AAAI 2025 论文列表

Neural Radiance Fields (NeRF) have achieved huge success in effectively capturing and representing 3D objects and scenes. However, to establish an ubiquitous presence in everyday media formats, such as images and videos, we need to fulfill three key objectives: 1. fast encoding and decoding time, 2. compact model sizes, and 3. high-quality renderings. Despite recent advancements, a comprehensive algorithm that adequately addresses all objectives has yet to be fully realized. In this work, we present CodecNeRF, a neural codec for NeRF representations, consisting of an encoder and decoder architecture that can generate a NeRF representation in a single forward pass. Furthermore, inspired by the recent parameter-efficient finetuning approaches, we propose a finetuning method to efficiently adapt the generated NeRF representations to a new test instance, leading to high-quality image renderings and compact code sizes. The proposed CodecNeRF, a newly suggested encoding-decoding-finetuning pipeline for NeRF, achieved unprecedented compression performance of more than 100x and a remarkable reduction in encoding time while maintaining (or improving) the image quality on widely used 3D object datasets.

Recent advancements in audio generation have been significantly propelled by the capabilities of Large Language Models (LLMs). The existing research on audio LLM has primarily focused on enhancing the architecture and scale of audio language models, as well as leveraging larger datasets, and generally, acoustic codecs, such as EnCodec, are used for audio tokenization. However, these codecs were originally designed for audio compression, which may lead to suboptimal performance in the context of audio LLM. Our research aims to address the shortcomings of current audio LLM codecs, particularly their challenges in maintaining semantic integrity in generated audio. For instance, existing methods like VALL-E, which condition acoustic token generation on text transcriptions, often suffer from content inaccuracies and elevated word error rates (WER) due to semantic misinterpretations of acoustic tokens, resulting in word skipping and errors. To overcome these issues, we propose a straightforward yet effective approach called X-Codec. X-Codec incorporates semantic features from a pre-trained semantic encoder before the Residual Vector Quantization (RVQ) stage and introduces a semantic reconstruction loss after RVQ. By enhancing the semantic ability of the codec, X-Codec significantly reduces WER in speech synthesis tasks and extends these benefits to non-speech applications, including music and sound generation. Our experiments in text-to-speech, music continuation, and text-to-sound tasks demonstrate that integrating semantic information substantially improves the overall performance of language models in audio generation.

Large Language Models (LLMs) have made significant progress in code generation, offering developers groundbreaking automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible, but may not execute as expected or fulfill specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To advance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We categorize code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we present a dynamic detection algorithm called CodeHalu designed to detect and quantify code hallucinations. We also introduce the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks, to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs using this benchmark, we reveal significant differences in their accuracy and reliability in code generation, offering detailed insights for further improving the code generation capabilities of LLMs.

Code-switching is a linguistic phenomenon in which different languages are used interactively during conversation. It poses significant performance challenges to natural language processing (NLP) tasks due to the often monolingual nature of the underlying system. We focus on sentence-level semantic associations between the different code-switching expressions. And we propose an innovative task-free semantic learning method based on the semantic property. Specifically, there are many different ways of languages switching for a sentence with the same meaning. We refine this into a semantic computational method by designing the loss of semantic invariant constraint during the model optimization. In this work, we conduct thorough experiments on speech recognition, speech translation, and language modeling tasks. The experimental results fully demonstrate that the proposed method can widely improve the performance of code-switching related tasks.

In recent years, applying multi-modal large language models (MLLMs) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, MLLMs comprise the well-known Transformer network, which has a less efficient quadratic computation complexity. In this study, we introduce Cobra, a multi-modal large-scale language model built upon a state-space model, which has demonstrated significant potential in efficiently handling long sequences with fast inference and linear scalability concerning sequence length. Specifically, Cobra involves replacing Transformer-based backbone models (e.g., LLaMA or Phi) with pre-trained Mamba language models. We then empirically explore effective strategies for aligning visual and textual modalities and integrating various pre-trained Mamba model variants with visual encoders. Experiments across various multi-modal benchmarks demonstrate that: (i) Cobra performs 3× ∼ 4× faster than the most computationally efficient state-of-the-art methods, e.g., LLaVA-Phi and MobileVLM v2. Additionally, its performance is significantly enhanced thanks to the implementation of linear sequential modeling. (ii) Cobra fine-tunes a small parameter (∼48% of model parameters), leading to a significant improvement in overall performance compared to LLaVA.

Large Language Models (LLMs) offer groundbreaking advancements in recommender systems through superior text analysis and decision-making support. However, integrating LLMs into recommender systems still suffers from the problems of identifier uninterpretability and lack of transparency. To address these issues and fully leverage the capabilities of LLMs, we propose a chain of thought (CoT) based recommendation framework called CoT4Rec which employs LLMs as data enhancers for user preference analysis. Initially, we design a CoT reasoning strategy that can derive more behaviorally-aligned user preference features by clustering users’ historical interactions. Subsequently, we propose a two-stage recommendation model that not only makes full use of the world knowledge embedded in LLMs but also generates a logically transparent reasoning path. By integrating a user preference analyzer early in the recommendation pipeline, the model deeply analyzes users' historical interactions, helping to enhance the personalization and transparency of the recommender system. CoT4Rec demonstrates superior performance over existing state-of-the-art models in recommendation tasks across four public datasets, achieving improvements ranging from 2.2% to 12.2%.

Generative image watermarking inserts secret watermarks into generated images and plays an important role in tracing the usages of generative models. For watermarking of diffusion models, inversion-based framework emerges as an effective approach. Such framework employs a robust mechanism to embed the watermark into the starting latent before ``forward sampling'', thereby generating images with the implicit watermark. During watermark detection, inversion techniques are employed to reverse the process and obtain the watermarked latent, followed by further extraction. The robustness of this technique hinges primarily on the embedding mechanism and inversion accuracy. Previous methods predominantly focused on enhancing the robustness of the embedding mechanism but overlooked the reduction of the inversion errors. However, our results show that inversion error will significantly affect the overall robustness. Therefore, in this paper, we delve into the inversion error aspect and propose CoSDA, a compensation sampling and drift alignment-based approach. The inversion error primarily accumulated during two stages: the internal error incurred by the algorithm, and the inevitable external noise. We observe that the main source of internal error comes from the mismatch in conditions (e.g. prompt, guidance scale) between forward and backward sampling processes. Therefore, we propose a compensation-based forward sampling, compensating for certain mismatch conditions and reducing the inversion error caused by the mismatch. Addressing external error caused by inevitable image distortions (e.g. JPEG compression), we introduce a drift-alignment approach, where a neural network is trained adversarially to restore the original watermarked latent from the distorted counterpart. Experimental results show that CoSDA effectively enhances watermark robustness while maintaining the visual quality of generated images.

Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our approach is based on the fact that generating prompt-aligned images requires a precise semantic understanding of the prompt, which involves accurately processing the interactions between the new concept and its surrounding context tokens within the CLIP text encoder. To address this, we aim to embed the new concept properly into the input embedding space of the text encoder, allowing for seamless integration with existing tokens. We introduce Context Regularization (CoRe), which enhances the learning of the new concept's text embedding by regularizing its context tokens in the prompt. This is based on the insight that appropriate output vectors of the text encoder for the context tokens can only be achieved if the new concept's text embedding is correctly learned. CoRe can be applied to arbitrary prompts without requiring the generation of corresponding images, thus improving the generalization of the learned text embedding. Additionally, CoRe can serve as a test-time optimization technique to further enhance the generations for specific prompts. Comprehensive experiments demonstrate that our method outperforms several baseline methods in both identity preservation and text alignment.

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation data can undermine its inherent world knowledge and fundamental competencies, which are crucial for interpreting and inferring recommendation text. (2) Incorporating collaborative features into textual prompts disrupts the semantics of the original prompts, preventing LLM from generating appropriate outputs. In this paper, we propose a new paradigm, Collaborative LoRA (CoRA), with a collaborative query generator. Rather than input space alignment, this method aligns collaborative information with LLM's parameter space, representing them as incremental weights to update LLM's output. This way, LLM perceives collaborative information without altering its general knowledge and text inference capabilities. Specifically, we employ a collaborative filtering model to extract user and item embeddings and inject them into a set number of learnable queries. We then convert collaborative queries into collaborative weights with low-rank properties and merge the collaborative weights into LLM's weights, enabling LLM to perceive the collaborative signals and generate personalized recommendations without fine-tuning or extra collaborative tokens in prompts. Extensive experiments confirm that CoRA effectively integrates collaborative information into LLM, enhancing recommendation performance.

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

Multi-agent collaborative perception is expected to significantly improve perception performance by overcoming the limitations of single-agent perception through exchanging complementary information. However, training a robust collaborative perception model requires collecting sufficient training data that covers all possible collaboration scenarios, which is impractical due to intolerable deployment costs. Hence, the trained model is not robust against new traffic scenarios with inconsistent data distribution and fundamentally restricts its real-world applicability. Further, existing methods, such as domain adaptation, have mitigated this issue by exposing the deployment data during the training stage but incur a high training cost, which is infeasible for resource-constrained agents. In this paper, we propose a Parameter-Efficient Fine-Tuning-based lightweight framework, CoPEFT, for fast adapting a trained collaborative perception model to new deployment environments under low-cost conditions. CoPEFT develops a Collaboration Adapter and Agent Prompt to perform macro-level and micro-level adaptations separately. Specifically, the Collaboration Adapter utilizes the inherent knowledge from training data and limited deployment data to adapt the feature map to new data distribution. The Agent Prompt further enhances the Collaboration Adapter by inserting fine-grained contextual information about the environment. Extensive experiments demonstrate that our CoPEFT surpasses existing methods with less than 1\% trainable parameters, proving the effectiveness and efficiency of our proposed method.

Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and multi-modal reasoning output, aiming to mimic human-like reasoning that inherently integrates visual operation. Specifically, CoMT consists of four categories: (1) Visual Creation, (2) Visual Deletion, (3) Visual Update, and (4) Visual Selection to comprehensively explore complex visual operations and concise expression in real scenarios. We evaluate various LVLMs and strategies on CoMT, revealing some key insights into the capabilities and limitations of the current approaches. We hope that CoMT can inspire more research on introducing multi-modal generation into the reasoning process.

Sequential recommendation systems aim to predict the next item based on users' historical interactions. While traditional methods focus on learning feature representations or user preferences, they often struggle with detecting subtle demand shifts in short sequences, especially when these shifts are obscured by noise or biases. To address these issues, we propose CoDeR (Counterfactual Demand Reasoning), a novel framework designed to handle demand shifts in sequential recommendations with greater precision. CoDeR features two key modules: (1) the User Demand Extraction module, which utilizes self-attention mechanisms and demand graphs to identify and model demand shifts from minimal user interactions; and (2) the Counterfactual Demand Reasoning module, which employs causal effect analysis and backdoor adjustment techniques to distinguish true demand shifts from noisy or biased signals. Our approach represents the first application of counterfactual reasoning to sequential recommendation systems. Comprehensive experiments on three real-world datasets demonstrate that CoDeR significantly outperforms existing baselines.

Communication has been widely employed to enhance multi-agent collaboration. Previous research has typically assumed delay-free communication, a strong assumption that is challenging to meet in practice. However, real-world agents suffer from channel delays, receiving messages sent at different time points, termed Asynchronous Communication, leading to cognitive biases and breakdowns in collaboration. This paper first defines two communication delay settings in MARL and emphasizes their harm to collaboration. To handle the above delays, this paper proposes a novel framework, Communication Delay-Tolerant Multi-Agent Collaboration (CoDe). At first, CoDe learns an intent representation as messages through future action inference, reflecting the stable future behavioral trends of the agents. Then, CoDe devises a dual alignment mechanism of intent and timeliness to strengthen the fusion process of asynchronous messages. In this way, agents can extract the long-term intent of others, even from delayed messages, and selectively utilize the most recent messages that are relevant to their intent. Experimental results demonstrate that CoDe outperforms baseline algorithms in three MARL benchmarks without delay and exhibits robustness under fixed and time-varying delays.

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate pseudo labels for the missing instances. However, these methods fail to achieve an optimal confidence threshold that harmonizes the quality and quantity of pseudo labels. To address this issue, we propose an end-to-end Collaborative perception Dual Teacher-Student framework (CoDTS), which employs adaptive complementary learning to produce both high-quality and high-quantity pseudo labels. Specifically, the Main Foreground Mining (MFM) module generates high-quality pseudo labels based on the prediction of the static teacher. Subsequently, the Supplement Foreground Mining (SFM) module ensures a balance between the quality and quantity of pseudo labels by adaptively identifying missing instances based on the prediction of the dynamic teacher. Additionally, the Neighbor Anchor Sampling (NAS) module is incorporated to enhance the representation of pseudo labels. To promote the adaptive complementary learning, we implement a staged training strategy that trains the student and dynamic teacher in a mutually beneficial manner. Extensive experiments demonstrate that the CoDTS effectively ensures an optimal balance of pseudo labels in both quality and quantity, establishing a new state-of-the-art in sparsely supervised collaborative perception.

Video inpainting is a crucial task with diverse applications, including fine-grained video editing, video recovery, and video dewatermarking. However, most existing video inpainting methods primarily focus on visual content completion while neglecting text information. There are only a limited number of text-guided video inpainting techniques, and these techniques struggle with maintaining visual quality and exhibit poor semantic representation capabilities. In this paper, we introduce CoCoCo, a text-guided video inpainting diffusion framework. To address the aforementioned challenges, we enhance both the training data and model structure. Specifically, we devise an instance-aware region selection strategy for masked area sampling and develop a novel motion block that incorporates efficient 3D full attention and textual cross attention. Additionally, our CoCoCo framework can be seamlessly integrated with various personalized text-to-image diffusion models through a delicate training-free transfer mechanism. Comprehensive experiments demonstrate that CoCoCo can create high-quality visual content with enhanced temporal consistency, improved text controllability, and better compatibility with personalized image models.

Unsupervised anomaly detection has emerged as a powerful technique for identifying abnormal patterns in images without relying on pre-labeled defective samples. Many unsupervised methods use pre-trained feature extractors from large datasets, with knowledge distillation between teacher and student models being a leading technique. However, due to the similar structures of teacher and student, these methods face challenges like excessive specialization and inadequate generalization, reducing detection performance. In this paper, we introduce a Co-Progression Knowledge Distillation (CPKD) framework, enabling bidirectional learning between teacher and student models. This innovative framework enables concurrent evolution of both models, fostering mutual improvement and enhanced adaptability. To maintain system stability and prevent overspecialization, we introduce a knowledge prototype as a regulatory mechanism for the teacher's learning process. Our method effectively addresses key challenges in anomaly detection, including insufficient learning and overadaptation, by striking a balance between acquiring new knowledge and preserving core competencies. We demonstrate significant improvements in detection accuracy, achieving SOTA performance on the MVTec dataset.

Federated Learning (FL) has pioneered the idea of "share wisdom not raw data" to enable collaborative learning over decentralized data. FL achieves this goal by averaging model parameters instead of centralizing data. However, representing "wisdom" in the form of model parameters has its own limitations including the requirement for uniform model architectures across clients and communication overhead proportional to model size. In this work we introduce Co-Dream a framework for representing "wisdom" in data space instead of model parameters. Here, clients collaboratively optimize random inputs based on their locally trained models and aggregate gradients of their inputs. Our proposed approach overcomes the aforementioned limitations and comes with additional benefits such as adaptive optimization and interpretable representation of knowledge. We empirically demonstrate the effectiveness of Co-Dream and compare its performance with existing techniques.

Spectral clustering requires the time-consuming decomposition of the Laplacian matrix of the similarity graph, thus limiting its applicability to large datasets. To improve the efficiency of spectral clustering, a top-down approach was recently proposed, which first divides the data into several micro-clusters (granular-balls), then splits these micro-clusters when they are not ``compact'', and finally uses these micro-clusters as nodes to construct a similarity graph for more efficient spectral clustering. However, this top-down approach is challenging to adapt to unevenly distributed or structurally complex data. This is because constructing micro-clusters as a rough ball struggles to capture the shape and structure of data in a local range, and the simplistic splitting rule that solely targets ``compactness'' is susceptible to noise and variations in data density and leads to micro-clusters with varying shapes, making it challenging to accurately measure the similarity between them. To resolve these issues and improve spectral clustering, this paper first proposes to start from local structures to obtain micro-clusters, such that the complex structural information inside local neighborhoods is well captured by them. Moreover, by noting that Euclidean distance is more suitable for convex sets, this paper further proposes a data splitting rule that couples local density and data manifold structures, so that the similarities of the obtained micro-clusters can be easily characterized. A novel similarity measure between micro-clusters is then proposed for the final spectral clustering. A series of experiments based on synthetic and real-world datasets demonstrate that the proposed method has better adaptability to structurally complex data than granular-ball based methods.