Singapore

Flow matching-based generative models offer a principled approach to modeling continuous-time dynamics in speech generation. However, inference is often computationally expensive due to repeated neural network evaluations required by ODE solvers.
We propose WaveEx, a training-free and plug-in acceleration framework which replaces portions of ODE integration with wavelet-guided extrapolation. By leveraging the multi-scale structure of latent trajectories, WaveEx predicts future states directly in the frequency domain without additional model evaluations or architectural changes.
WaveEx consistently accelerates inference across diverse speech generation tasks. The gains are especially pronounced in tasks like speech synthesis (up to 5.73$\times$ speedup) and music generation (2.75$\times$), where flow matching plays a central role in alignment modeling and dense ODE integration. Even in tasks with simpler input-output mappings such as speech enhancement (4.55$\times$) and voice conversion (2.75$\times$), WaveEx still achieves notable acceleration, demonstrating the robustness and generalizability of the approach.
These results highlight wavelet-guided extrapolation as a lightweight and broadly applicable alternative to full ODE solving for flow matching-based speech generation.

AAAI 2026

WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation

wavelet-guided extrapolation

speech generation

acceleration

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.

poster

Training large language models (LLMs) is fundamentally constrained by limited device memory and costly inter-device communication. Although pipeline parallelism alleviates memory pressure by partitioning models across devices, it incurs activation communication overhead that scales linearly with sequence length, limiting efficiency in long-context training. Recent weight-passing approaches (e.g., WeiPipe) mitigate this by transmitting model weights instead of activations, but suffer from redundant peer-to-peer (P2P) transfers and underutilized intra-node bandwidth. We propose TawPipe—topology-aware weight pipeline parallelism, which exploits hierarchical bandwidth in distributed clusters for improved communication efficiency. TawPipe: (i) groups devices based on topology to optimize intra-node collective and inter-node P2P communication; (ii) assigns each device a fixed shard of model weights and gradients, avoiding redundant transfers; and (iii) overlaps communication with computation to hide latency. Unlike global collective operations used in Fully Sharded Data Parallelism, TawPipe confines most communication within node boundaries, significantly reducing cross-node traffic. Extensive experiments on up to 24 GPUs with LLaMA‑style models show that TawPipe achieves superior throughput and scalability compared to state-of-the-art baselines.

TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training

In this work, we explore the technical feasibility of implementing end-to-end 3D object detection (3DOD) with surround-view fisheye camera system. Specifically, we first investigate the performance drop incurred when transferring classic pinhole-based 3D object detectors to fisheye imagery. To mitigate this, we then develop two methods that incorporate the unique geometry of fisheye images into mainstream detection frameworks: one based on the bird's-eye-view (BEV) paradigm, named FisheyeBEVDet, and the other on the query-based paradigm, named FisheyePETR. Both methods adopt spherical spatial representations to effectively capture fisheye geometry. In light of the lack of dedicated evaluation benchmarks, we release Fisheye3DOD, a new open dataset synthesized using CARLA and featuring both standard pinhole and fisheye camera arrays. Experiments on Fisheye3DOD demonstrate that our fisheye-compatible modeling improves accuracy by up to 6.2\% compared to baseline methods.

Exploring Surround-View Fisheye Camera 3D Object Detection

Generalized referring image segmentation (RIS) aims to segment regions in an image described by a natural language expression, handling not only single-target but also no- and multi-target scenarios. 
Previous approaches have proposed new components that enable a conventional RIS model to handle these additional scenarios, such as a target presence prediction head for no-target scenarios and multiple mask candidates for multi-target cases.
However, we observe that these methods predominantly rely on the conventional RIS backbone without fully integrating the additional components and thus still struggle in such general scenarios.
To address this, we propose an effective framework specifically tailored to handle no-target and multi-target scenarios, incorporating both architectural and data-driven approaches. 
Our architecture employs a learnable query designed to understand both target presence and plurality. 
While this approach alone outperforms previous state-of-the-art methods with similar computational requirements, we further introduce a novel data augmentation strategy that enables our framework to surpass computationally intensive LMM-based approaches.

Improving Target Presence and Plurality Recognition for Generalized Referring Image Segmentation

Wave‑like images—from attosecond streaking spectrograms to optical spectra, audio mel‑spectrograms and periodic video frames—encode critical harmonic structures that elude conventional feature extractors. We propose a unified, matrix‑equivalent framework that reinterprets convolution and attention as linear transforms on flattened inputs, revealing filter weights as basis vectors spanning latent feature subspaces. To infuse spectral priors we apply elementwise $\sin(\cdot)$ mappings to each weight matrix. Embedding these transforms into CNN, ViT and Capsule architectures yields Sin‑Basis Networks with heightened sensitivity to periodic motifs and built‑in invariance to spatial shifts. Experiments on a diverse collection of wave‑like image datasets—including 80,000 synthetic attosecond streaking spectrograms, thousands of Raman, photoluminescence and FTIR spectra, mel‑spectrograms from AudioSet and cycle‑pattern frames from Kinetics—demonstrate substantial gains in reconstruction accuracy, translational robustness and zero‑shot cross‑domain transfer. Theoretical analysis via matrix isomorphism and Mercer‑kernel truncation quantifies how sinusoidal reparametrization enriches expressivity while preserving stability in data‑scarce regimes. Sin‑Basis Networks thus offer a lightweight, physics‑informed approach to deep learning across all wave‑form imaging modalities.

SinBasis Networks: Matrix-Equivalent Feature Extraction for Wave-Like Optical Spectrograms

Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs). However, existing SFL methods require model homogeneity and assume all clients have sufficient computational resources, resulting in the exclusion of some resource-constrained clients. To address the prevalent system heterogeneity in real-world scenarios, enabling heterogeneous SFL systems that allow clients to adaptively deploy models of different scales based on their local resources is crucial. To this end, we introduce SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion. Specifically, SFedHIFI employs channel-wise matrix decomposition to deploy SNN models of adaptive complexity on clients with heterogeneous resources. Building on this, the proposed heterogeneous information fusion module enables cross-scale aggregation among models of different widths, thereby enhancing the utilization of diverse local knowledge. Extensive experiments on three public benchmarks demonstrate that SFedHIFI can effectively enable heterogeneous SFL, consistently outperforming all three baseline methods. Compared with ANN-based FL, it achieves significant energy savings with only a marginal trade-off in accuracy.

SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

Large language models (LLMs) augmented with retrieval have shown impressive performance in open-domain question answering, yet struggle significantly with temporal knowledge graph question answering (TKGQA). The core issue lies in structural misalignment: treating structured, temporally sensitive graph queries as plain text often causes LLMs to retrieve or reason with semantically similar but structurally incorrect facts, resulting in critical inaccuracies. To address this, we introduce SAR (Structure-Aligned Reasoning), a novel TKGQA framework that integrates LLM reasoning tightly with the explicit subject–predicate–object–time schema inherent in knowledge graphs. SAR employs an LLM agent to first decompose natural language questions into structured queries, clearly delineating entities, relationships, and temporal constraints. It then conducts schema-consistent, time-aware retrieval from the knowledge graph to acquire candidate quadruples, which guide a subsequent iterative ReAct-style reasoning process by the LLM. A final verification stage ensures that proposed answers strictly adhere to temporal conditions, reinforcing accuracy and temporal coherence. Experiments on two benchmark datasets, MultiTQ and CronQuestions, demonstrate SAR’s effectiveness, achieving the best results. Specifically, with GPT-4.1, SAR achieves 78.2% Hits@1 on MultiTQ, significantly outperforming existing methods, and similarly establishes a new performance record on CronQuestions. Our results underscore the critical importance of structural alignment in temporal reasoning tasks, particularly in handling complex queries involving multiple temporal constraints and multi-hop reasoning.

SAR: A Structure-Aligned Reasoning Framework for Temporal Knowledge Graph Question Answering

Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds and images simultaneously, little attention has been paid to the usefulness of image data in 3D UDA when training the models. In this paper, we propose an approach named MMAssist that improves the performance of 3D UDA with multi-modal assistance. A method is designed to align 3D features between the source domain and the target domain by using image and text features as bridges. More specifically, we project the ground truth labels or pseudo labels to the images to get a set of 2D bounding boxes. For each 2D box, we extract its image feature from a pre-trained vision backbone. A large vision-language model (LVLM) is adopted to extract the box's text description, and a pre-trained text encoder is used to obtain its text feature. During the training of the model in the source domain and the student model in the target domain, we align the 3D features of the predicted boxes with their corresponding image and text features, and the 3D features and the aligned features are fused with learned weights for the final prediction. The features between the student branch and the teacher branch in the target domain are aligned as well. To enhance the pseudo labels, we use an off-the-shelf 2D object detector to generate 2D bounding boxes from images and estimate their corresponding 3D boxes with the aid of point cloud, and these 3D boxes are combined with the pseudo labels generated by the teacher model. Experimental results show that our approach achieves promising performance compared with state-of-the-art methods in three domain adaptation tasks on three popular 3D object detection datasets. The code is available at https://github.com/liangp/MMAssist.

Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection

Standardized microplates are used to conduct large-scale biomedical research. The design of microplate layouts plays an essential role in handling so-called plate effects, i.e., systematic variations across the geometry of a microplate. An effective layout allows us to detect and negate plate effects. The randomized placement of controls and compounds produces layouts of limited effectiveness, so specific approaches are needed. A previously developed system, PLAID, proposed a constraint satisfaction model to construct effective plate layouts. However, PLAID does not scale well with microplate dimensions. To improve on PLAID, we propose Constraint Optimization of MicroPlate Designs (COMPD), which allows for greater flexibility and higher quality of the layouts.

Constraint Optimization of MicroPlate Designs

Maximum satisfiability (MaxSAT) is a viable approach to solving NP-hard combinatorial optimization problems through propositional encodings.
Understanding how problem structure and encodings impact the behaviour of different MaxSAT solving algorithms is an important challenge.
In this work, we identify MaxSAT instances in which the constraints entail an ordering of the objective variables as an interesting instance class from the perspectives of problem structure and MaxSAT solving. From the problem structure perspective, we show that a non-negligible percentage of instances in commonly used MaxSAT benchmark sets have ordered objectives and further identify various examples of such problem domains to which MaxSAT solvers have been successfully applied. From the algorithmic perspective, we argue that MaxSAT instances with ordered objectives, provided an ordering, can be solved (at least) as efficiently with a very simplistic algorithmic approach as with modern core-based MaxSAT solving algorithms. We show empirically that state-of-the-art MaxSAT solvers suffer from overheads and are outperformed by the simplistic approach on real-world optimization problems with ordered objectives.

Ordered Objectives in Maximum Satisfiability

During the video encoding process, the original spatial domain signal is first transformed into the frequency domain, followed by quantization and compression. As a result, the quality degradation in compressed videos primarily stems from distortions in the frequency domain information. However, existing video enhancement methods typically directly fuse information from adjacent frames in the spatial domain, making it difficult for models to effectively compensate for frequency domain distortions, which leads to suboptimal detail restoration. To address this issue, we propose a Hierarchical Frequency-Guided Alignment Transformer. Additionally, by analyzing the characteristics of the frequency domain, we find that different frequency bands exhibit both correlations and a certain degree of independence. Based on this, we introduce a Frequency-Aware Transformer module that employs a combination of independent and mixed processing to optimize information exchange across different frequency domains, effectively mitigating cross-interference from irrelevant information. Experimental results demonstrate that, compared to existing methods, our approach achieves state-of-the-art performance in objective metrics (PSNR/SSIM), perceptual quality (LPIPS), and subjective visual effects, while reducing model complexity.

Content not yet available

Next from AAAI 2026

TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training

Similar lecture

BSLM: A Bi-Level Speech-Language Model for the Joint Modeling of Discrete and Continuous Tokens