Singapore

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce data-independent spatial decay based on fixed distance metrics, applying uniform attention weighting regardless of image content and limiting adaptability to diverse visual scenarios. Inspired by recent advances in large language models where content-aware gating mechanisms (e.g., GLA, HGRN2, FOX) significantly outperform static alternatives, we present the first successful adaptation of data-dependent spatial decay to 2D vision transformers. 
We introduce \textbf{Spatial Decay Transformer (SDT)}, featuring a novel Context-Aware Gating (CAG) mechanism that generates dynamic, data-dependent decay for patch interactions. 
Our approach learns to modulate spatial attention based on both content relevance and spatial proximity. We address the fundamental challenge of 1D-to-2D adaptation through a unified spatial-content fusion framework that integrates manhattan distance-based spatial priors with learned content representations.
Extensive experiments on ImageNet-1K classification and generation tasks demonstrate consistent improvements over strong baselines. Our work establishes data-dependent spatial decay as a new paradigm for enhancing spatial attention in vision transformers.

AAAI 2026

Learning Spatial Decay for Vision Transformers

linear attention

vision transformer

decay

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 ACL 2025". 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 need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

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.

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.

Generalist Virtual Agents (GVAs) powered by Multimodal Large Language Models (MLLMs) exhibit impressive capabilities. However, their long-term learning is hampered by a core limitation: a failure to evolve beyond existing trajectories. This stems from memory systems that treat experiences as isolated fragments and rely on brittle semantic retrieval, preventing the synthesis of novel solutions from disparate knowledge. To address this, we introduce CA3Mem, a framework inspired by the human hippocampus that organizes experiences into a structured memory graph. Leveraging this graph, CA3Mem features two key innovations: 1) a generative memory recombination mechanism that synthesizes novel solutions to drive agent evolution, and 2) an associative retrieval algorithm that employs spreading activation to recall a comprehensive and contextually-aware set of experiences. Experiments on OSWorld and WebArena demonstrate that CA3Mem significantly enhances agent capabilities, leading to marked improvements in long-horizon planning, compositional generalization for novel tasks, and continuous adaptation from experience. The code is included in the supplementary materials.

Evolving Generalist Virtual Agents with Generative and Associative Memory

Detecting Out-Of-Distribution (OOD) samples in image classification is crucial for model reliability. With the rise of Vision-Language Models (VLMs), CLIP-OOD has become a research hotspot. However, we observe the Low Focus Attention phenomenon from the image encoders of CLIP, which means the attention of image encoders often spreads to non-in-distribution regions. This phenomenon comes from the semantic mismalignment and inter-class feature confusion. To address these issues, we propose a novel fine-tuned OOD detection method with the Double loss constraint based on Optimal Transport (DOT-OOD). DOT-OOD integrates the Double Loss Constraint (DLC) module and Optimal Transport (OT) module. The DLC module comprises the Aligned Image-Text Concept Matching Loss and the Negative Sample Repulsion Loss, which respectively (1) focus on the core semantics of ID images and achieve cross-modal semantic alignment, (2) expand inter-class distances and enhance discriminative. While the OT module is introduced to obtain enhanced image feature representations. Extensive experimental results show that in the 16-shot scenario of the ImageNet-1k benchmark, DOT-OOD reduces the FPR95 by over 10\% and improves the AUROC from 94.48\% to 96.57\% compared with SOTAs.

A Novel Fine-Tuned CLIP-OOD Detection Method with Double Loss Constraint Through Optimal Transport Semantic Alignment

Cross-market recommendation (CMR) faces severe challenges from distribution shifts between data-rich source markets and sparse target markets. Existing methods rely on a pre-training and fine-tuning paradigm for knowledge transfer, yet suffer from two key limitations: i) the objective gap between pre-training and full-parameter fine-tuning causes loss of generalized knowledge from source markets; ii) the high computational costs of extensive fine-tuning hinder scalability. To this end, we propose DCMPT, a novel Distilled Cross-Market Prompt-Tuning approach. DCMPT reframes the problem under a more efficient pre-training and prompt-tuning paradigm. Instead of full fine-tuning, we adapt a pre-trained universal backbone by freezing its weights and injecting a minimal set of learnable prompts to form a "student" model. To effectively optimize these prompts on sparse data, we introduce a novel teacher-student architecture: a specialized "teacher" model, trained exclusively on the target market, provides dense, market-specific supervision. This guidance is delivered via a dual distillation strategy designed to transfer global ranking patterns and adapt to local consumer tastes. Extensive experiments on real-world market datasets demonstrate that DCMPT significantly outperforms state-of-the-art methods, achieving superior target market performance with substantial parameter-efficiency. Code is provided in the supplementary material to ensure reproducibility.

Breaking Down Market Barriers: Distilled Prompt-Tuning Approach for Cross-Market Recommendation

As diffusion probabilistic models (DPMs) become central to Generative AI (GenAI), understanding their memorization behavior is essential for evaluating risks such as data leakage, copyright infringement, and trustworthiness. While prior research finds conditional DPMs highly susceptible to data extraction attacks using explicit prompts, unconditional models are often assumed to be safe. We challenge this view by introducing \textbf{Surrogate condItional Data Extraction (SIDE)}, a general framework that constructs data-driven surrogate conditions to enable targeted extraction from any DPM. Through extensive experiments on CIFAR-10, CelebA, ImageNet, and LAION-5B, we show that SIDE can successfully extract training data from so-called safe unconditional models, outperforming baseline attacks even on conditional models. Complementing these findings, we present a unified theoretical framework based on informative labels, demonstrating that all forms of conditioning, explicit or surrogate, amplify memorization. Our work redefines the threat landscape for DPMs, establishing precise conditioning as a fundamental vulnerability and setting a new, stronger benchmark for model privacy evaluation.

SIDE: Surrogate Conditional Data Extraction from Diffusion Models

Although deep learning-based methods have achieved promising performance in Pansharpening, they generally suffer from severe performance degradation when applied to data from unseen sensors. Existing cross-domain strategies, including retraining, fine-tuning, and zero-shot methods, fail to simultaneously preserve model architecture and maintain low adaptation costs. Therefore, we are the first to define and address a novel task in the pansharpening field: enhancing a model's cross-sensor generalization at an extremely low cost while keeping the model architecture invariant. To tackle this task, we propose SWIFT (Sensitive Weight Identification for Fast Transfer), a plug-and-play framework. SWIFT first employs an unsupervised manifold-based sampling strategy to efficiently select a high-fidelity subset the most informative target-domain samples. It then leverages this subset to probe a source-domain pre-trained model, identifying and updating only the weight subset most sensitive to the domain shift by analyzing the gradient behavior of its parameters. Extensive experiments demonstrate that SWIFT can be applied to various deep learning models, boosting adaptation efficiency by up to \textit{30-fold}. On a single NVIDIA RTX 4090 GPU, this reduces adaptation time from hours to as little as one minute. The adapted models not only substantially outperform direct-transfer baselines but also achieve performance competitive with, or even superior to full retraining while using only\textit{ 3\%} of the target domain dataset and adapting nearly 10\% to 30\% of the model’s parameters. This establishs a new state-of-the-art on the WorldView-2 and QuickBird datasets.

SWIFT：A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening

Despite extensive theoretical research on proportionality in approval-based multiwinner voting, its implications for which committees can be selected in practical elections remain poorly understood. We address this gap by (i) analyzing the computational complexity of several natural problems related to the behavior of proportionality axioms, and (ii) conducting an extensive experimental study on both real-world and synthetic elections. Our findings reveal substantial variation in the restrictiveness of proportionality across instances, including previously unobserved high levels of restrictiveness in some real-world cases. We also introduce and evaluate novel measures for quantifying a candidate's importance for achieving proportional outcomes, demonstrating that they clearly differ from traditional approval score–based assessments.

Understanding the Impact of Proportionality in Approval-Based Multiwinner Elections

Multi-object tracking (MOT) predominantly follows the tracking-by-detection paradigm, where motion prediction serves as a critical component for maintaining tracking continuity and handling occlusions. While Kalman filter have been the standard motion predictor due to their computational efficiency, they inherently fail on non-linear motion patterns. Conversely, recent data-driven motion predictors capture complex non-linear dynamics but suffer from limited domain generalization and computational overhead. Through extensive analysis, we reveal that even in datasets dominated by non-linear motion, Kalman filter outperforms data-driven predictors in up to 34\% of cases, demonstrating that real-world tracking scenarios inherently involve both linear and non-linear patterns. To leverage this complementarity, we propose PlugTrack, a novel framework that adaptively fuses Kalman filter and data-driven motion predictors through multi-perceptive motion understanding. Our approach employs multi-perceptive motion analysis through temporal patterns, prediction discrepancies, and uncertainty quantification to generate adaptive blending factors. Without architectural modifications to existing motion predictors, PlugTrack achieves significant performance gains on MOT17/MOT20, and attains state-of-the-art performance on DanceTrack. To the best of our knowledge, PlugTrack is the first framework to bridge classical and modern motion prediction paradigms through adaptive fusion in MOT.

PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking

Generating high-fidelity full-body human interactions with dynamic objects and static scenes remains a critical challenge in computer graphics and animation. Existing methods for human-object interaction often neglect scene context, leading to implausible penetrations, while human-scene interaction approaches struggle to coordinate fine-grained manipulations with long-range navigation. To address these limitations, we propose HOSIG, a novel framework for synthesizing full-body interactions through hierarchical scene perception. Our method decouples the task into three key components: 1) a scene-aware grasp pose generator that ensures collision-free whole-body postures with precise hand-object contact by integrating local geometry constraints, 2) a heuristic navigation algorithm that autonomously plans obstacle-avoiding paths in complex indoor environments via compressed 2D floor maps and dual-component spatial reasoning, and 3) a scene-guided motion diffusion model that generates trajectory-controlled, full-body motions with finger-level accuracy by incorporating spatial anchors and dual-space classifier-free guidance. Extensive experiments on the TRUMANS dataset demonstrate superior performance over state-of-the-art methods. Notably, our framework supports unlimited motion length through autoregressive generation and requires minimal manual intervention. This work bridges the critical gap between scene-aware navigation and dexterous object manipulation, advancing the frontier of embodied interaction synthesis. Codes will be available after publication.

HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception

Score Distillation Sampling (SDS) enables 3D asset generation by distilling priors from pretrained 2D text-to-image diffusion models, but vanilla SDS suffers from over-saturation and over-smoothing. To mitigate this issue, recent variants have incorporated negative prompts. However, these methods face a critical trade-off: limited texture optimization, or significant texture gains with shape distortion. In this work, we first conduct a systematic analysis and reveal that this trade-off is fundamentally governed by the utilization of the negative prompts, where Target Negative Prompts (TNP) that embed target information in the negative prompts dramatically enhancing texture realism and fidelity but inducing shape distortions. Informed by this key insight, we introduce the Target-Balanced Score Distillation (TBSD). It formulates generation as a multi-objective optimization problem and introduces an adaptive strategy that effectively resolves the aforementioned trade-off. Extensive experiments demonstrate that TBSD significantly outperforms existing state-of-the-art methods, yielding 3D assets with high-fidelity textures and geometrically accurate shape. Our code is available at https://anonymous.4open.science/r/TBSD-8A62.

Target-Balanced Score Distillation

In industrial anomaly detection, the scarcity of diverse defective samples poses a major challenge to training robust and scalable models. To address this, we propose an efficient few-shot training framework for synthesizing industrial anomalies using diffusion models. Unlike prior generative methods that rely on redundant or semantically meaningless prompts (e.g., "sks"), our method leverages only normal data with minimal textual guidance. We build upon the Stable Diffusion 3 architecture and introduce lightweight architectural adaptations and a curated training strategy guided by vision-language models (VLMs). Our method generates realistic and diverse anomalies aligned with interpretable prompts such as "scratch" or "broken component", and further allows spatial localization through prompt engineering. During inference, we adopt a multi-prompt strategy with attention modulation to enable precise and controllable anomaly synthesis. Experimental results demonstrate that our synthesized anomalies significantly enhance downstream anomaly detection performance and exhibit strong generalization across various industrial categories, even under limited supervision.

Content not yet available

Next from AAAI 2026

Evolving Generalist Virtual Agents with Generative and Associative Memory

Similar lecture

Spatial Representation of Large Language Models in 2D Scene