United States

Smart contracts, closely intertwined with cryptocurrency transactions, have sparked widespread concerns about considerable
financial losses of security issues. To counteract this, a variety of tools have been developed to identify vulnerability
in smart contract. However, they fail to overcome two challenges at the same time when faced with smart contract
bytecode: (i) strong interference caused by enormous non-relevant instructions; (ii) missing semantics of bytecode
due to incomplete data and control flow dependencies. In this paper, we propose a multi-teacher based bytecode vulnerability
detection method, namely Multi-Teacher Vulnerability Hunter (MTVHunter), which delivers effective denoising
and missing semantic to bytecode under multi-teacher guidance. Specifically, we first propose an instruction denoising
teacher to eliminate noise interference by abstract vulnerability pattern and further reflect in contract embeddings. Secondly,
we design a novel semantic complementary teacher with neuron distillation, which effectively extracts necessary
semantic from source code to replenish the bytecode. Particularly, the proposed neuron distillation accelerate this semantic filling by turning the knowledge transition into a regression task. We conduct experiments on 229,178 real-world smart contracts that concerns four types of common vulnerabilities.
Extensive experiments show MTVHunter achieves significantly
performance gains over state-of-the-art approaches.

AAAI 2025

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation

knowledge acquisition

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.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

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-25 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.



Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliable negative pairs due to the homogeneity of variables, hindering contrastive learning methods; 2) overlooking spatial correlations across variables over time; 3) limitations of efficiency and scalability in exist self-supervised learning methods. To tackle these, we propose a lightweight representation-learning model ST-ReP, integrating current value reconstruction and future value prediction into the pre-training framework for spatial-temporal forecasting. And we design a new spatial-temporal encoder to model fine-grained relationships. Moreover, multi-time scale analysis is incorporated into the self-supervised loss to enhance predictive capability. Experimental results across diverse domains demonstrate that the proposed model surpasses pre-training-based baselines, showcasing its ability to learn compact and semantically enriched representations while exhibiting superior scalability.

ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting

Zero-shot anomaly detection (ZSAD) aims to identify anomalies in new classes of images, and it's vital in industry and other fields. Most current methods are based on the multi-modal models CLIP and SAM, which have prior knowledge to assist model training, but they are highly dependent on the input of the prompts and their accuracy. We found that some diffusion model-based anomaly detection methods generate a large amount of semantic information and are very valuable for the ZSAD task. Therefore, we propose a diffusion model based on the zero-shot anomaly detection method, DZAD, and no additional prompt input is required. First, we propose the first diffusion-based zero-shot anomaly detection framework, which uses the proposed multi-timestep noise features extraction method to achieve anomaly detection in the denoising process of a latent space diffusion model with a semantic-guided (SG) network. Second, based on the detection results, we proposed a two-branch feature extractor for anomaly maps at different scales. Third, based on the difference between the anomaly detection task and other general image detection tasks, we propose a noise feature weight function for the diffusion model in the zero-shot anomaly detection task. Comparing with 7 recently state-of-the-art (SOTA) methods on MVTec AD and VisA datasets and analysis of the role of each component in ablation studies. The experiments demonstrate the validity of the method beyond the existing methods.

DZAD: Diffusion-based Zero-shot Anomaly Detection

Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training phase of FL is vulnerable to reconstruction attacks, such as attribute inference attacks (AIA), where adversaries exploit  exchanged messages and auxiliary public information to uncover sensitive attributes of targeted clients. While these attacks have been extensively studied in the context of classification tasks, their impact on regression tasks remains largely unexplored. In this paper, we address this gap by proposing novel model-based AIAs specifically designed for regression tasks in FL environments. Our approach considers scenarios where adversaries can either eavesdrop on exchanged messages or directly interfere with the training process. We benchmark our proposed attacks against state-of-the-art methods using real-world datasets. The results demonstrate a significant increase in reconstruction accuracy, particularly in heterogeneous client datasets, a common scenario in FL. The efficacy of our model-based AIAs makes them better candidates for empirically quantifying privacy leakage for federated regression tasks.

Attribute Inference Attacks for Federated Regression Tasks

The identification of the financial characteristics of indus-
try sectors has a large importance in accounting audit, al-
lowing auditors to prioritize the most important area during
audit. Existing company classification standards such as the
Standard Industry Classification (SIC) code allow to map a
company to a category based on its activity and products. In
this paper, we explore the potential of machine learning al-
gorithms and language models to analyze the relationship be-
tween those categories and companies’ financial statements.
We propose a supervised company classification methodol-
ogy and analyze several types of representations for financial
statements. Existing works address this task using solely nu-
merical information in financial records. Our findings show
that beyond numbers, textual information occurring in finan-
cial records can be leveraged by language models to match
the performance of dedicated decision tree-based classifiers,
while providing better explainability and more generic ac-
counting representations. We think this work can serve as a
preliminary work towards semi-automatic auditing. The mod-
els, code, and a preprocessed dataset will be made publicly
available for further research.

Linking Industry Sectors and Financial Statements: A Hybrid Approach for Company Classification

Code search is a highly required technique for software development. In recent years, the rapid development of transformer-based language models has made it increasingly more popular to adapt a pre-trained language model to a code search task, where contrastive learning is typically adopted to semantically align user queries and codes in an embedding space. Considering that the same semantic meaning can be presented using diverse language styles in user queries and codes, the representation of queries and codes in an embedding space may thus be non-deterministic. To address the above-specified point, this paper proposes an uncertainty-aware contrastive learning approach for code search. Specifically, for both queries and codes, we design an uncertainty learning strategy to produce diverse embeddings by learning to transform the original inputs into Gaussian distributions and then taking a reparameterization trick. We also design a hard negative sampling strategy to construct query-code pairs for improving the effectiveness of uncertainty-aware contrastive learning. The experimental results indicate that our approach outperforms 10 baseline methods on a large code search dataset with six programming languages. The results also show that our strategies of uncertainty learning and hard negative sampling can really help enhance the representation of queries and codes leading to an improvement of the code search performance.

Uncertainty-Aware Contrastive Learning with Hard Negative Sampling for Code Search Tasks

The capability of the reward model (RM) is crucial for the success of Reinforcement Learning from Human Feedback (RLHF) in aligning with human preferences. However, as training progresses, the output space distribution of the policy model shifts. The RM, initially trained on responses sampled from the output distribution of the early policy model, gradually loses its ability to distinguish between responses from the newly shifted distribution. This issue is further compounded when the RM, trained on a specific data distribution, struggles to generalize to examples outside of that distribution. These two issues can be united as a challenge posed by the shifted distribution of the environment. To surmount this challenge, we introduce MetaRM, a novel method leveraging meta-learning to adapt the RM to the shifted environment distribution. MetaRM optimizes the RM in an alternating way, by preserving both the preferences of the original preference pairs, as well as maximizing discrimination power over new examples of the shifted distribution. Extensive experiments demonstrate that MetaRM can iteratively enhance the performance of human preference alignment by improving the RM's capacity to identify subtle differences in samples of shifted distributions.

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective" width needed to process a token can vary from layer to layer. Motivated by this observation, we introduce the Adaptive Computation Module (ACM), a generic module that dynamically adapts its computational load to match the estimated difficulty of the input on a per-token basis. An ACM consists of a sequence of learners that progressively refine the output of their preceding counterparts. An additional gating mechanism determines the optimal number of learners to execute for each token. We also propose a distillation technique to replace any pre-trained model with an "ACMized" variant. Our evaluation of transformer models in computer vision and speech recognition demonstrates that substituting layers with ACMs significantly reduces inference costs without degrading the downstream accuracy for a wide interval of user-defined budgets.

Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference

Accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. While deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, enhancing the range of their visibility. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nature and massive scale.
In this work, we derive model spirit from the distribution of multiple randomly sampled generations, using three measures of consistency. We extensively evaluate eleven open and closed-source models on nine reasoning datasets. Results show that consistency-based calibration methods outperform existing post-hoc approaches in terms of calibration error. Meanwhile, we find that factors such as intermediate explanations, model scaling, and larger sample sizes enhance calibration, while instruction-tuning makes calibration more difficult. Moreover, confidence scores obtained from consistency can potentially enhance model performance. Finally, we offer guidance on choosing suitable consistency metrics for calibration, tailored to model characteristics such as the exposure to instruction-tuning and RLHF.

Calibrating Large Language Models with Sample Consistency

Model knowledge editing has become a widely researched topic because it enables efficient and rapid injection of new knowledge into language models or the correction of erroneous or outdated knowledge. Existing model knowledge editing methods typically categorized into single-instance sequential editing and massive one-time editing. However, in practical applications, the batched and iterative editing manner better aligns with model updating patterns. In this work, we explored the performance of parameter-update-based models in a new batched iterative editing benchmark. Our findings show that with an increase in the number of editing iterations, the accumulation of updated parameters leads to a greater change in the distribution of model parameters, making it more challenging to maintain editing performance and model stability. To address this degradation issue, we propose two methods: the Wasserstein distance constraint and update parameter sparsification, where the Wasserstein distance constraint optimizes the transition of parameter distribution before and after the editing, and update parameter sparsification significantly reduces the number of update parameters, thereby alleviating the issue of instability in the parameter distribution caused by the accumulation of update parameters through iterations. Our methods can be generally applied to different parameter-update-based knowledge editing models. Experiments on the zsRE and CounterFact datasets demonstrate that our methods can improve editing performance and enhance the later-stage stability of batched iterative editing across different models.

Downloads

Next from AAAI 2025

ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting

Similar lecture

Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification