United States

Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the first music generation model capable of restoring Chinese SongCi to our knowledge. Our model first predicts the melody from the input SongCi, then separately generates the singing voice and accompaniment based on that melody, and finally combines all elements to create the final piece of music. Additionally, to address the lack of ancient music datasets, we create OpenSongSong, a comprehensive dataset of ancient Chinese SongCi music, featuring 29.9 hours of compositions by various renowned SongCi music masters. To assess SongSong&#39;s proficiency in performing SongCi, we randomly selected 85 SongCi sentences that were not part of the training set for evaluation against SongSong and music generation platforms such as Suno and SkyMusic. The subjective and objective outcomes indicate that our proposed model achieves leading performance in generating high-quality SongCi music.

AAAI 2025

SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away

peai

applications

Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the first music generation model capable of restoring Chinese SongCi to our knowledge. Our model first predicts the melody from the input SongCi, then separately generates the singing voice and accompaniment based on that melody, and finally combines all elements to create the final piece of music. Additionally, to address the lack of ancient music datasets, we create OpenSongSong, a comprehensive dataset of ancient Chinese SongCi music, featuring 29.9 hours of compositions by various renowned SongCi music masters. To assess SongSong's proficiency in performing SongCi, we randomly selected 85 SongCi sentences that were not part of the training set for evaluation against SongSong and music generation platforms such as Suno and SkyMusic. The subjective and objective outcomes indicate that our proposed model achieves leading performance in generating high-quality SongCi music.

technical paper

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.



The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models (LLMs). Despite these advancements, challenges persist in the implementation of RALMs, particularly concerning their reliability and traceability. To be specific, the irrelevant document retrieval may result in unhelpful response generation or even deteriorate the performance of LLMs, while the lack of proper citations in generated outputs complicates efforts to verify the trustworthiness of the models. To this end, we propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs, whose core idea is to leverage reasoning trajectories generated by the LLM itself. The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process. We evaluated our framework across four public datasets (two short-form QA datasets, one long-form QA dataset, and one fact verification dataset) to demonstrate its superiority. Our method can outperform existing state-of-art models and achieve performance comparable with GPT-4, while only using 2,000 training samples.

Improving Retrieval Augmented Language Model with Self-Reasoning

Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, similar to issues in graph neural networks (GNNs). While oversmoothing in GNNs has been extensively studied, its implications in hypergraphs are less explored. This paper addresses this gap by first theoretically exploring the reasons behind oversmoothing in deep HGNNs. Our novel insights suggest that a spectral-based hypergraph convolution, equipped with both low-pass and high-pass filters, can potentially mitigate these effects. Motivated by these findings, we introduce FrameHGNN, a framework that utilizes framelet-based hypergraph convolutions integrating tight framelet transforms with both low-pass and high-pass components, as well as the commonly-used strategies in designing deep GNN architecture: initial residual and identity mappings.  Experimental results on diverse benchmark datasets demonstrate that FrameHGNN outperforms several state-of-the-art models, effectively reducing oversmoothing while improving predictive accuracy. Our contributions not only advance the theoretical understanding of deep hypergraph learning but also propose a practical spectral-based approach for HGNNs, emphasizing the design of multifrequency channels

Deep Hypergraph Neural Networks with Tight Framelets

Reinforcement learning is a widely used approach for training an agent to maximize rewards in a given environment. Action policies learned with this technique see a broad range of applications in practical areas like games, healthcare, robotics, or autonomous driving. However, enforcing ethical behavior or norms based on deontic constraints that the agent should adhere to during policy execution remains a complex challenge. Especially constraints that emerge after the training can necessitate to redo policy learning, which can be costly and, more critically, time-intense. In order to mitigate this problem, we present a framework for policy fixing in case of a norm violation, which allows the agent to stay operational. Based on answer set programming (ASP), emergency plans are generated that exclude or minimize cost of norm violations by future actions in a horizon of interest. By combining and developing optimization techniques, efficient policy fixing under real-time constraints can be achieved.

ASP-Driven Emergency Planning for Norm Violations in Reinforcement Learning

The gold standard in human-AI collaboration is complementarity: when combined performance exceeds both the human and algorithm alone. We investigate this challenge in binary classification settings where the goal is to maximize 0-1 accuracy. Given two or more agents who can make calibrated probabilistic predictions, we show a "No Free Lunch"-style result. Any deterministic collaboration strategy (a function mapping calibrated probabilities into binary classifications) that does not essentially always defer to the same agent will sometimes perform worse than the $\textit{least accurate}$ agent. In other words, complementarity cannot be achieved "for free." The result does suggest one model of collaboration with guarantees, where one agent identifies "obvious" errors of the other agent. We also use the result to understand the necessary conditions enabling the success of other collaboration techniques, providing guidance to human-AI collaboration.

A No Free Lunch Theorem for Human-AI Collaboration

Group Equivariant Convolution (GConv) can effectively handle rotational symmetry data.
They assume uniform and strict rotational symmetry across all features, as the transformations under the specific group. 
However, real-world data rarely conforms to strict rotational symmetry commonly referred to as Rotational Symmetry-Breaking in the system or dataset, making GConv unable to adapt effectively to this phenomenon. 
Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called the $G$-Biases under the group order to break strict group constraints and achieve $\textbf{R}$elaxed $\textbf{R}$otational $\textbf{E}$quivarant $\textbf{Conv}$olution (RREConv). 
We conduct extensive experiments to validate Relaxed Rotational Equivariance on rotational symmetry groups $\mathcal{C}_n$ (e.g. $\mathcal{C}_2$, $\mathcal{C}_4$, and $\mathcal{C}_6$ groups). 
Further experiments demonstrate that our proposed RREConv-based methods achieve excellent performance, compared to existing GConv-based methods in classification and detection tasks on natural image datasets.

Relaxed Rotational Equivariance via G-Biases in Vision

Graph neural networks (GNNs) have emerged as an effective tool for fraud detection, identifying fraudulent users, and uncovering malicious behaviors. However, attacks against GNN-based fraud detectors and their risks have rarely been studied, thereby leaving potential threats unaddressed. Recent findings suggest that frauds are increasingly organized as gangs or groups. In this work, we design attack scenarios where fraud gangs aim to make their fraud nodes misclassified as benign by camouflaging their illicit activities in collusion. Based on these scenarios, we study adversarial attacks against GNN-based fraud detectors by simulating attacks of fraud gangs in three real-world fraud cases: spam reviews, fake news, and medical insurance frauds. We define these attacks as multi-target graph injection attacks and propose MonTi, a transformer-based Multi-target one-Time graph injection attack model. MonTi simultaneously generates attributes and edges of all attack nodes with a transformer encoder, capturing interdependencies between attributes and edges more effectively than most existing graph injection attack methods that generate these elements sequentially. Additionally, MonTi adaptively allocates the degree budget for each attack node to explore diverse injection structures involving target, candidate, and attack nodes, unlike existing methods that fix the degree budget across all attack nodes. Experiments show that MonTi outperforms the state-of-the-art graph injection attack methods on five real-world graphs.

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors

The generalization problem is broadly recognized as a critical challenge in detecting deepfakes. Most previous work believes that the generalization gap is caused by the differences among various forgery methods. However, our investigation reveals that the generalization issue can still occur even when the forgery techniques are identical or similar. In this work, we identify two biases that detectors may also be prone to overfitting: position bias and content bias, as depicted in Fig. 1. For the position bias, we observe that detectors are prone to ``lazily" depending on the specific positions within an image (e.g., central regions even no forgery). As for content bias, we argue that detectors may potentially and mistakenly utilize forgery-unrelated information for detection (e.g., background and hair). To intervene in these biases, we propose two branches for shuffling and mixing with tokens in the latent space of transformers. For the shuffling branch, we rearrange the tokens and corresponding position embedding for each image while maintaining the local correlation. For the mixing branch, we randomly select and mix the tokens in the latent space between two images with the same label within the mini-batch to recombine the content information. During the learning process, we align the outputs of detectors from different branches in both feature space and logit space. Contrastive losses for features and divergence losses for logits are applied to obtain unbiased feature representation and classifiers. We demonstrate and verify the effectiveness of our method through extensive experiments on widely used evaluation datasets.

Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixing

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems are confronted with several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, impeding practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyper-parameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces an innovative methodology to overcome these obstacles. The proposed technique, DG-NLOS, integrates two branches: an albedo-focused reconstruction branch dedicated to the recovery of albedo information, and a depth-focused reconstruction branch that extracts geometrical details. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. Moreover, we employ the graph as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. In essence, DG-NLOS demonstrates robustness in realistic scenarios by adeptly handling various types of corruption in NLOS reconstruction tasks, including different noise levels, multiple blur kernels, and variations in temporal resolution. The code will be made available.

Dual-branch Graph Feature Learning for NLOS Imaging

The rapid development of large language models (LLMs) has significantly advanced code completion capabilities, giving rise to a new generation of LLM-based Code Completion Tools (LCCTs). Unlike general-purpose LLMs, these tools possess unique workflows, integrating multiple information sources as input and prioritizing code suggestions over natural language interaction, which introduces distinct security challenges. Additionally, LCCTs often rely on proprietary code datasets for training, raising concerns about the potential exposure of sensitive data. This paper exploits these distinct characteristics of LCCTs to develop targeted attack methodologies on two critical security risks: jailbreaking and training data extraction attacks. Our experimental results expose significant vulnerabilities within LCCTs, including a 99.4% success rate in jailbreaking attacks on GitHub Copilot and a 46.3% success rate on Amazon Q. Furthermore, We successfully extracted sensitive user data from GitHub Copilot, including 54 real email addresses and 314 physical addresses associated with GitHub usernames. Our study also demonstrates that these code-based attack methods are effective against general-purpose LLMs, such as the GPT series, highlighting a broader security misalignment in the handling of code by modern LLMs. These findings underscore critical security challenges associated with LCCTs and suggest essential directions for strengthening their security frameworks. The code and attack samples from our research are provided in the appendix.
Disclaimer. This paper contains examples of harmful language. Reader discretion is recommended.

Security Attacks on LLM-based Code Completion Tools

Pansharpening aims to combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. Although pansharpening in the frequency domain offers clear advantages, most existing methods either continue to operate solely in the spatial domain or fail to fully exploit the benefits of the frequency domain. To address this issue, we innovatively propose Multi-Frequency Fusion Attention (MFFA), which leverages wavelet transforms to cleanly separate frequencies and enable lossless reconstruction across different frequency domains. Then, we generated Frequency-Query, Spatial-Key, and Fusion-Value based on the physical meanings represented by different features, which enables more effective capture of specific information in the frequency domain. Additionally, we focus on the preservation of frequency features across different operations. On a broader level, our network employs a wavelet pyramid to progressively fuse information across multiple scales. Compared to previous frequency domain approaches, our network better prevents confusion and loss of different frequency features during the fusion process. Quantitative and qualitative experiments on multiple datasets demonstrate that our method outperforms existing approaches and shows significant generalization capabilities for real-world scenarios. Code will be provided after acceptance.

Premium content

Next from AAAI 2025

Improving Retrieval Augmented Language Model with Self-Reasoning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES