AAAI 2025 Papers

Lyric-to-melody generation is a highly challenging task in the field of AI music generation. Due to the difficulty of learning strict yet weak correlations between lyrics and melodies, previous methods have suffered from weak controllability, low-quality and poorly structured generation. To address these challenges, we propose CSL-L2M, a controllable song-level lyric-to-melody generation method based on an in-attention Transformer decoder with fine-grained lyric and musical controls, which is able to generate full-song melodies matched with the given lyrics and user-specified musical attributes. Specifically, we first introduce REMI-Aligned, a novel music representation that incorporates strict syllable- and sentence-level alignments between lyrics and melodies, facilitating precise alignment modeling. Subsequently, sentence-level semantic lyric embeddings independently extracted from a sentence-wise Transformer encoder are combined with word-level part-of-speech embeddings and syllable-level tone embeddings as fine-grained controls to enhance the controllability of lyrics over melody generation. Then we introduce human-labeled musical tags, sentence-level statistical musical attributes, and learned musical features extracted from a pre-trained VQ-VAE as coarse-grained, fine-grained and high-fidelity controls, respectively, to the generation process, thereby enabling user control over melody generation. Finally, an in-attention Transformer decoder technique is leveraged to exert fine-grained control over the full-song melody generation with the aforementioned lyric and musical conditions. Experimental results demonstrate that our proposed CSL-L2M outperforms the state-of-the-art models, generating melodies with higher quality, better controllability and enhanced structure.

Authorship models have historically generalized poorly to new domains because of the wide distribution of author-identifying signals across domains. In particular, the effects of topic and genre are highly domain-dependent and impact authorship analysis performance greatly. This paper addresses the existing data gap in authorship for these resources by introducing CROSSNEWS, a novel cross-genre dataset that connects formal journalistic articles and casual social media posts. CROSSNEWS is the largest authorship dataset of its kind for supporting both verification and attribution tasks, with comprehensive topic and genre annotations. We use CROSSNEWS to demonstrate that current models exhibit poor performance in genre transfer scenarios, underscoring the need for authorship models robust to genre-specific effects. We also explore SELMA, a new LLM embedding approach for large-scale authorship setups that outperforms existing models in both same-genre and cross-genre settings.

Event-based cameras feature high temporal resolution, wide dynamic range, and low power consumption, which are ideal for high-speed and low-light object detection. Spiking neural networks (SNNs) are promising for event-based object recognition and detection due to their spiking nature but lack efficient training methods, leading to gradient vanishing and high computational complexity, especially in deep SNNs. Additionally, existing SNN frameworks often fail to effectively handle multi-scale spatiotemporal features, leading to increased data redundancy and reduced accuracy. To address these issues, we propose CREST, a novel conjointly trained spike-driven framework to exploit spatiotemporal dynamics in event-based object detection. We introduce the conjoint learning rule to accelerate SNN learning and alleviate gradient vanishing. It also supports dual operation modes for efficient and flexible implementation on different hardware types. Additionally, CREST features a fully spike driven framework with a multi-scale spatiotemporal event integrator (MESTOR) and a spatiotemporal-IoU (ST-IoU) loss. Our approach achieves superior object recognition & detection performance and energy efficiency compared with state of-the-art SNN algorithms on three datasets, providing an efficient solution for event-based object detection algorithms suitable for SNN hardware implementation.

Collaborative Perception (CP) has shown a promising technique for autonomous driving, where multiple connected and autonomous vehicles (CAVs) share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, ego CAV needs to receive messages from the collaborators, which makes it easy to be attacked by malicious agents. For example, a malicious agent can send harmful information to the ego CAV to mislead it. To address this critical issue, we propose a novel method, **CP-Guard**, a tailored defense mechanism for CP that can be deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is that CP will lead to a consensus rather than a conflict against the ego CAV's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method that can effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we design a collaborative consistency loss (CCLoss) to calculate the discrepancy between the ego CAV and the collaborators, which is used as a verification criterion for consensus. Finally, we conduct extensive experiments in collaborative bird's eye view (BEV) tasks and the results demonstrate the effectiveness of our CP-Guard.

Recent research on universal object detection aims to introduce language in a SoTA closed-set detector and then generalize the open-set concepts by constructing large-scale (text-region) datasets for training. However, these methods face two main challenges: (i) how to efficiently use the prior information in the prompts to genericise objects and (ii) how to reduce alignment bias in the downstream tasks, both leading to sub-optimal performance in some scenarios beyond pre-training. To address these challenges, we propose a strong universal detection foundation model called CP-DETR, which is competitive in almost all scenarios, with only one pre-training weight. Specifically, we design an efficient prompt visual hybrid encoder that enhances the information interaction between prompt and visual through scale-by-scale and multi-scale fusion modules. Then, the hybrid encoder is facilitated to fully utilize the prompted information by prompt multi-label loss and auxiliary detection head. In addition to text prompts, we have designed two practical concept prompt generation methods, visual prompt and optimized prompt, to extract abstract concepts through concrete visual examples and stably reduce alignment bias in downstream tasks. With these effective designs, CP-DETR demonstrates superior universal detection performance in a broad spectrum of scenarios. For example, our Swin-T backbone model achieves 47.6 zero-shot AP on LVIS, and the Swin-L backbone model achieves 32.2 zero-shot AP on ODinW35. Furthermore, our visual prompt generation method achieves 68.4 AP on COCO val by interactive detection, and the optimized prompt achieves 73.1 fully-shot AP on ODinW13.

Early exiting is an effective paradigm for improving the inference efficiency of pre-trained language models (PLMs) by dynamically adjusting the number of executed layers for each sample. However, in most existing works, easy and hard samples are treated equally by each classifier during training, which neglects the test-time early exiting behavior, leading to inconsistency between training and testing. Although some methods have tackled this issue under a fixed speed-up ratio, the challenge of flexibly adjusting the speed-up ratio while maintaining consistency between training and testing is still under-explored. To bridge the gap, we propose a novel Consistency-Oriented Signal-based Early Exiting (COSEE) framework, which leverages a calibrated sample weighting mechanism to enable each classifier to emphasize the samples that are more likely to exit at that classifier under various acceleration scenarios. Extensive experiments on the GLUE benchmark demonstrate the effectiveness of our COSEE across multiple exiting signals and backbones, yielding a better trade-off between performance and efficiency.

Multi-sensor fusion systems (MSFs) play a vital role as the perception module in modern autonomous vehicles (AVs). Therefore, ensuring their robustness against common and realistic adversarial semantic transformations, such as rotation and shifting in the physical world, is crucial for the safety of AVs. While empirical evidence suggests that MSFs exhibit improved robustness compared to single-modal models, they are still vulnerable to adversarial semantic transformations. In addition, although many empirical defenses have been proposed, several works show that these defenses can be further attacked by new adaptive attacks. So far, there is no certified defense proposed for MSFs. In this work, we propose the first robustness certification framework COMMIT to certify the robustness of multi-sensor fusion systems against semantic attacks. In particular, we propose a practical anisotropic noise mechanism that leverages randomized smoothing on multi-modal data and performs a grid-based splitting method to characterize complex semantic transformations. We also propose efficient algorithms to compute the certification in terms of object detection accuracy and IoU for large-scale MSF models. Empirically, we evaluate the efficacy of COMMIT in different settings and provide a comprehensive benchmark of certified robustness for different MSF models using the CARLA simulation platform. We show that the certification for MSF models is at most 48.39% higher than that of single-modal models, which validates the advantages of MSF models. We believe our certification framework and benchmark will contribute an important step towards certifiably robust AVs in practice.

Document-level relation extraction (DocRE) is the process of identifying and extracting relations between entities that span multiple sentences within a document. Due to its realistic settings, DocRE has garnered increasing research attention in recent years. Previous research has mostly focused on developing sophisticated encoding models to better capture the intricate patterns between entity pairs. While these advancements are undoubtedly crucial, an even more foundational challenge lies in the data itself. The complexity inherent in DocRE makes the labeling process prone to errors, compounded by the extreme sparsity of positive relation samples, which is driven by both the limited availability of positive instances and the broad diversity of positive relation types. These factors can lead to biased optimization processes, further complicating the task of accurate relation extraction. Recognizing these challenges, we have developed a robust framework called COMM to better solve DocRE. COMM operates by initially employing an instance-aware reasoning method to dynamically capture pertinent information of entity pairs within the document and extract relational features. Following this, COMM takes into account the distribution of relations and the difficulty of samples to dynamically adjust the margins between prediction logits and the decision threshold, a process we call Concentrated Margin Maximization. In this way, COMM not only enhances the extraction of relevant relational features but also boosts DocRE performance by addressing the specific challenges posed by the data. Extensive experiments and analysis demonstrate the versatility and effectiveness of COMM, especially its robustness when trained on low-quality data (achieves >10% performance gains).

While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI and has not been used to test visual perception systems. To bridge this gap, we formulate visual lateral thinking as a multiple-choice question-answering task and describe a three-step taxonomy-driven methodology for instantiating task examples. Then, we develop COLUMBUS, a synthetic benchmark that applies the task pipeline to create QA sets with text and icon rebus puzzles based on publicly available collections of compounds and common phrases. COLUMBUS comprises over 1,000 puzzles, each with four answer candidates. While the SotA vision language models (VLMs) achieve decent performance, our evaluation demonstrates a substantial gap between humans and models. VLMs benefit from human-curated descriptions but struggle to self-generate such representations at the right level of abstraction.

Conditioning image generation facilitates seamless editing and the creation of photorealistic images. However, conditioning on noisy or Out-of-Distribution (OoD) images poses significant challenges, particularly in balancing fidelity to the input and realism of the output. We introduce Confident Ordinary Differential Editing (CODE), a novel approach for image synthesis that effectively handles OoD guidance images. Utilizing a diffusion model as a generative prior, CODE enhances images through score-based updates along the probability-flow Ordinary Differential Equation (ODE) trajectory. This method requires no task-specific training, handcrafted modules, or assumptions, and is compatible with any diffusion model. Positioned at the intersection of conditional image generation and blind image restoration, CODE operates in a fully blind manner, relying solely on a pre-trained generative model. Our method introduces an alternative approach to blind restoration: instead of targeting a specific ground truth image based on assumptions about the underlying corruption, CODE aims to increase the likelihood of the input image while maintaining fidelity. This results in the most probable in-distribution image around the input. Our contributions are twofold. First, CODE introduces a novel editing method based on ODE providing enhanced control, realism, and fidelity compared to SDE-based counterpart. Second, we introduce a confidence interval-based clipping method, which improves CODE’s effectiveness by allowing it to disregard certain pixels or information, thus enhancing the restoration process in a blind manner. Experimental results demonstrate CODE’s effectiveness over existing methods, particularly in scenarios involving severe degradation or OoD inputs.

Existing unsupervised distillation-based methods rely on the differences between encoded and decoded features to locate abnormal regions in test images. However, the decoder trained only on normal samples still reconstructs abnormal patch features well, degrading performance. This issue is particularly pronounced in unsupervised multi-class anomaly detection tasks. We attribute this behavior to ‘over-generalization’ (OG) of decoder: the significantly increasing diversity of patch patterns in multi-class training enhances the model generalization on normal patches, but also inadvertently broadens its generalization to abnormal patches. To mitigate ‘OG’, we propose a novel approach that leverages class-agnostic learnable prompts to capture common textual normality across various visual patterns, and then apply them to guide the decoded features towards a ‘normal’ textual representation, suppressing ‘over-generalization’ of the decoder on abnormal patterns. To further improve performance, we also introduce a gated mixture-of-experts module to specialize in handling diverse patch patterns and reduce mutual interference between them in multi-class training. Our method achieves competitive performance on the MVTec AD and VisA datasets, demonstrating its effectiveness.

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However, updates are necessary to keep them in sync with rapidly evolving human knowledge. To address these challenges, this paper proposes the Compression Memory Training (CMT) method, an efficient and effective online adaptation framework for LLMs that features robust knowledge retention capabilities. Inspired by human memory mechanisms, CMT compresses and extracts information from new documents to be stored in a memory bank. When answering to queries related to these new documents, the model aggregates these document memories from the memory bank to better answer user questions. The parameters of the LLM itself do not change during training and inference, reducing the risk of catastrophic forgetting. To enhance the encoding, retrieval, and aggregation of memory, we further propose three new general and flexible techniques, including memory-aware objective, self-matching and top-k aggregation. Extensive experiments conducted on three continual learning datasets (i.e., StreamingQA, SQuAD and ArchivalQA) demonstrate that the proposed method improves model adaptability and robustness across multiple base LLMs (e.g., +4.07 EM & +4.19 F1 in StreamingQA with Llama-2-7b).

Large Language Models (LLMs) have shown great promise in vulnerability identification. As C/C++ comprise half of the open-source Software (OSS) vulnerabilities over the past decade and updates in OSS mainly occur through commits, enhancing LLMs' ability to identify C/C++ Vulnerability-Contributing Commits (VCCs) is essential. However, current studies primarily focus on further pre-training LLMs on massive code datasets, which is resource-intensive and poses efficiency challenges. In this paper, we enhance the ability of BERT-based LLMs to identify C/C++ VCCs in a lightweight manner. We propose CodeLinguaNexus (CLNX) as a bridge facilitating communication between C/C++ programs and LLMs. Based on commits, CLNX efficiently converts the source code into a more natural representation while preserving key details. Specifically, CLNX first applies Structure-level Naturalization to decompose complex programs, followed by Token-level Naturalization to interpret complex symbols. We evaluate CLNX on public datasets of 25,872 C/C++ functions with their commits. The results demonstrate that CLNX substantially improves the ability of LLMs to detect C/C++ VCCs. Moreover, CLNX-equipped CodeBERT achieves new state-of-the-art performance and identifies 38 OSS vulnerabilities in the real world.

With the emergence of vision-language pre-trained models, such as CLIP, some textual prompts have been gradually introduced recently into re-identification (Re-ID) tasks to obtain considerably robust multimodal information. However, most textual descriptions based on vehicle Re-ID tasks only contain identity index words without specific words to describe vehicle view information, thereby resulting in difficulty to be widely applied in vehicle Re-ID tasks with view variations. This case inspires us to propose a CLIP-driven view-aware prompt learning framework for unsupervised vehicle Re-ID. We first design a learnable textual prompt template called view-aware context optimization (ViewCoOp) based on dynamic multi-view word embeddings, which can fully obtain the proportion and position encoding of each view in the whole vehicle body region. Subsequently, a cross-modal mutual graph is constructed to explore the connections between inter-modal and intra-modal. Each sample is treated as a graph node, which extracts textual features based on ViewCoOp and the visual features of images. Moreover, leveraging the inter-cluster and intra-cluster correlation in the bimodal clustering results in the determination of connectivity between graph node pairs. Lastly, the proposed cross-modal mutual graph method utilizes supervised information from the bimodal gap to directly fine-tune the image encoder of CLIP for downstream unsupervised vehicle Re-ID tasks. Extensive experiments verify that the proposed method is capable of effectively obtaining cross-modal description ability from multiple views.

Exposure correction aims to adjust the exposure of an under- and over-exposed image to enhance its overall visual quality. The core challenge of this task lies in that it requires to faithfully restore both the structure and perception information. In this work, we present a novel exposure correction method, referred to as CLIP-RestoreX, that leverages structural and perceptual priors from CLIP to tackle exposure correction. Specifically, we in CLIP-RestoreX propose to perform exposure correction by aligning CLIP-based structural and perceptual feature of the impaired image with its ground-truth image. To better restore the damaged structural information and perceptual information, we further design a frequency-domain based feature enhancement diffusion model, where we utilize the globality of Fourier transform to help reveal potential the relationship within the features. We conduct extensive experiments on several benchmark datasets. The results demonstrate that the proposed CLIP-RestoreX outperforms state-of-the-art exposure correction methods.

In recent years, No-Reference Point Cloud Quality Assessment (NR-PCQA) research has achieved significant progress. However, existing methods mostly seek a direct mapping function from visual data to the Mean Opinion Score (MOS), which is contradictory to the mechanism of practical subjective evaluation. To address this, we propose a novel language-driven PCQA method named CLIP-PCQA. Considering that human beings prefer to describe visual quality using discrete quality descriptions (e.g., "excellent" and "poor") rather than specific scores, we adopt a retrieval-based mapping strategy to simulate the process of subjective assessment. More specifically, based on the philosophy of CLIP, we calculate the cosine similarity between the visual features and multiple textual features corresponding to different quality descriptions, in which process an effective contrastive loss and learnable prompts are introduced to enhance the feature extraction. Meanwhile, given the personal limitations and bias in subjective experiments, we further covert the feature similarities into probabilities and consider the Opinion Score Distribution (OSD) rather than a single MOS as the final target. Experimental results show that our CLIP-PCQA outperforms other State-Of-The-Art (SOTA) approaches.

Prior work employing deep neural networks (DNNs) with explainable techniques has identified human visual cortical selective representation to specific categories. However, constructing high-performing encoding models that accurately capture brain responses to coexisting multi-semantics remains elusive. Here, we used CLIP models combined with CLIP Dissection to establish a multi-semantic mapping framework (CLIP-MSM) for hypothesis-free analysis in human high-level visual cortex. First, we utilize CLIP models to construct voxel-wise encoding models for predicting visual cortical responses to natural scene images. Then, we apply CLIP Dissection and normalize the semantic mapping score to achieve the mapping of single brain voxels to multiple semantics. Our findings indicate that CLIP Dissection applied to DNNs modeling the human high-level visual cortex demonstrates better interpretability accuracy compared to Network Dissection. In addition, to demonstrate how our method enables fine-grained discovery in hypothesis-free analysis, we quantify the accuracy between CLIP-MSM’s reconstructed brain activation in response to categories of faces, bodies, places, words and food, and the ground truth of brain activation. We demonstrate that CLIP-MSM provides more accurate predictions of visual responses compared to CLIP Dissection. Our results have been validated using two large natural image datasets: the Natural Scenes Dataset (NSD) and the Natural Object Dataset (NOD).

Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. Although knowledge distillation has been widely applied in single modality models, how to efficiently expand knowledge distillation to vision-language foundation models with extensive data remains relatively unexplored. In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a large vision-language foundation model to a smaller model. We initially propose a simple but efficient image semantic balance method to reduce transfer learning bias and improve distillation efficiency. This method filters out 43.7% of image-text pairs from the LAION400M while maintaining superior performance. After that, we leverage cluster-instance discrimination to facilitate knowledge transfer from the teacher model to the student model, thereby empowering the student model to acquire a holistic semantic comprehension of the pre-training data. Experimental results demonstrate that CLIP-CID achieves state-of-the-art performance on various downstream tasks including linear probe and zero-shot classification.

Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP's knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our proposed method outperforms other state-of-the-art methods on both image and video person ReID benchmarks.