first framework, to our knowledge, that explicitly models the directional transferability between news domains to mitigate negative transfer. At its core, PANDA learns a set of compact and representative \textit{prototypes} for each domain to encapsulate its core characteristics. Based on these prototypes, we devise a novel \textbf{P}rototype-based \textbf{A}symmetric \textbf{D}istance (PAD) metric to quantify the potential benefit of transferring knowledge from a source domain to a target one. Guided by this metric, a \textbf{G}umbel-based \textbf{N}eighbor \textbf{S}elector (GNS) dynamically identifies the most beneficial neighbor domains for each instance. Finally, a \textbf{D}omain-\textbf{C}ollaborative \textbf{A}ttention (DCA) module adaptively fuses knowledge from the selected domains. Extensive experiments on benchmark datasets demonstrate that PANDA significantly outperforms state-of-the-art methods and effectively mitigates negative transfer, showcasing its superior adaptability and robustness in real-world scenarios.

From Blind Transfer to Wise Selection: Prototype-Driven Neighbor-Domain Adaptation for Fake News Detection

The recent success of machine learning models, especially large-scale classifiers and language models, relies heavily on training with massive data. These data are often collected from online sources. This raises serious concerns about the protection of user data, as individuals may not have given consent for their data to be used in training. To address this concern, recent studies introduce the concept of unlearnable examples, i.e., data instances that appear natural but are intentionally altered to prevent models from effectively learning from them. While existing methods demonstrate empirical effectiveness, they typically rely on heuristic trials and lack formal guarantees. Besides, when unlearnable examples are mixed with clean data, as is often the case in practice, their unlearnability disappears. In this work, we propose a novel approach to constructing unlearnable examples by systematically maximising the Bayes error, a measurement of irreducible classification error. We develop an optimisation-based approach and provide an efficient solution using projected gradient ascent. Our method provably increases the Bayes error and remains effective when the unlearning examples are mixed with clean samples. Experimental results across multiple datasets and model architectures are consistent with our theoretical analysis and show that our approach can restrict data learnability, effectively in practice.

Towards Provably Unlearnable Examples via Bayes Error Optimization

Multivariate Time-Series (MTS) clustering is essential for uncovering latent temporal pattern distributions, yet it is significantly challenged by the prevalence of redundant, low-discriminative information in real-world data. That is, redundancy refers to repetitive, meaningless temporal patterns, while low-discriminative information denotes components within representations that hinder the differentiation of sample differences. Such redundancy dilutes cluster-specific temporal signatures, thereby impairing clustering performance. Although mainstream approaches mitigate redundancy through static masking, they lack the ability to refine adaptively driven by training, limiting their focus to truly discriminative characteristics. To address this limitation, an Evolving Masking Representation Learning model for Multivariate Time-Series Clustering (EMTC) is proposed, adopting evolving masking that leverages model training to mask redundant timestamps while highlighting cluster-friendly temporal information through adaptive refinement and multi-endogenous view contrastive training for capturing localized nuances and global coherence. At its core is an Evolving Masking Mechanism via dynamic self-attention: the module observes multi-endogenous view representations to identify discriminative features across local perspectives, pinpointing timestamps critical for high-discriminability representations. These insights refine masking by suppressing redundant timestamps and enhancing inter-sample discriminability. Furthermore, a Consistency and Reconstruction Adjustment module enhances training stability by enforcing cross-view consistency and facilitating MEV reconstruction, ensuring the learning of robust representations. Comprehensive experiments conducted on 13 real-world benchmark datasets demonstrate that EMTC significantly outperforms state-of-the-art methods in both redundancy reduction and overall clustering performance.

Mask the Redundancy: Evolving Masking Representation Learning for Multivariate Time-Series Clustering

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a condition often violated due to annotation noise, bias, or limited coverage. This misalignment can lead to undesirable behaviors, where models optimize for flawed signals rather than true human values. In this paper, we investigate a novel framework to identify and mitigate such misalignment by treating the fine-tuning process as a form of knowledge integration. We focus on detecting instances of \emph{proxy-policy conflicts}, cases where the base model strongly disagrees with the proxy. We argue that such conflicts often signify areas of \emph{shared ignorance}, where neither the policy nor the reward model possesses sufficient knowledge, making them especially susceptible to misalignment. To this end, we propose two complementary metrics for identifying these conflicts: a localized \textit{Proxy-Policy Alignment Conflict Score (PACS)} and a global \textit{Kendall-Tau Distance} measure. Building on this insight, we design an algorithm named \textbf{Selective Human-in-the-loop Feedback via Conflict-Aware Sampling (SHF-CAS)} that targets high-conflict QA pairs for additional feedback, refining both the reward model and policy efficiently. Experiments on two alignment tasks demonstrate that our approach enhances general alignment performance, even when trained with a biased proxy reward. Our work provides a new lens for interpreting alignment failures and offers a principled pathway for targeted refinement in LLM training.

Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment

Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, offensive, or culturally inappropriate content when prompted adversarially. Current defenses struggle to align outputs with human values without sacrificing generation quality or incurring high costs.
To address these challenges, we introduce VALOR (Value-Aligned LLM-Overseen Rewriter), a modular, zero-shot agentic framework for safer and more helpful text-to-image generation. VALOR integrates layered prompt analysis with human-aligned value reasoning: a multi-level NSFW detector filters lexical and semantic risks; a cultural value alignment module identifies violations of social norms, legality, and representational ethics; and an intention disambiguator detects subtle or indirect unsafe implications. When unsafe content is detected, prompts are selectively rewritten by a large language model under dynamic, role-specific instructions designed to preserve user intent while enforcing alignment. If the generated image still fails a safety check, VALOR optionally performs a stylistic regeneration to steer the output toward a safer visual domain without altering core semantics. Experiments across adversarial, ambiguous, and value-sensitive prompts show that VALOR significantly reduces unsafe outputs by up to 100.00% while preserving prompt usefulness and creativity. These results highlight VALOR as a scalable and effective approach for deploying safe, aligned, and helpful image generation systems in open-world settings.

Content not yet available

Next from AAAI 2026

Uncertainty Quantification for Machine Learning: One Size Does Not Fit All

Similar lecture

Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES