AAAI 2025 论文列表

Batch Bayesian Optimisation (BBO) has emerged as a potent approach for optimising expensive black-box functions. Central to BBO is the issue of selecting a number of solutions at the same time through a batch method, in the hope for them to represent good, yet different, trade-offs between exploitation and exploration. To address this issue, one of the recent advancements has leveraged multi-objective optimisation to simultaneously consider several acquisition functions (e.g., PI, EI, and LCB), allowing them to complement each other. However, acquisition functions may behave similarly (since they all aim for a good balance between exploitation and exploration), restricting the search on different promising areas. In this paper, we attempt to address the above issue. We directly treat exploitation (reflected by quality, i.e., the posterior mean) and exploration (reflected by uncertainty) as two objectives. When selecting trade-off solutions between the two objectives, we consider a dynamically updated Pareto front where the uncertainty changes once a solution is selected, thereby allowing exploration on different promising areas. Through an extensive experiment study, we show the effectiveness of the proposed method in comparison with state-of-the-arts in the area.

A rich line of theoretical work has modeled scenarios in which a set of agents make decisions sequentially, based on observing a growing mix of public and private signals that are revealed as these decisions occur. Here, we study a second crucial dimension, which is the way in which strategies can depend on crowding. In particular, consider a setting in which agents must sequentially decide which of several options to invest in, each based on a public signal that they receive. One of these options will ultimately be revealed to be valuable; but crucially, all the agents who selected this option must divide the value that comes from it. As a result, when a given agent j goes to make a decision among the options, the decisions of earlier agents convey information about the payoff that j will receive in any eventual division of the value. When many earlier agents have chosen a specific option, the greater crowding on this option means it must be divided more finely, resulting in lower payoffs. To simulate large games when signals are public, we define a polynomial-time algorithm to compute equilibrium strategies. We show that even in this case of public signals, the interaction of crowding with informational effects leads to complex non-monotonicities in the resulting sequential decisions, with agents sometimes choosing options with lower expected levels of crowding --- and hence a better split of the potential value --- over options with better informational or current crowding properties.

Misinformation and propaganda undermine trust in institutions, spread falsehoods, and sometimes incite violence. However, recent advancements in transformer-based AI models can help combat the proliferation of disinformation globally and in real time. In this work, I propose and develop a system using these models to scalably identify, track, and analyze the spread of narratives from over 40,000 international news websites. First, by employing novel multilingual Matryoshka embeddings and hierarchical level-wise clustering, my proposed system identifies news stories, topics, and themes across these thousands of news websites. Second, by utilizing multilingual stance detection, my system assesses the biases and factual inconsistencies in news articles, enabling the identification of websites that spread propaganda or misinformation. Finally, through network inference methods, my system uncovers connections among websites disseminating slanted or false content. My approach illustrates how AI can be utilized to mitigate the global spread of harmful misinformation and propaganda.

Pixel tracking in single-view video sequences has recently emerged as a significant area of research. While previous work has primarily concentrated on tracking within a given video, we propose to expand pixel correspondence estimation into multi-view scenarios. The central concept involves utilizing a canonical space that preserves a universal 3D representation across different views and timesteps. This model allows for precise tracking of points even through prolonged occlusions and significant deformations in appearance between views. Moreover, we show that our model, through the use of an efficient training strategy incorporating distillation loss, is capable of performing incremental pixel tracking, a process often seen as complex in test-time optimization techniques. Comprehensive experiments validate the method's ability to accurately establish point correspondences across cameras. Furthermore, our method achieves promising results of multi-view pixel tracking without requiring the entire video sequences to be provided at once.

Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object parts, sophisticated motion trajectories, and coherent background movement, remains a challenge. In this paper, we introduce *TrackGo*, a novel approach that leverages free-form masks and arrows for conditional video generation. This method offers users with a flexible and precise mechanism for manipulating video content. We also propose the *TrackAdapter* for control implementation, an efficient and lightweight adapter designed to be seamlessly integrated into the temporal self-attention layers of a pretrained video generation model. This design leverages our observation that the attention map of these layers can accurately activate regions corresponding to motion in videos. Our experimental results demonstrate that our new approach, enhanced by the TrackAdapter, achieves state-of-the-art performance on key metrics such as FVD, FID, and ObjMC scores.

Video text-based visual question answering (TextVQA) is a practical task that aims to answer questions by jointly reasoning textual and visual information in a given video. Inspired by the development of TextVQA in image domain, existing Video TextVQA approaches leverage a language model (e.g. T5) to process text-rich multiple frames and generate answers auto-regressively. Nevertheless, the spatio-temporal relationships among visual entities (including scene text and objects) will be disrupted and models are susceptible to interference from unrelated information, resulting in irrational reasoning and inaccurate answering. To tackle these challenges, we propose the TEA (stands for "Track the Answer'') method that better extends the generative TextVQA framework from image to video. TEA recovers the spatio-temporal relationships in a complementary way and incorporates OCR-aware clues to enhance the quality of reasoning questions. Extensive experiments on several public Video TextVQA datasets validate the effectiveness and generalization of our framework. TEA outperforms existing TextVQA methods, video-language pretraining methods and video large language models by great margins. The code will be publicly released.

Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory. This paper presents a Toy-GS method for accurately rendering large-scale free camera trajectories. Specifically, we propose an adaptive spatial division approach for free trajectories to divide cameras and the sparse point cloud of the entire scene into various regions according to camera poses. Training each local Gaussian in parallel for each area enables us to concentrate on texture details and minimize GPU memory usage. Next, we use the multi-view constraint and position-aware point adaptive control (PPAC) to improve the rendering quality of texture details. In addition, our regional fusion approach combines local and global Gaussians to enhance rendering quality with an increasing number of divided areas. Extensive experiments have been carried out to confirm the effectiveness and efficiency of Toy-GS, leading to state-of-the-art results on two public large-scale datasets as well as our SCUTic dataset. Our proposal demonstrates an enhancement of 1.19 dB in PSNR and conserves 7 G of GPU memory when compared to various benchmarks.

In a prior paper, we argued that Artificial Intelligence (AI) should be placed on a different foundation, one based on pattern recognition and feature learning rather than symbol manipulation and feature engineering. In this paper, we provide a proof of concept of an AI course that follows that proposed approach. Students study how these systems become so incredibly powerful through machine learning of features and through pattern matching. Students learn how those systems represent knowledge and they study their currently limited reasoning abilities. Students spend time discussing the accomplishments of current systems, positive as well as negative and they study the projected impact of anticipated systems. In this paper, we give a brief argument of why one would want to offer such a course. We present a detailed outline of the contents of such a course, together with learning materials and their proposed use. We summarize relevant anonymous student feedback and offer a subjective evaluation of the pilot course.

I am a person and so are you. Philosophically we sometimes grant personhood to non-human animals, and entities such as sovereign states or corporations can legally be considered persons. But when, if ever, should we ascribe personhood to AI systems? In this paper, we outline necessary conditions for AI personhood, focusing on agency, theory-of-mind, and self-awareness. We discuss evidence from the machine learn- ing literature regarding the extent to which contemporary AI systems, such as language models, satisfy these conditions, finding the evidence surprisingly inconclusive. If AI systems can be considered persons, then typical fram- ings of AI alignment may be incomplete. Whereas agency has been discussed at length in the literature, other aspects of per- sonhood have been relatively neglected. AI agents are often assumed to pursue fixed goals, but AI persons may be self- aware enough to reflect on their aims, values, and positions in the world and thereby induce their goals to change. We highlight open research directions to advance the understand- ing of AI personhood and its relevance to alignment. Finally, we reflect on the ethical considerations surrounding the treat- ment of AI systems. If AI systems are persons, then seeking control and alignment may be ethically untenable.

In recent years, Multimodal Large Language Models (MLLM) have achieved notable advancements, demonstrating the feasibility of developing an intelligent biomedical assistant. However, current biomedical MLLMs predominantly focus on image-level understanding and restrict interactions to textual commands, thus limiting their capability boundaries and the flexibility of usage. In this paper, we introduce a novel end-to-end multimodal large language model for the biomedical domain, named MedPLIB, which possesses pixel-level understanding. Excitingly, it supports visual question answering (VQA), arbitrary pixel-level prompts (points, bounding boxes, and free-form shapes), and pixel-level grounding. We propose a novel Mixture-of-Experts (MoE) multi-stage training strategy, which divides MoE into separate training phases for a visual-language expert model and a pixel-grounding expert model, followed by fine-tuning using MoE. This strategy effectively coordinates multitask learning while maintaining the computational cost at inference equivalent to that of a single expert model. To advance the research of biomedical MLLMs, we introduce the Medical Complex Vision Question Answering Dataset (MeCoVQA), which comprises an array of 8 modalities for complex medical imaging question answering and image region understanding. Experimental results indicate that MedPLIB has achieved state-of-the-art outcomes across multiple medical visual language tasks. More importantly, in zero-shot evaluations for the pixel grounding task, MedPLIB leads the best small and large models by margins of 19.7 and 15.6 respectively on the mDice metric.

Segment anything model (SAM) demonstrates strong generalization ability on natural image segmentation. However, its direct adaptation in medical image segmentation tasks shows significant performance drops. It also requires an excessive number of prompt points to obtain a reasonable accuracy. Although quite a few studies explore adapting SAM into medical image volumes, the efficiency of 2D adaptation methods is unsatisfactory and 3D adaptation methods are only capable of segmenting specific organs/tumors. In this work, we propose a comprehensive and scalable 3D SAM model for whole-body CT segmentation, named CT-SAM3D. Instead of adapting SAM, we propose a 3D promptable segmentation model using a (nearly) fully labeled CT dataset. To train CT-SAM3D effectively, ensuring the model's accurate responses to higher-dimensional spatial prompts is crucial, and 3D patch-wise training is required due to GPU memory constraints. Therefore, we propose two key technical developments: 1) a progressively and spatially aligned prompt encoding method to effectively encode click prompts in local 3D space; and 2) a cross-patch prompt scheme to capture more 3D spatial context, which is beneficial for reducing the editing workloads when interactively prompting on large organs. CT-SAM3D is trained using a curated dataset of 1204 CT scans containing 107 whole-body anatomies and extensively validated using five datasets, achieving significantly better results against all previous SAM-derived models.

Text generation with citations makes it easy to verify the factuality of Large Language Models’ (LLMs) generations. Existing one-step generation studies expose distinct shortages in answer refinement and in-context demonstration matching. In light of these challenges, we propose R2-MGA, a Retrieval and Reflection Memory-augmented Generative Agent. Specifically, it first retrieves the memory bank to obtain the best-matched memory snippet, then reflects the retrieved snippet as a reasoning rationale, next combines the snippet and the rationale as the best-matched in-context demonstration. Additionally, it is capable of in-depth answer refinement with two specifically designed modules. We evaluate R2-MGA across five LLMs on the ALCE benchmark. The results reveal R2-MGA’ exceptional capabilities in text generation with citations. In particular, compared to the selected baselines, it delivers up to +58.8% and +154.7% relative performance gains on answer correctness and citation quality, respectively. Extensive analyses strongly support the motivations of R2-MGA.

Despite significant progress has been made in image deraining, most existing methods are limited to handling only a single type of rain degradation or a specific pattern of rain. However, real-world rain scenarios tend to contain diverse rainy patterns due to variations in the rainfall process and lighting conditions. To address this dilemma and advance this field, we introduce a new task: Universal Rainy Image Restoration (URIR), which aims to handle multiple types of rain degradation on a single model. To benchmark this task, we construct a high-quality dataset called URIR-8K, which contains four patterns: rain streak, raindrop, rain accumulation and nighttime rain. Building upon this dataset, we present a comprehensive study on existing approaches by evaluating their universal deraining capabilities and their effect on downstream object detection task. In addition, we design a multi-scale vision Mamba as a baseline model, leveraging the benefits of multi-scale learning for its robustness to diverse rain appearances. Unlike existing methods that use fixed-scale scanning for feature extraction, we employ a multi-scale 2D scanning technique to better help image restoration in the richer scale space. Extensive experimental analysis shows the potential of our proposed task and the effectiveness of our model.

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output and, hence, are crucial for supporting decision-making. Despite their importance, the evaluation of these explanations often lacks grounding in user studies and remains fragmented, with existing metrics not fully capturing human perspectives. To address this challenge, we developed a diverse set of 30 counterfactual scenarios and collected ratings across 8 evaluation metrics from 206 respondents. Subsequently, we fine-tuned different Large Language Models (LLMs) to predict average or individual human judgment across these metrics. Our methodology allowed LLMs to achieve an accuracy of up to 63% in zero-shot evaluations and 85% (over a 3-classes prediction) with fine-tuning across all metrics. The fine-tuned models predicting human ratings offer better comparability and scalability in evaluating different counterfactual explanation frameworks.

Cross-Domain Recommendation (CDR) leverages additional knowledge from auxiliary domains to address the long-standing data sparsity issue. However, existing methods typically acquire this knowledge by minimizing the average loss over all domains, overlooking the fact that different domains possess different user-preference distributions. As a result, the acquired knowledge may contain biased information from data-rich domains, leading to performance degradation in data-scarce domains. In this paper, we propose a novel CDR method, which takes domain distinctions into consideration to extract and adapt unbiased information. Specifically, our method consists of two key components: Unbiased Information Extraction (UIE) and Unbiased Information Adaptation (UIA). In the UIE, inspired by distributionally robust optimization, we optimize the worst-case performance across all domains to extract domain-invariant information, preventing the potential bias from auxiliary domains. In the UIA, we introduce a new user-item attention module, which employs domain-specific information from historically interacted items to attend the adaptation of domain-invariant information. To verify the effectiveness of our method, we conduct extensive experiments on three real-world datasets, each of which contains three extremely sparse domains. Experimental results demonstrate the considerable superiority of our proposed method compared to baselines.

Throughout the development of machine learning, researchers have increasingly focused on the challenges of trustworthiness, efficiency, and scalability. Our research specifically addresses these critical aspects.

Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. It involves two key challenges: distribution shifts and trustworthiness concerns. Having these challenges in mind, my research focuses on understanding transfer learning from the perspective of knowledge transferability (e.g., IID and non-IID learning tasks) and trustworthiness (e.g., adversarial robustness, data privacy, and performance fairness).

Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, e.g., KG-based retrieval-augmented framework. However, current KG-LLM frameworks lack rigorous uncertainty estimation, limiting their reliable deployment in applications where the cost of errors is significant. Directly incorporating uncertainty quantification into KG-LLM frameworks presents a challenge due to their more complex architectures and the intricate interactions between the knowledge graph and language model components. To address this crucial gap, we propose a new trustworthy KG-LLM framework, UAG (Uncertainty Aware Knowledge-Graph Reasoning), which incorporates uncertainty quantification into the KG-LLM framework. We design an uncertainty-aware multi-step reasoning framework that leverages conformal prediction to provide a theoretical guarantee on the prediction set. To manage the error rate of the multi-step process, we additionally introduce an error rate control module to adjust the error rate within the individual components. Extensive experiments show that UAG can achieve any pre-defined coverage rate while reducing the prediction set/interval size by 40% on average over the baselines.

SHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP scores can produce unsatisfactory results. Concretely, for some ML models, SHAP scores will mislead with respect to relative feature influence. To address these limitations, recently proposed alternatives exploit different axiomatic aggregations, all of which are defined in terms of abductive explanations. However, the proposed axiomatic aggregations are not Shapley values. This paper investigates how SHAP scores can be modified so as to extend axiomatic aggregations to the case of Shapley values in XAI. More importantly, the proposed new definition of SHAP scores avoids all the known cases where unsatisfactory results have been identified. The paper also characterizes the complexity of computing the novel definition of SHAP scores, highlighting families of classifiers for which computing these scores is tractable. Furthermore, the paper proposes modifications to the existing implementations of SHAP scores. These modifications eliminate some of the known limitations of SHAP scores, and have negligible impact in terms of performance.