Singapore

Major progress in reward modeling over recent years has been driven by a paradigm shift from task-specific designs to generalist reward models. Despite this trend, developing effective reward models remains a fundamental challenge: the heavy reliance on large-scale labeled preference data. Pre-training on abundant unlabeled data offers a promising direction, but existing approaches fall short in instilling explicit reasoning capabilities into reward models. To bridge this gap, we propose a self-training approach that can leverage unlabeled data to scale up reward reasoning in reward models. Based on this approach, we develop GRAM-R$^2$, a generative reward model trained to produce not only preference labels but also accompanying reward rationales. GRAM-R$^2$ can serve as a foundation model for reward reasoning and can be applied to a wide range of tasks with minimal or no additional fine-tuning. It can support downstream applications such as policy optimization and task-specific reward tuning. Experiments on response ranking, task adaptation, and reinforcement learning from human feedback demonstrate that GRAM-R$^2$ consistently delivers strong performance, outperforming several strong discriminative and generative baselines.

AAAI 2026

GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning

generative reward model

rlhf

large language model

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 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://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

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 

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.

Logit Knowledge Distillation has gained substantial
research interest in recent years due to its simplicity and
lack of requirement for intermediate feature alignment;
however, it suffers from limited interpretability in its
decision-making process. To address this, we propose
implicit Clustering Distillation (iCD): a simple and
effective method that mines and transfers interpretable
structural knowledge from logits, without requiring
ground-truth labels or feature-space alignment. iCD
leverages Gram matrices over decoupled local logit
representations to enable student models to learn latent
semantic structural patterns. Extensive experiments on
benchmark datasets demonstrate the effectiveness of iCD
across diverse teacher-student architectures, with
particularly strong performance in fine-grained
classification tasks---achieving a peak improvement of
+5.08% over the baseline.

iCD: An Implicit Clustering Distillation Method for Structural Information Mining (Student Abstract)

Adversarial attacks remain a major challenge for deep
learning models, as they can undermine both performance and
reliability in practical applications such as image
recognition. Although evolutionary algorithms (EAs) have
proven effective in optimizing complex systems, their use
for directly enhancing model robustness for adversarial
defense has been limited. In this study, we introduce
ResNet-GA, a method that applies evolutionary deep learning
(EDL) to develop ResNet-like networks specifically designed
to resist different forms of adversarial perturbations. The
approach evolves network architectures with a genetic
algorithm (GA), adapting the Residual Blocks at every stage
in ResNet according to the needs of each dataset and attack
type. Experimental results show that ResNet-GA strengthens
model robustness beyond standard baselines, highlighting
the value of iterative evolutionary design for building
more dependable deep learning systems under various
adversarial conditions.

ResNet-GA: Evolutionary Deep Learning Models for Adversarial Defense (Student Abstract)

End-to-end (E2E) autonomous driving must maintain global consistency while preserving local precision. However, existing E2E approaches rarely achieve both goals simultaneously. Therefore, we propose a multimodal coarse-to-local transformer (MC2L-Transformer), which is composed of a hierarchical transformer architecture. Multimodal inputs are fused into a shared embedding, and global waypoints are produced. Local refinement is then utilized to capture fine interactions around the vehicle. Furthermore, a temporal encoder summarizes recent context, and navigation target and velocity are embedded to guide route- and speed-aware decoding. We evaluate in CARLA, and the results show lower collision and off-route rates even under sudden events. These results indicate that combining a coarse-to-local hierarchical transformer with a lightweight temporal context provides a practical step toward reliable E2E autonomous driving.

Multimodal Coarse-to-Local Transformer for End-to-End Autonomous Driving (Student Abstract)

The consideration of channel correlation is crucial for
improving the performance of multivariate time series
forecasting. However, existing models fail to capture it in
homogeneous and highly correlated channels. In this work,
we introduce CompRestacking (Compression Restacking), a
strikingly intuitive and effective method to address this
problem. The approach consists of three main components:
(1) PCC-Restacking for correlation-aware channel ordering,
(2) Temporal embedding for time encoding, and (3)
Aggregation compression for compact token generation.
CompRestacking consistently outperforms in experiment
results. The results demonstrate that CompRestacking
leverages strong channel correlations for improved
performance.

CompRestacking: Capturing Channel Dependency in Highly Correlated Multivariate Time Series Data (Student Abstract)

Large language models (LLMs) have become indispensable, but the most celebrated efficiency methods---mixture-of-experts (MoE), speculative decoding, and complex retrieval-augmented generation (RAG)---were built for hyperscale providers with vast infrastructure and elite teams. 
Outside that context, their benefits collapse into overhead, fragility, and wasted carbon. 
The result is that a handful of Big Tech companies benefit, while thousands of hospitals, schools, governments, and enterprises are left without viable options. 
We argue that the next frontier is not greater sophistication at scale, but robust simplicity: efficiency that thrives under modest resources and minimal expertise. We propose a new research agenda: retrofitting pretrained models with more efficient architectures without retraining, inventing lightweight fine-tuning that preserves alignment, making reasoning economical despite long chains of thought, enabling dynamic knowledge management without heavy RAG pipelines, and adopting Overhead-Aware Efficiency (OAE) as a standard benchmark.
By redefining efficiency to include adoption cost, sustainability, and fairness, we can democratize LLM deployment---ensuring that optimization reduces inequality and carbon waste rather than amplifying them.

Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability

Large language models (LLMs) have the potential to address social and behavioral determinants of health by transforming labor intensive workflows in resource-constrained settings. Creating LLM-based applications that serve the needs of underserved communities requires a deep understanding of their local context, but it is often the case that neither LLMs nor their developers possess this local expertise, and the experts in these communities often face severe time/resource constraints.
This creates a disconnect: how can one engage in meaningful co-design of an LLM-based application for an under-resourced community when the communication channel between the LLM developer and domain expert is constrained? 
We explored this question through a real-world case study, in which our data science team sought to partner with social workers at a safety net hospital to build an LLM application that summarizes patients' social needs. 
Whereas prior works focus on the challenge of prompt tuning, we found that the most critical challenge in this setting is the careful and precise specification of *what* information to surface to providers so that the LLM application is accurate, comprehensive, and verifiable.
Here we present a novel co-design framework for settings with limited access to domain experts, in which the summary generation task is first decomposed into individually-optimizable attributes and then each attribute is efficiently refined and validated through a multi-tier cascading approach.

When the Domain Expert Has No Time and the LLM Developer Has No Clinical Expertise: Real-World Lessons from LLM Co-Design in a Safety-Net Hospital

Cognitive diagnosis (CD), inferring student knowledge mastery based on historical response records, is crucial for personalized educational services such as adaptive practice and learning path planning. Existing CD models were built based on the assumption that student's response data is integral, overlooking the nonrandom missingness of data caused by student answering exercises selectively. 
This missingness generally leads to biased and incomplete observations, where confounders, such as selection bias and exposure bias, significantly undermine the accuracy of student knowledge modeling.
To address missingness, we propose a Debiased Cognitive Diagnosis (DBCD) framework through the perspective of counterfactual modeling to remove exogenous confounders from the response data.
Specifically, the proposed DBCD achieves debiasing for CD by applying the idea of contrastive learning 
to constrain the model's prediction distributions on both factual and counterfactual data.
For a student, the factual data is his/her original response records, while the counterfactual data is generated by sampling the same number of exercises from all exercises of each concept through a similarity-based counterfactual sampling strategy.
Considering the difficulty of directly removing the exogenous confounders for student, we devise a β-Variational Autoencoder to model their exogenous confounders within the latent representations of knowledge proficiency by leveraging exercise priors and student response patterns. 
Then, the learned representations are further combined with the vanilla student's ability embedding 
via a gating mechanism-based fusion for final diagnosis prediction of the model.
Extensive experiments on three real-world educational datasets demonstrate that the proposed DBCD effectively mitigates confounders and even outperforms existing methods, thereby validating the feasibility and effectiveness of the DBCD framework.

Debiased Cognitive Diagnosis: A Contrastive Counterfactual Modeling Method via Variational Autoencoder

As one of the primary causes of visual impairment, Diabetic Retinopathy (DR) requires accurate and robust grading to facilitate timely diagnosis and intervention. Different from conventional DR grading methods that utilize single-view images, recent clinical studies have revealed that multi-view fundus images can significantly enhance DR grading performance by expanding the field of view (FOV). However, there is a long-tailed distribution problem in fundus image analysis, i.e., a high prevalence of mild DR grades and a low prevalence of rare ones (e.g., cases of high severity), which presents a significant challenge to developing a unified model capable of detecting rare or unseen DR grades not encountered during training. In this paper, we propose ProME-DR, a Prompt-driven zero-shot DR grading framework, which leverages prompt Matching and Emulating to recognize the unseen DR categories and views beyond the training set. ProME-DR disentangles the training process into two stages to learn generalized knowledge for novel DR disease grading. Initially, ProME-DR leverages two sets of prompt units to capture semantic and inter-view consistency knowledge via a split-and-mask manner, gathering instance-level DR visual clues. Subsequently, it constructs a concept-aware emulator to generate context prompt units, linking extensible knowledge learned from the previously seen DR attributes for zero-shot DR grading. Extensive experiments conducted on eight datasets and various scenarios confirm the superiority of ProME-DR.

Towards Zero-Shot Diabetic Retinopathy Grading: Learning Generalized Knowledge via Prompt-Driven Matching and Emulating

Quantifying and understanding human-AI alignment in high-risk tasks such as traffic accident prediction is crucial for deployment of AI systems. Existing alignment studies, however, focus mostly on the static domain and neglect the importance of attentional processing. Here, we present Attention‑DADA, a dataset of accident and non-accident traffic situations that contains detailed human prediction and frame-level eye gaze annotations. Using this benchmark we evaluate open- and closed-source, state‑of‑the‑art large vision-language-models (VLMs) in terms of their alignment in accident prediction performance and attentional processing in both zero-shot and attention-guided settings. Our results show that human prediction performance and consistency improves as the event time approaches. Similarly, human attentional patterns show dynamic updating throughout the event progression. Conversely, while attention guidance improves VLM prediction performance, both performance and attentional alignment stay significantly below human levels. These results provide the first quantitative evidence of misalignment both in terms of performance and attentional processing during analysis of time-critical, dynamic events, highlighting the need for future improvements in this area. Attention‑DADA and all evaluation codes are released on GitHub.

Mind the Gap: Quantifying and Aligning Human-AI Visual Attention for Accident Anticipation

The success of modern machine learning hinges on access to high-quality training data. In many real-world scenarios, such as acquiring data from public repositories or sharing across institutions, data is naturally organized into discrete datasets that vary in relevance, quality, and utility. Selecting which repositories or institutions to search for useful datasets, and which datasets to incorporate into model training are therefore critical decisions, yet most existing methods select individual samples and treat all data as equally relevant, ignoring differences between datasets and their sources. In this work, we formalize the task of dataset selection: selecting entire datasets from a large, heterogeneous pool to improve downstream performance under resource constraints. We propose **Da**taset **S**election via **Hierarchies** (**DaSH**), a dataset selection method that models utility at both dataset and group (e.g., collections, institutions) levels, enabling efficient generalization from limited observations. Across two public benchmarks (Digit-Five and DomainNet), **DaSH** outperforms state-of-the-art data selection baselines by up to 26.2% in accuracy, while requiring significantly fewer exploration steps. Ablations show **DaSH** is robust to low-resource settings and lack of relevant datasets, making it suitable for scalable and adaptive dataset selection in practical multi-source learning workflows.

Downloads

Next from AAAI 2026

iCD: An Implicit Clustering Distillation Method for Structural Information Mining (Student Abstract)

Similar lecture

Beyond Monolithic Rewards: Hybrid Multi-Aspect Reward Optimization