Singapore

Recent advancements in Text-to-Speech (TTS) technology have been remarkable, enabling current models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, corresponding evaluation techniques appear to be lagging: Existing Mean Opinion Score (MOS) estimation models typically perform regression-based scoring on entire speech segments—while a failed synthesized speech usually contains problematic elements in only a few isolated words rather than throughout the entire utterance. In this context, we present an intriguing finding: encoder-decoder ASR models, such as Whisper, leverage their extensive pre-training to precisely capture word-level mismatches between speech and text within their cross-attention mechanisms, thereby providing a fine-grained reward signal. Building upon this insight, we propose a novel TTS optimization method, which we term Word-level TTS Alignment by ASR-driven Attentive Reward (W3AR). Instead of relying on any explicit reward annotations, W3AR leverages the attention information within a pre-trained ASR model, enabling finer-grained alignment and optimization of the sequences predicted by the TTS model. Experimental results demonstrate that W3AR not only effectively improves the TTS generation quality of existing models but also further enhances zero-shot robustness on unseen speakers. Additionally, our findings and proposed methodology offer a new insight for generative tasks: understanding models can potentially serve as evaluators, providing highly fine-grained and valuable feedback for generative optimization.

AAAI 2026

Speech Recognition Model Improves Text-to-Speech Synthesis Using Fine-Grained Reward

text to speech

automatic speech recognition

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

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.

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.

Recent progress in robot learning has produced impressive
results, yet many systems still require learning from large
datasets of demonstrations and are less effective in clutter
or with highly deformable objects. This talk presents work
on data-efficient manipulation using (i) diffusion-based
augmentation that synthesizes geometrically consistent
images
and action labels to reduce demonstration requirements and
(ii) Vision-Language Models (VLMs) that inject high-level
semantics for contact-rich motion planning in clutter. We
will
also introduce ManipBench, which evaluates VLMs’ abilities
for low-level manipulation. Together, we show how to move
the community towards achieving robot manipulators that can
learn and operate with reduced demonstration requirements
across cluttered and real-world environments.

Data-Efficient and Contact-Rich Manipulation Through Diffusion Augmentation and Vision-Language Models

Accurate crop yield forecasting is essential for global food security. However, current AI models systematically underperform when yields deviate from historical trends. This issue arises from key data challenges, including a major asymmetry between rich pretraining weather datasets and the limited data available for fine-tuning. We introduce VITA (Variational Inference Transformer for Asymmetric data)}, a variational pretraining framework that addresses this asymmetry. Instead of relying on input reconstruction, VITA uses detailed weather variables as proxy targets during pretraining and learns to predict rich atmospheric states through self-supervised feature masking. This allows the model to be fine-tuned using only basic weather statistics during deployment. Applied to 763 counties in the U.S. Corn Belt, VITA achieves state-of-the-art performance in predicting corn and soybean yields across all evaluation scenarios. While it consistently delivers superior performance under normal conditions, its advantages are particularly pronounced during extreme weather years, with statistically significant improvements (paired t-test, $p \approx 0.01$). Importantly, VITA outperforms prior frameworks like GNN-RNN using less data, making it more practical for real-world use—particularly in data-scarce regions. This work highlights how domain-aware AI design can overcome data limitations and support resilient agricultural forecasting in a changing climate.

VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting

AI has great potential to transform education and daily
life. However, before integrating AI into classrooms, it is
crucial to first educate children on what AI is and how to
use it responsibly. Effective AI education should build on
children's existing perceptions, address misconceptions,
and establish a solid foundation for AI literacy. This
study explores primary school students’ perception of AI
and its relationship to their demographic characteristics
and digital skills. A survey was conducted in seven local
schools, with 233 students participating. The results
indicate that most of them were unfamiliar with AI, and
those who attempted to define or depict it often associated
it with robots or digital devices. The study also found
significant differences in students’ AI perceptions based
on factors like gender, grade, and prior digital skills
training. These variables were also linked to students’
awareness and understanding of AI. These findings
underscore the need for targeted AI educational
interventions for primary school students, leveraging their
existing perceptions.

‘What Do Children Think About AI?’: Insights and Educational Implications from Primary School Students’ Perceptions of AI

Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present $\textbf{EAGLE}$, a novel framework that leverages $\textbf{e}$pisodic $\textbf{a}$ppearance- and $\textbf{g}$eometry-aware memory to achieve unified 2D-3D visual query $\textbf{l}$ocalization in $\textbf{e}$gocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-of-the-art performance on the Ego4D-VQ benchmark. Code will be released soon.

EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision

Low-count positron emission tomography (PET) reconstruction is a challenging inverse problem due to severe degradations arising from Poisson noise, photon scarcity, and attenuation correction errors. Existing deep learning methods typically address these in the spatial domain with an undifferentiated optimization objective, making it difficult to disentangle overlapping artifacts and limiting correction effectiveness. In this work, we perform a Fourier-domain analysis and reveal that these degradations are spectrally separable: Poisson noise and photon scarcity cause high-frequency phase perturbations, while attenuation errors suppress low-frequency amplitude components. Leveraging this insight, we propose \textit{FourierPET}, a Fourier-based unrolled reconstruction framework grounded in the Alternating Direction Method of Multipliers. It consists of three tailored modules: a \textit{spectral consistency module} that enforces global frequency alignment to maintain data fidelity, an \textit{amplitude–phase correction module} that decouples and compensates for high-frequency phase distortions and low-frequency amplitude suppression, and a \textit{dual adjustment module} that accelerates convergence during iterative reconstruction. Extensive experiments demonstrate that \textit{FourierPET} achieves state-of-the-art performance with significantly fewer parameters, while offering enhanced interpretability through frequency-aware correction.

FourierPET: Deep Fourier-based Unrolled Network for Low-count PET Reconstruction

Multivariable time series forecasting methods can integrate information from exogenous variables, leading to significant prediction accuracy gains. The transformer architecture has been widely applied in various time series forecasting models due to its ability to capture long-range sequential dependencies. However, a naïve application of transformers often struggles to effectively model complex relationships among variables over time. To mitigate against this, we propose a novel architecture, termed Spectral Operator Neural Network (Sonnet). Sonnet applies learnable wavelet transformations to the input and incorporates spectral analysis using the Koopman operator. Its predictive skill relies on the Multivariable Coherence Attention (MVCA), an operation that leverages spectral coherence to model variable dependencies. Our empirical analysis shows that Sonnet yields the best performance on 34 out of 47 forecasting tasks with an average mean absolute error (MAE) reduction of 2.2% against the most competitive baseline. We further show that MVCA can remedy the deficiencies of naïve attention in various deep learning models, reducing MAE by 10.7% on average in the most challenging forecasting tasks.

Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting

Time-inconsistent behavior, such as procrastination or abandonment of long-term goals, arises when agents evaluate immediate outcomes disproportionately higher than future ones. This leads to globally suboptimal behavior, where plans are frequently revised or abandoned entirely. In the influential model of Kleinberg and Oren (2014) such behavior is modeled by a present-biased agent navigating a task graph toward a goal, making locally optimal decisions at each step based on discounted future costs. As a result, the agent may repeatedly deviate from initially intended plans.

Recent work by Belova et al. (2024) introduced a two-agent extension of this model, where a fully-aware principal attempts to guide the present-biased agent through a specific set of critical tasks without causing abandonment. This captures a rich class of principal–agent dynamics in behavioral settings.

In this paper, we provide a comprehensive algorithmic characterization of this problem. We analyze its computational complexity through the framework of parameterized algorithms, focusing on graph parameters that naturally emerge in this setting, such as treewidth, vertex cover, and feedback vertex set. Our main result is a fixed-parameter tractable algorithm when parameterized by the treewidth of the task graph and the number of distinct $(v,t)$-path costs. Our algorithm encaptures several input settings, such as bounded edge costs and restricted task graph structure. We demonstrate that our main result yields efficient algorithms for a number of such configurations.

We complement this with tight hardness results, that highlight the extreme difficulty of the problem even on simplest graphs with bounded number of nodes and constant parameter values, and motivate our choice of parameters. We delineate tractable and intractable regions of the problem landscape, which include answers to open questions of Belova et al. (2024).

Structural Approach to Guiding a Present-Biased Agent

In this work, we argue that not all sequence-to-sequence tasks require the strong inductive biases of autoregressive (AR) models. Tasks like multilingual transliteration, code refactoring, grammatical correction or text normalization often rely on local dependencies where the full modeling capacity of AR models can be overkill, creating a trade-off between their high accuracy and high inference latency. While non-autoregressive (NAR) models offer speed, they typically suffer from hallucinations and poor length control. To explore this trade-off, we focus on the multilingual transliteration task in Indic languages and introduce NADIR, a novel NAR architecture designed to strike a balance between speed and accuracy. NADIR integrates a Differential Transformer and a Mixture-of-Experts mechanism, enabling it to robustly model complex character mappings without sequential dependencies. NADIR achieves over a 13× speed-up compared to the state-of-the-art AR baseline. It maintains a competitive mean Character Error Rate of 15.78%, compared to 14.44% for the AR model and 21.88% for a standard NAR equivalent. Importantly, NADIR reduces Repetition errors by 49.53%, Substitution errors by 24.45%, Omission errors by 32.92%, and Insertion errors by 16.87%. This work provides a practical blueprint for building fast and reliable NAR systems, effectively bridging the gap between AR accuracy and the demands of real-time, large-scale deployment.

NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages

The deployment of large, black-box foundation models for
medical image classification is often hindered by the high
cost of acquiring large, task-specific labeled datasets for fine-
tuning. While active learning (AL) presents a promising solu-
tion, many state-of-the-art AL methods are computationally
expensive or require full access to internal model parame-
ters. We present VALIANT (Visual Adaptation and Learning
Integration for Active learNing Tasks), a new active learning
framework designed to efficiently adapt black-box foundation
models by overcoming these limitations. VALIANT intro-
duces a lightweight Visual Prompt Decoder (VIPD), trained
via unsupervised Zero-Order Optimization (ZOO), to gener-
ate task-specific visual prompts without internal model access.
Our core contribution is a perturbation-based ranking strat-
egy that leverages this VIPD to formulate a computationally
efficient, gradient-aware informativeness metric. This metric,
which we term prompt instability, identifies the most impactful
samples for the labeling budget. VALIANT further enhances
this process by incorporating anatomical information from
unsupervised segmentation maps to generate more discrimina-
tive visual prompts. Extensive evaluations on multiple medical
datasets demonstrate VALIANT’s superior performance and
significant reduction in labeling costs compared to a range of
existing active learning techniques, positioning it as a scalable
and practical solution for medical image analysis.

VALIANT: Prompt Instability for Active Learning in Black-Box Medical Imaging

The implicit hitting set (IHS) approach offers a general framework for solving
computationally hard combinatorial optimization problems declaratively.
Constituting a hybrid approach, IHS iterates between
decision oracle used for
extracting sources of inconsistency in the declarative specification at hand
and an optimizer for computing so-called
hitting sets (HSs) over the so-far accumulated sources of inconsistency.
While the decision oracle is specific to the declarative language at hand,
the optimizers is standardly instantiated through integer programming.
Focusing on the generic optimizer component, we explore alternative algorithmic
techniques for HS computation based on different ways of employing pseudo-Boolean (PB) reasoning
as well as stochastic local search. The alternative HS computation approaches are
applicable in general in different instantiations of the IHS approach.
We extensively evaluate the practical feasibility
of the alternatives in particular in the context of pseudo-Boolean (0-1 IP) optimization
as one of the most recent instantiations of IHS.
Highlighting a trade-off between efficiency and reliability,
while a commercial IP solver turns out to remain the most effective way to instantiate
HS computations in this setting, due to potential numerical instability using an off-the-shelf IP solver as-is
is not generally exact and can thereby result in incorrect results;
in fact, we show that exact HS computations instantiated via PB reasoning
can be made competitive with a numerically exact IP solver. Furthermore,
the use of PB reasoning as a basis for HS computations allows for obtaining certificates for
the correctness of IHS computations, generally applicable to any IHS instantiation in which
reasoning in the declarative language at hand can be captured in the PB-based proof format we employ.

Downloads

Next from AAAI 2026

Data-Efficient and Contact-Rich Manipulation Through Diffusion Augmentation and Vision-Language Models

Similar lecture

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

Data-Efficient and Contact-Rich Manipulation Through Diffusion Augmentation and Vision-Language Models

Similar lecture

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey

Downloads