AAAI 2025 Papers

With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modules to these two modalities, we investigate whether the frozen model can be fine-tuned by customized noise. Our approach is motivated by the scientific study of beneficial noise, namely Positive-incentive Noise (Pi-noise) , which quantitatively analyzes the impact of noise. It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models. Focusing on few-shot classification tasks based on CLIP, we reformulate the inference process of CLIP and apply variational inference, demonstrating how to generate Pi-noise towards visual and linguistic modalities. Then, we propose Positive-incentive Noise Injector (PiNI), which can fine-tune CLIP via injecting noise into both visual and text encoders. Since the proposed method can learn the distribution of beneficial noise, we can obtain more diverse embeddings of vision and language to better align these two modalities for specific downstream tasks within limited computational resources. We evaluate different noise incorporation approaches and network architectures of PiNI. The evaluation across 11 datasets demonstrates its effectiveness.

Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric alignment method leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation, thereby enabling downstream models to effectively interpret various modal inputs. This study evaluates the quality and robustness of multimodal representations in the face of noise imperfections, dynamic input order permutations, and missing modalities, revealing that current text-centric alignment methods can compromise downstream robustness. To address this issue, we propose a new text-centric adversarial training approach that significantly enhances robustness compared to traditional robust training methods and pre-trained multimodal foundation models. Our findings underscore the potential of this approach to improve the robustness and adaptability of multimodal representations, offering a promising solution for dynamic and real-world applications.

The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially when dealing with arbitrary objects and complex scenes. Existing methods usually mistakes mask as the object shape prior, which struggle to achieve a seamless integration result. The mostly used inversion noise initialization also hinders the identity consistency towards the target object. To address these challenges, we propose a novel training-free framework that formulates personalized content editing as the optimization of edited images in the latent space, using diffusion models as the energy function guidance conditioned by reference text-image pairs. A coarse-to-fine strategy is proposed that employs text energy guidance at the early stage to achieve a natural transition toward the target class and uses point-to-point feature-level image energy guidance to perform fine-grained appearance alignment with the target object. Additionally, we introduce the latent space content composition to enhance overall identity consistency with the target. Extensive experiments demonstrate that our method excels in object replacement even with a large domain gap, highlighting its potential for high-quality, personalized image editing.

Temporal Action Localization (TAL) aims to accurately identify the start and end times of actions in untrimmed videos and classify them according to specific labels. However, the complexity and imbalance between target actions and background in video data make this task particularly challenging. Although relying on large amounts of finely annotated data has led to some progress in existing methods, the presence of noisy labels in large-scale annotations limits their application in open-world scenarios. To address this issue, we take the perspective of the data itself, modeling the different energy patterns exhibited by the action foreground and background in video data to enhance video content inference. Specifically, we propose the Energy-Driven Meta Purifier (EDMP) method, which utilizes a meta-learning training paradigm to avoid dependence on extensive and precise manual annotations. Under this pipeline, we use energy modeling to distinguish between different actions and backgrounds from the perspective of energy differences, thereby improving the model's robustness to category noise. Additionally, these energy-based distinctions are employed to further refine action boundaries, enhancing the model's robustness to boundary noise. Experiments on THUMOS14 and ActivityNet1.3 datasets show that EDMP effectively enhances the robustness of TAL models.

Cooperatively utilizing both ego-vehicle and infrastructure sensor data via V2X communication has emerged as a promising approach for advanced autonomous driving. However, current research mainly focuses on improving individual modules, rather than taking end-to-end learning to optimize final planning performance, resulting in underutilized data potential. In this paper, we introduce UniV2X, a pioneering cooperative autonomous driving framework that seamlessly integrates all key driving modules across diverse views into a unified network. We propose a sparse-dense hybrid data transmission and fusion mechanism for effective vehicle-infrastructure cooperation, offering three advantages: 1) Effective for simultaneously enhancing agent perception, online mapping, and occupancy prediction, ultimately improving planning performance. 2) Transmission-friendly for practical and limited communication conditions. 3) Reliable data fusion with interpretability of this hybrid data. We implement UniV2X, as well as reproducing several benchmark methods, on the challenging DAIR-V2X, the real-world cooperative driving dataset. Experimental results demonstrate the effectiveness of UniV2X in significantly enhancing planning performance, as well as all intermediate output performance.

Large Language Models (LLMs), when combined with agent mechanisms, show great promise in applications requiring robust planning ability, such as financial analysis and medical diagnostics. However, the increasingly complex reasoning structures designed to enhance the planning ability of language agents often exceed the processing and comprehension capabilities of LLMs, thereby limiting their effectiveness. To address these challenges, we introduce the Encoder of Thoughts (EoT), a novel reasoning structure modeling method based on graph neural networks. EoT processes the reasoning structures of planning methods through a plug-and-play structural encoder and aligns these structural information with the input space of LLMs, enabling seamless integration with existing language agents. Experiments on multi-step reasoning and plan generation demonstrate that EoT significantly improves the performance of language agents. Moreover, EoT demonstrated stable results when combined with different LLMs and planning algorithms, further underscoring its potential for broader application.

Point-based interactive colorization techniques allow users to effortlessly colorize grayscale images using user-provided color hints. However, point-based methods often face challenges when different colors are given to semantically similar areas, leading to color intermingling and unsatisfactory results—an issue we refer to as color collapse. The fundamental cause of color collapse is the inadequacy of points for defining the boundaries for each color. To mitigate color collapse, we introduce a lasso tool that can control the scope of each color hint. Additionally, we design a framework that leverages the user-provided lassos to localize the attention masks. The experimental results show that using a single lasso is as effective as applying 4.18 individual color hints and can achieve the desired outcomes in 30% less time than using points alone.

Self-learning of Large Language Models (LLMs) facilitates their advancement towards super-intelligence by training with self-synthesized experiences. However, a critical challenge is the amplification of hallucinations in generated data during iterative self-learning, underscoring the need for reliable data selection. To address this, we investigate the mechanism of Inner Knowledge Explicitation, which involves explicitly extracting the inner knowledge from memory of LLMs, to concurrently improves reasoning, and enables reliable self-learning data selection. This paper introduces a Self Knowledge Explicitation Learning (SKE-Learn) framework, which equips the LLMs with meta-skills to explicitly extract, verify and utilize inner knowledge for reasoning. By leveraging these meta-skills, SKE-Learn establishes a self-learning approach that ensures reliable selection of self-synthetic data. This approach enhances performance through iterative self-learning while mitigating the problem of hallucinations. Empirical results from six benchmarks demonstrate that Inner Knowledge Explicitation improves reasoning by serving as a more effective prompting method. Additionally, SKE-Learn, based on the verifiability of explicit knowledge, shows consistent performance improvements over multiple self-training iterations, with an average performance increase from 52.79% to 56.54% across all benchmarks. Furthermore, Inner Knowledge Explicitation provides explanation and intervention space during LLM's generation process.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video captioning datasets, their temporal understanding capacity in video-language tasks can be obtained. However, there is a notable lack of untrimmed audio-visual video datasets with precise temporal annotations for events. This deficiency hinders LLMs from learning the alignment between time, audio-visual events, and text tokens, thus impairing their ability to localize audio-visual events in videos temporally. To address this gap, we introduce PU-VALOR, a comprehensive audio-visual dataset comprising over 114,081 pseudo-untrimmed videos with detailed temporal annotations. PU-VALOR is derived from the large-scale but coarse-annotated audio-visual dataset VALOR, through a subtle method involving event-based video clustering, random temporal scaling, and permutation. By fine-tuning a multimodal LLM on PU-VALOR, we developed AVicuna, a model capable of aligning audio-visual events with temporal intervals and corresponding text tokens. AVicuna excels in temporal localization and time-aware dialogue capabilities. Our experiments demonstrate that AVicuna effectively handles temporal understanding in audio-visual videos and achieves state-of-the-art performance on open-ended video QA, audio-visual QA, and audio-visual event dense localization tasks.

This paper examines the co-design process for a foundational AI microcredential course targeting K-12 teachers' knowledge, agency, and effectiveness in integrating AI into their classrooms. We collaborated with six K-12 teachers and instructional coaches to ensure the course's relevance and practicality. Using conjecture mapping and memoing, we systematically captured and analyzed insights from the collaborative process. These methods helped us pinpoint essential themes and requirements for effective professional development (PD) that meets the unique challenges and opportunities of teaching about and using AI in K-12 classrooms. Themes included concerns about in-class monitoring for unethical impacts of AI integration and the desire for empowerment in evaluating and selecting AI tools that they can best leverage to meet state and national standards. Educator requirements centered on the creation of quick, easily accessible, and asynchronous learning activities. In addition, educators requested just-in-time AI integration resources and learning opportunities that can be leveraged throughout the year, rather than being limited to PD sessions. This study contributes to AI education by providing a framework for designing teacher professional development programs that are responsive to the evolving educational landscape and the specific needs of K-12 teachers.

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC framework to generate precise speech of the target emotion. Traditional approaches control the intensity of an emotional state in the utterance via emotion class probabilities or intensity labels that often lead to inept style manipulations and degradations in quality. On the contrary, we aim to regulate emotion intensity using self-supervised learning-based feature representations and unsupervised directional latent vector modeling (DVM) in the emotional embedding space within a diffusion-based framework. These emotion embeddings can be modified based on the given target emotion intensity and the corresponding direction vector. Furthermore, the updated embeddings can be fused in the reverse diffusion process to generate the speech with the desired emotion and intensity. In summary, this paper aims to achieve high-quality emotional intensity regularization in the diffusion-based EVC framework, which is the first of its kind work. The effectiveness of the proposed method has been shown across state-of-the-art (SOTA) baselines in terms of subjective and objective evaluations for the English and Hindi languages.

Existing causal learning algorithms focus on micro-level causal discovery, confronting significant challenges in identifying the influence of macro systems, composed of micro-level variables, on other variables. This difficulty arises because the causal relationships in macro systems are often mediated through micro-level causal interactions, which can lead to erroneous causal discovery or omission when dispersed. To address this issue, we propose the Emergence-inspired Multi-granularity Causal learning (EMCausal) method. Inspired by the emerging phenomena of aggregating micro level variables into macro level representations, EMCausal introduces a progressive mapping encoder to simulate the process, thus capturing the causal relationships driven by these macro entities. Next, it introduces a causal consistency constraint to collaboratively reconstruct micro variables using macro-level representations, enabling the learning of a multi-granular causal structure. Experimental results on both synthetic and real datasets demonstrate that EMCausal can identify causal graphs under the influence of causal emergence, outperforming competitive baselines in term of accuracy and robustness.

Many manufacturing companies are facing an acute shortage of qualified workers. Deploying robotic cells is a potential solution to address this challenge. Historically robots have been deployed only in mass production applications in manufacturing. A large fraction of manufacturing is classified as high-mix manufacturing where a large variety of products are produced. Manually programming robots is not a viable solution in high-mix manufacturing applications. Robotic cells need to be powered by embodied AI to make them useful in high-mix manufacturing applications. This paper aims to build a bridge between smart manufacturing and AI communities to enable AI researchers to develop methods and tool that can be successfully deployed to realize smart robotic cells for high-mix manufacturing applications. This paper highlights key requirements for developing embodied AI for powering robotic cells for high-mix manufacturing applications. It also makes the case for approaches that combine model-based and data-driven methods to meet the needs of embodied AI in manufacturing applications and describes the role of generative AI approaches in smart manufacturing applications. Finally, it describes how AI can be used to enhance digital twins and augment human-machine interfaces in manufacturing applications.

Ceramic artworks with elegant patterns present enormous collectible value and profits. To claim the copyright, the builder usually pastes their conspicuous stamp on the bottom or side of the ceramic artworks, which inevitably affects the external image of the artwork. In addition, the stamp is weak in resisting forgery attacks due to its visible nature. To address the above issues, we propose in this paper a novel framework for embedding invisible watermarking into patterns of the ceramic artworks. In the framework, a template-based watermarking embedding scheme is designed to map the watermark to an invisible template, which is added to the ceramic pattern to create its watermarked version. A distortion layer is further proposed to model the distortion of ceramic patterns in the ceramic manufacturing process, where a color-halftoning and an adaptive brightness adjustment strategy are developed to counter the print and firing operations that introduce the most significant distortions. Finally, a deep decoder is learned to extract the watermarking from the distorted pattern. Various experiments have been conducted to demonstrate the advantage of our proposed method for protecting the copyright of the ceramic artworks, which provides reliable watermark extraction accuracy without the need for a conspicuous stamp.

Majority illusion is a phenomenon in social networks wherein the decision by the majority of the network is not the same as one's personal social circle's majority, leading to an incorrect perception of the majority in a large network. We present polynomial-time algorithms which completely eliminate majority illusion by altering as few connections in the network as possible. Eliminating majority illusion ensures each neighbourhood in the network has at least a 1/2-fraction of the majority winner. This result is surprising as partially eliminating majority illusion is NP-hard. We generalize the majority illusion problem to an arbitrary fraction p and show that the problem of ensuring all neighbourhoods in the network contain at least a p-fraction of nodes consistent with a given preference is NP-hard, for nearly all values of p.

Prompt optimization automatically refines prompting expressions, unlocking the full potential of LLMs in downstream tasks. However, current prompt optimization methods are costly to train and lack sufficient interpretability. This paper proposes enhancing LLMs' reasoning performance by eliciting their causal inference ability from prompting instructions to correct answers. Specifically, we introduce the Self-Causal Instruction Enhancement (SCIE) method, which enables LLMs to generate high-quality, low-quantity observational data, then estimates the causal effect based on these data, and ultimately generates instructions with the optimized causal effect. In SCIE, the instructions are treated as the treatment, and textual features are used to process natural language, establishing causal relationships through treatments between instructions and downstream tasks. Additionally, we propose applying Object-Relational (OR) principles, where the uncovered causal relationships are treated as the inheritable class across task objects, ensuring low-cost reusability. Extensive experiments demonstrate that our method effectively generates instructions that enhance reasoning performance with reduced training cost of prompts, leveraging interpretable textual features to provide actionable insights.

Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video. In this study, we propose a robust and practical VI framework that leverages a large generative model for reference generation in combination with an advanced pixel propagation algorithm. Powered by a strong generative model, our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts. For pixel propagation, we introduce a one-shot pixel pulling method that effectively avoids error accumulation from repeated sampling while maintaining sub-pixel precision. To evaluate various VI methods in realistic scenarios, we also propose a high-quality VI benchmark, HQVI, comprising carefully generated videos using alpha matte composition. On public benchmarks and the HQVI dataset, our method demonstrates significantly higher visual quality and metric scores compared to existing solutions. Furthermore, it can process high-resolution videos exceeding 2K resolution with ease, underscoring its superiority for real-world applications.

Single hyperspectral image super-resolution (single-HSI-SR) aims to improve the resolution of a single input low-resolution HSI. Due to the bottleneck of data scarcity, the development of single-HSI-SR lags far behind that of RGB natural images. In recent years, research on RGB SR has shown that models pre-trained on large-scale benchmark datasets can greatly improve performance on unseen data, which may stand as a remedy for HSI. But how can we transfer the pre-trained RGB model to HSI, to overcome the data-scarcity bottleneck? Because of the significant difference in the channels between the pre-trained RGB model and the HSI, the model cannot focus on the correlation along the spectral dimension, thus limiting its ability to utilize on HSI. Inspired by the HSI spatial-spectral decoupling, we propose a new framework that first fine-tunes the pre-trained model with the spatial components (known as eigenimages), and then infers on unseen HSI using an iterative spectral regularization (ISR) to maintain the spectral correlation. The advantages of our method lie in: 1) we effectively inject the spatial texture processing capabilities of the pre-trained RGB model into HSI while keeping spectral fidelity, 2) learning in the spectral-decorrelated domain can improve the generalizability to spectral-agnostic data, and 3) our inference in the eigenimage domain naturally exploits the spectral low-rank property of HSI, thereby reducing the complexity. This work bridges the gap between pre-trained RGB models and HSI via eigenimages, addressing the issue of limited HSI training data, hence the name EigenSR. Extensive experiments show that EigenSR outperforms the state-of-the-art (SOTA) methods in both spatial and spectral metrics.

Long-term series forecasting aims to predict future data over long horizons based on historical information. However, existing methods struggle to effectively utilize long lookback windows due to overfitting, computational resource constraints, or information extraction challenges, thereby limiting them to using limited lookback windows for predicting long-term future series. To address these issues, this paper introduces the Input Refinement and Prediction Auxiliary (IRPA) framework, a lightweight model consisting of four linear layers designed to extract key information from ultra-long lookback windows to enhance limited lookback windows and assist prediction processes. IRPA comprises an Input Refinement Module (IRM) and a Prediction Auxiliary Module (PAM), each constructed from two linear layer sub-modules. The IRM performs effective decomposition and patching of ultra-long series, refining seasonal and trend features to increase the information density in limited lookback windows and mitigate overfitting and parameter inflation. The PAM extracts historical similarities and seasonal patterns from ultra-long lookback windows to significantly improve prediction accuracy. IRPA substantially extends the utilization of lookback windows, offering a lightweight and efficient solution with broad applicability. Experimental results on eight datasets show IRPA reduces the Mean Squared Error (MSE) by an average of 16.1% for various models.