Singapore

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.

AAAI 2026

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

and transparency

cv: interpretability

ml: transfer

explainable ml

ml: transparent

interpretable

explainability

domain adaptation

multi-task learning

### 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)

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.

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.

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

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

Learning multimodal representation is a fundamental task that supports a wide range of applications such as visual-text retrieval. While pioneering approaches \textit{e.g.,} CLIP paves the way by learning separated encoders for different modalities, they struggle to model complex interactions between modalities, resulting in inferior vision and language representation. Recently, researchers have begun to leverage powerful Large Vision-Language Models (LVLMs) for unimodal or multimodal encoding, showing substantial improvement over separated encoder methods. However, we find that directly adapting LVLMs to embedding models suffers from insufficient visual representation and coarse multimodal alignment. To address these issues, we propose a simple yet effective Fine-grained Alignment Matters (FAM) method to achieve fine-grained vision-language embedding learning with LVLMs. First, to close the gap between the pure generation and multimodal embedding using LVLMs, we propose Multi-granularity Aligned Contrastive (MAC) to explicitly learn and align fine-grained modality representations at multiple granularity levels using image-text pairs. Second, to mitigate the insufficiency of visual representation during adapting LVLMs to downstream embedding tasks, we propose a Vision Embedding Inversion Training (VEIN) strategy to encourage the extracted embeddings to preserve fine-grained visual features. Extensive experiments demonstrate the effectiveness of our method, which achieves superior performance on various downstream multimodal datasets.

FAM: Fine-Grained Alignment Matters in Multimodal Embedding Learning with Large Vision-Language Models

Neural Radiance Fields (NeRF) have shown remarkable capabilities
for photorealistic novel view synthesis. One major deficiency of
NeRF is that dense inputs are typically required, and the rendering
quality will drop drastically given sparse inputs. In this paper, we
highlight the effectiveness of rendered semantics from dense novel
views, and show that rendered semantics can be treated as a more
robust form of augmented data than rendered RGB. Our method
enhances NeRF’s performance by incorporating guidance derived
from the rendered semantics. The rendered semantic guidance encompasses
two levels: the supervision level and the feature level.
The supervision-level guidance incorporates a bi-directional verification
module that decides the validity of each rendered semantic
label, while the feature-level guidance integrates a learnable codebook
that encodes semantic-aware information, which is queried
by each point via the attention mechanism to obtain semanticrelevant
predictions. The overall semantic guidance is embedded
into a self-improved pipeline.We also introduce a more challenging
sparse-input indoor benchmark, where the number of inputs is
limited to as few as 6. Experiments demonstrate the effectiveness
of our method and it exhibits superior performance compared to
existing approaches.

Empowering Sparse-Input Neural Radiance Fields with Dual-Level Semantic Guidance from Dense Novel Views

Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training costs. In this paper, we investigate how to effectively bridge vision-language (VL) representations to action (A). We introduce VLA-Adapter, a novel paradigm designed to reduce the reliance of VLA models on large-scale VLMs and extensive pre-training. To this end, we first systematically analyze the effectiveness of various VL conditions and present key findings on which conditions are essential for bridging perception and action spaces. Based on these insights, we propose a lightweight Policy module with Bridge Attention, which autonomously injects the optimal condition into the action space. In this way, our method achieves high performance using only a 0.5B-parameter backbone, without any robotic data pre-training. Extensive experiments on both simulated and real-world robotic benchmarks demonstrate that VLA-Adapter not only achieves state-of-the-art performance, but also offers the fast inference speed reported to date. Furthermore, thanks to the proposed advanced bridging paradigm, VLA-Adapter enables the training of a powerful VLA model in just 8 hours on a single consumer-grade GPU, significantly lowering the barrier to deploying VLA models.

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Glass surfaces challenge object detection models as they mix the transmitted background with the reflected surrounding, creating confusing visual patterns. Previous methods relying on low-level cues (e.g., reflections and boundaries) or surrounding semantics are often unreliable in complex real-world scenarios. A glass image inherently comprises three distinct semantic components: semantics of the transmitted content, semantics of the reflected content, and semantics of the surrounding content. In this work, we observe that there is a relationship among these three types of semantics, where reflection semantics closely resembles surrounding semantics, while these two types of semantics tend to be different from the transmission semantics. For example, when on a street, we may see into a cafeteria through a glass wall, intermixed with reflection of the street, while the glass is surrounded by other street contents like shops and pedestrians, thereby creating a unique multi-semantic signature. Based on this observation, we propose the Multi-Semantic Net, MSNet, which identifies transmission, reflection, and surrounding semantics from glass images and exploits their relationships for glass surface detection. MSNet consists of two novel modules: (1) A Semantic Decomposition Module (SDM) containing Dual-Semantics Extraction Block (DSEB) to extract original image and reflection semantics and Semantic Elimination Block (SEB) to progressively derive transmission and surrounding semantics, and (2) An Adaptive Semantic Fusion Module (ASFM) to fuse these semantic components and adaptively learn their relationships to handle varying reflection conditions. Extensive experiments demonstrate that MSNet surpasses SOTA methods on public glass detection benchmarks.

Multi-Semantic Modeling for Glass Surface Detection in the Wild

Long Chain-of-Thought (CoT) reasoning has shown great promise in complex reasoning tasks, but its application to medical decision-making presents unique challenges.
Unlike structured tasks relying on static verification frameworks, medical decision-making requires dynamic validation through longitudinal clinical outcomes, exhibiting temporal-causal dependencies that complicate the verification of reasoning processes. 
Therefore, we introduce a novel data construction framework specifically designed for medical decision-making.
First, the framework analyzes real-world clinical cases to construct comprehensive timelines of medical events and identify critical decision points, including examination, diagnosis, and treatment.
Subsequently, the framework employs a clinical causality-aware strategy to generate decision-making questions at the identified critical decision points, along with reasoning traces and corresponding answers.
Finally, information drawn from future nodes serves as clinical logic-constrained criteria to re-evaluate and refine the soundness and coherence of the generated reasoning and responses.
Building on this, we present OncoCoT, an oncologic decision-making dataset derived from clinical records from the past four years across eight common cancer types.
Furthermore, we distill a subset of OncoCoT into a dedicated benchmark, OncoEval, to facilitate systematic evaluation of clinical reasoning capabilities in LLMs.
Evaluation results show that existing state-of-the-art reasoning models, such as Deepseek-r1 and GPT-o3, exhibit limited capability in addressing clinical problems in OncoEval, revealing room for improvement.

OncoCoT: A Temporal-causal Chain-of-Thought Dataset for Oncologic Decision-Making

How should we quantify the value of each training example when datasets are large, heterogeneous, and geometrically structured? Classical *Data‑Shapley* answers in principle, but its $O(n!)$ complexity and point‑wise perspective are ill‑suited to modern scales. We propose Hierarchical Contrastive Data Valuation (HCDV), a three‑stage framework that (i) learns a contrastive, geometry‑preserving representation, (ii) organises the data into a balanced coarse‑to‑fine hierarchy of clusters, and (iii) assigns Shapley‑style pay‑offs to *coalitions* via local Monte‑Carlo games whose budgets are propagated downward. HCDV collapses the factorial burden to $O\\bigl(T\sum_{\ell}K_{\ell}\bigr)=O(TK_{\max}\log n)$, rewards examples that sharpen decision boundaries, and regularises outliers through curvature‑based smoothness. We prove that HCDV approximately satisfies the four Shapley axioms with surplus loss $O(\eta\log n)$, enjoys sub‑Gaussian coalition deviation $\tilde{O}(1/\sqrt{T})$, and incurs at most $k\varepsilon_\infty$ regret for top‑$k$ selection. Experiments on four benchmarks — tabular, vision, streaming, and a 45 M‑sample CTR task — plus the OpenDataVal suite show that HCDV lifts accuracy by up to +5 pp, slashes valuation time by up to **$100\times$**, and directly supports tasks such as augmentation filtering, low‑latency streaming updates, and fair marketplace payouts.

From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples

Recent advances in deep learning have enabled highly accurate six-degree-of-freedom (6DoF) object pose estimation, driving its widespread use in real-world applications such as robotics, augmented reality, virtual reality, and autonomous systems. However, backdoor attacks pose a major security risk to deep learning models. By injecting malicious triggers into training data, an attacker can cause a model to perform normally on benign inputs but behave incorrectly under specific conditions. While most research on backdoor attacks has focused on 2D vision tasks, their impact on 6DoF pose estimation remains largely unexplored. Furthermore, unlike traditional backdoors that only change the object class, backdoors in 6DoF estimation must manipulate other dimensions, such as intrinsic camera parameters, translation, and rotation. Therefore, two-dimensional backdoor attack methods are completely ineffective against 6DoF pose estimation networks. To address this issue, we propose a novel backdoor attack framework to expose vulnerabilities in 6DoF pose estimation. Our framework uses synthetic and real 3D objects of varying shapes as triggers and assigns target poses to induce controlled erroneous pose outputs while maintaining normal behavior on clean inputs. We evaluated this attack on multiple models (including PVNet, DenseFusion, and PoseDiffusion) and datasets (such as Linemod, YCB-Video, and CO3D). Experimental results demonstrate that our approach achieves extremely high attack success rates without compromising performance on legitimate tasks. Across various models and objects, the backdoored network achieves up to 100% ADD accuracy on clean data, while also achieving 100% attack success rate (ASR) under trigger conditions. The accuracy of controlled erroneous pose output is also extremely high,as the attack sample achieves 97.70% ADD-P. These results demonstrate that the backdoor can be reliably implanted and activated, achieving a high attack success rate under trigger conditions and with negligible impact on benign data. Furthermore, we employ a simple defense method to demonstrate that our attack framework is undefendable. These findings reveal a potentially serious and previously underexplored threat to modern 6DoF pose estimation systems.

Downloads

Next from AAAI 2026

Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability

Similar lecture

A General Knowledge Injection Framework for ICD Coding