Singapore

Reinforcement learning (RL) has achieved promising results in continuous control tasks, where efficient exploration of the state space is crucial for success. However, many recent RL approaches still struggle with sample inefficiency and insufficient exploration for long-horizon tasks, particularly in environments characterized by high-dimensional and complex state spaces.
To address these challenges, we propose a novel exploration framework, Latent State Predictive Exploration (LSPE). The core idea behind LSPE is to endow the agent with a form of ``foresight&quot; to enhance exploration in long-horizon settings. Specifically, LSPE employs a state encoder to learn compact latent representations from high-dimensional visual observations, effectively filtering out irrelevant or noisy information. To further enrich and stabilize these representations, we incorporate a diffusion-based self-predictive module that enforces temporal consistency by predicting future states, thereby improving both exploration and downstream predictive control.
Additionally, we introduce an Exploration Reward Function (ERF) that explicitly encourages the agent to visit novel latent states. This reward signal promotes more efficient and scalable exploration in complex environments.
We evaluate LSPE across a diverse set of challenging long-horizon navigation and manipulation tasks, spanning simulation environments such as Habitat and Robosuite, as well as deployment on a real robot in a **physical indoor environment**. Experimental results show that LSPE substantially enhances exploration efficiency and scales effectively to complex, high-dimensional tasks.

AAAI 2026

Latent State-Predictive Exploration for Deep Reinforcement Learning

representation learning

machine learning

reinforcement learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

Reinforcement learning (RL) has achieved promising results in continuous control tasks, where efficient exploration of the state space is crucial for success. However, many recent RL approaches still struggle with sample inefficiency and insufficient exploration for long-horizon tasks, particularly in environments characterized by high-dimensional and complex state spaces.
To address these challenges, we propose a novel exploration framework, Latent State Predictive Exploration (LSPE). The core idea behind LSPE is to endow the agent with a form of ``foresight" to enhance exploration in long-horizon settings. Specifically, LSPE employs a state encoder to learn compact latent representations from high-dimensional visual observations, effectively filtering out irrelevant or noisy information. To further enrich and stabilize these representations, we incorporate a diffusion-based self-predictive module that enforces temporal consistency by predicting future states, thereby improving both exploration and downstream predictive control.
Additionally, we introduce an Exploration Reward Function (ERF) that explicitly encourages the agent to visit novel latent states. This reward signal promotes more efficient and scalable exploration in complex environments.
We evaluate LSPE across a diverse set of challenging long-horizon navigation and manipulation tasks, spanning simulation environments such as Habitat and Robosuite, as well as deployment on a real robot in a **physical indoor environment**. Experimental results show that LSPE substantially enhances exploration efficiency and scales effectively to complex, high-dimensional tasks.

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.

The Segment Anything Model 2 (SAM2) has established a new benchmark for high-precision image and video segmentation, offering significant potential for a wide range of computer vision tasks. Despite its impressive performance, the model's substantial computational and memory requirements present a significant obstacle to its practical deployment on resource-constrained devices. In this paper, we introduce a novel framework for optimizing SAM2 through two synergistic, importance-driven strategies: quantization and memory management. Specifically, an Importance-driven Mixed-Precision Quantization scheme, which analyzes the sensitivity of each layer using a Weight-Activation Importance Score, is employed to enable a targeted bit-width assignment, preserving model accuracy by keeping critical layers at higher precision. Then, the Selective Importance-driven Synthesis (SIS) mechanism is proposed to address the inefficient accumulation of redundant data in the memory bank. SIS intelligently compresses the memory by identifying the most contextually similar historical frames and synthesizing them into a single, representative feature, thereby preserving informational diversity while enhancing temporal context understanding. Extensive experiments on the COCO and SA-V benchmarks validate our approach, showing that our optimized model consistently outperforms state-of-the-art quantization methods. Our work provides a principled framework for the co-design of quantization and dynamic memory management, offering a practical path toward deploying powerful video segmentation models in real-world applications.

Mix-QSAM2: Mixed-Precision Quantization for High Fidelity Segmentation in Resource Constrained Scenarios

Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception.

MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privacy-preserving methods often rely on anonymization. These methods suffer from (1) low concealment, where producing visually distorted videos that attract attackers’ attention during transmission, and (2) spatiotemporal disruption, where degrading essential spatiotemporal features for accurate VAR. To address these issues, we propose StegaVAR, a novel framework that embeds action videos into ordinary cover videos and directly performs VAR in the steganographic domain for the first time. Throughout both data transmission and action analysis, the spatiotemporal information of hidden secret video remains complete, while the natural appearance of cover videos ensures the concealment of transmission. Considering the difficulty of steganographic domain analysis, we propose Secret Spatio-Temporal Promotion (STeP) and Cross-Band Difference Attention (CroDA) for analysis within the steganographic domain. STeP uses the secret video to guide spatiotemporal feature extraction in the steganographic domain during training. CroDA suppresses cover interference by capturing cross-band semantic differences. Experiments demonstrate that StegaVAR achieves superior VAR and privacy-preserving performance on widely used datasets. Moreover, our framework is effective for multiple steganographic models. The codes will be released soon.

StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis

Multi-view 3D detection with bird’s eye view (BEV) is crucial for autonomous driving and robotics, but its robustness in real-world is limited as it struggles to predict accurate depth values. A mainstream solution, cross-modal distillation, transfers depth information from LiDAR to camera models but also unintentionally transfers depth-irrelevant information (e.g. LiDAR density). To mitigate this issue, we propose RayD3D, which transfers crucial depth knowledge along the ray: a line projecting from the camera to true location of an object. It is based on the fundamental imaging principle that predicted location of this object can only vary along this ray, which is finally determined by predicted depth value. Therefore, distilling along the ray enables more effective depth information transfer. More specifically, we design two ray-based distillation modules. Ray-based Contrastive Distillation (RCD) incorporates contrastive learning into distillation by sampling along the ray to learn how LiDAR accurately locates objects. Ray-based Weighted Distillation (RWD) adaptively adjusts distillation weight based on the ray to minimize the interference of depth-irrelevant information in LiDAR. For validation, we widely apply RayD3D into three representative types of BEV-based models, including BEVDet, BEVDepth4D, and BEVFormer. Our method is trained on clean NuScenes, and tested on both clean NuScenes and RoboBEV with a variety types of data corruptions. Our method significantly improves the robustness of all the three base models in all scenarios without increasing inference costs, and achieves the best when compared to recently released multi-view and distillation models.

RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection

Few-shot image classification (FSIC) aims to recognize novel categories from only a few labeled examples, making it inherently challenging under limited supervision. Existing approaches have attempted to alleviate this issue by incorporating explicit semantics like class names or knowledge graphs to guide learning. However, such methods often encounter semantic ambiguity due to their dependence on either overly simplistic semantic priors or resource-intensive external knowledge sources, which limits their potential. In this paper, we explore the frequency domain as an implicit and task-adaptive source of semantic information. We propose F2SST, a Frequency-to-Spatial Semantic Transfer framework that enhances feature learning by leveraging spectral signals as hidden semantics. Specifically, F2SST applies Fast Fourier Transform (FFT) to extract phase-invariant global frequency descriptors, followed by a lightweight Gated Spectral Attention (GSA) module that selectively emphasizes class-relevant frequency components. These enhanced spectral cues are then integrated into the spatial stream through a class-guided fusion mechanism, enabling more robust and semantically aligned representations. Extensive experiments on four standard benchmarks—miniImageNet, tieredImageNet, CIFAR-FS, and FC100—demonstrate that F2SST consistently improves performance, validating the effectiveness of frequency-domain semantics in FSIC.

F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification

Recent advances in vision-language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging sub-domain, with current pathology-specific VLMs exhibiting limitations in both diagnostic accuracy and reasoning plausibility. Such shortcomings are largely attributable to the nature of current pathology datasets, which are primarily composed of image–description pairs that lack the depth and structured diagnostic paradigms employed by real-world pathologists. In this study, we leverage pathology textbooks and real-world pathology experts to construct high-quality, reasoning-oriented datasets. Building on this, we introduce Patho-R1, a multimodal RLbased pathology Reasoner, trained through a three-stage pipeline: (1) continued pretraining on 3.5 million image-text pairs for knowledge infusion; (2) supervised fine-tuning on 500k high-quality Chain-of-Thought samples for reasoning incentivizing; (3) reinforcement learning using Group Relative Policy Optimization and Decoupled Clip and Dynamic sAmpling Policy Optimization strategies for multimodal reasoning quality refinement. To further assess the alignment quality of our dataset, we propose Patho-CLIP, trained on the same figure-caption corpus used for continued pretraining. Comprehensive experimental results demonstrate that both Patho-CLIP and Patho-R1 achieve robust performance across a wide range of pathology-related tasks, including zero-shot classification, cross-modal retrieval, Visual Question Answering, and Multiple Choice Question.

Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce EgoCross, a comprehensive benchmark designed to evaluate the cross-domain generalization of MLLMs in EgocentricQA. EgoCross covers four diverse and challenging domains, including surgery, industry, extreme sports, and animal perspective, representing realistic and high-impact application scenarios. It comprises approximately 1,000 QA pairs across 798 video clips, spanning four key QA tasks: prediction, recognition, localization, and counting. Each QA pair provides both OpenQA and CloseQA formats to support fine-grained evaluation. Extensive experiments show that most existing MLLMs, whether general-purpose or egocentric-specialized, struggle to generalize to domains beyond daily life, highlighting the limitations of current models. Furthermore, we conduct several pilot studies, e.g., fine-tuning and reinforcement learning, to explore potential improvements. We hope EgoCross and our accompanying analysis will serve as a foundation for advancing domain-adaptive, robust egocentric video understanding.
Data and codes will be released.

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering

Emerging from recent advances in foundation models, Large Wireless Models (LWMs) represent a new paradigm of general-purpose intelligence for wireless communications that transcends task-specific engineering. The success of foundation models is critically underpinned by scaling laws, which provide a predictable roadmap for how performance scales with resources. However, established scaling laws from language and vision, charting performance as a power-law of model and dataset sizes, are ill-suited for the wireless domain, as their core formulations cannot model the structured nature of the physical channel. To address this, we propose a novel wireless scaling law that extends the classical formulation by modeling two wireless-native factors: channel heterogeneity and discretization granularity. These two factors reshape scaling behavior via nested linear and power-law relationships, recasting the scaling law's parameters (notably the scaling exponent and irreducible loss) from universal constants into dynamic variables dictated by the physical environment. Our physics-aware formulation reveals two key insights: first, that compute-optimal scaling is not dictated by a fixed model-data ratio but is instead a dynamic function of heterogeneity and granularity, and second, that this dependency is particularly sensitive to granularity, allowing significant performance to be unlocked from existing data simply by refining its resolution. Crucially, this establishes a reliable roadmap for designing powerful yet resource-efficient LWMs, translating theoretical insights into actionable engineering principles. Extensive experiments validate our wireless scaling law, showing a 32.31% prediction accuracy improvement over classical laws in diverse wireless scenarios where they fail.

Scaling Law for Large Wireless Models

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM) agents to solve complex, multi-step tasks through environmental interaction. A fundamental challenge in such long-horizon scenarios is credit assignment, as delayed rewards provide inadequate signals for evaluating individual action contributions. 
Existing methods typically neglect trajectory transition dynamics, which leads to coarse-grained or biased credit assignment.
To address these limitations, we introduce SHADOW, a novel framework that systematically incorporates transition dynamics for improved credit assignment. Our framework makes two primary contributions: (i) a dynamics-aware state grouping mechanism that mitigates misleading action comparisons between dynamically inconsistent states, and (ii) a local dynamic advantage estimator that leverages Generalized Advantage Estimation (GAE) to precisely quantify individual action contributions through a fine-grained analysis of transition patterns. 
Comprehensive experiments conducted with the Qwen2.5-1.5/7B-Instruct agent model demonstrate that our method achieves success rate improvements of 9.4\%/7.6\% on the ALFworld benchmark and a performance gain of over 5\% on WebShop.

SHADOW: Dynamic-Aware Credit Assignment Against Long-Horizon Tasks

Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This ``cognitive shortcutting'' leads to suboptimal performance and brittle generalization, especially in zero-shot and low-resource scenarios where reasoning from limited contextual cues is crucial.
To address this problem, a reasoning framework is proposed for NER, which shifts the extraction paradigm from implicit pattern matching to explicit reasoning. This framework consists of three stages: Chain-of Thought (CoT) generation, CoT tuning, and reasoning enhancement. First, a dataset annotated with NER-oriented CoTs is generated, which contain task-relevant reasoning chains. Then, they are used to tune the NER model to generate coherent rationales before deriving the final answer. Finally, a reasoning enhancement stage is implemented to optimize the reasoning process using a comprehensive reward signal. This stage ensures explicit and verifiable extractions.
Experiments show that ReasoningNER demonstrates impressive cognitive ability in the NER task, achieving competitive performance. In zero-shot settings, it achieves state-of-the-art (SOTA) performance, outperforming GPT-4 by $12.3$ percentage points on the F1 score. Analytical results also demonstrate its great potential to advance research in reasoning-oriented information extraction.

Content not yet available

Next from AAAI 2026

Mix-QSAM2: Mixed-Precision Quantization for High Fidelity Segmentation in Resource Constrained Scenarios

Similar lecture

Exploration via State Influence Modeling

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES