United States

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do not exist in the image. In this paper, we reveal that object hallucination can be attributed to overconfidence in irrelevant visual features when soft visual tokens map to the LLM&#39;s word embedding space. Specifically, by figuring out the semantic similarity between visual tokens and LLM&#39;s word embedding, we observe that the smoothness of similarity distribution strongly correlates with the emergence of object hallucinations. To mitigate hallucinations, we propose using the Variational Information Bottleneck (VIB) to alleviate overconfidence by introducing stochastic noise, facilitating the constraining of irrelevant information. Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution. We adapt the proposed AdaVIB across distinct model architectures. Experimental results demonstrate that the proposed AdaVIB mitigates object hallucinations by effectively alleviating the overconfidence in irrelevant visual features, with consistent improvements on two object hallucination benchmarks.

AAAI 2025

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do not exist in the image. In this paper, we reveal that object hallucination can be attributed to overconfidence in irrelevant visual features when soft visual tokens map to the LLM's word embedding space. Specifically, by figuring out the semantic similarity between visual tokens and LLM's word embedding, we observe that the smoothness of similarity distribution strongly correlates with the emergence of object hallucinations. To mitigate hallucinations, we propose using the Variational Information Bottleneck (VIB) to alleviate overconfidence by introducing stochastic noise, facilitating the constraining of irrelevant information. Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution. We adapt the proposed AdaVIB across distinct model architectures. Experimental results demonstrate that the proposed AdaVIB mitigates object hallucinations by effectively alleviating the overconfidence in irrelevant visual features, with consistent improvements on two object hallucination benchmarks.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than 2% of the parameters.

Few-Shot Domain Adaptation for Learned Image Compression

Online to batch conversion involves constructing a new batch learner by utilizing a series of models generated by an existing online learning algorithm, for achieving generalization guarantees under i.i.d assumption. However, when applied to real-world streaming applications such as streaming recommender systems, the data stream may be sampled from time-varying distributions instead of persistently being i.i.d. This poses a challenge in terms of out-of-distribution (OOD) generalization. Existing approaches employ fixed conversion mechanisms that are unable to adapt to novel testing distributions, hindering the testing accuracy of the batch learner. To address these issues, we propose AdaO2B, an adaptive online to batch conversion approach under the bandit setting. AdaO2B is designed to be aware of the distribution shifts in the testing data and achieves OOD generalization guarantees. Specifically, AdaO2B can dynamically combine the sequence of models learned by a contextual bandit algorithm and determine appropriate combination weights using a context-aware weighting function. This innovative approach allows for the conversion of a sequence of models into a batch learner that facilitates OOD generalization. Theoretical analysis provides justification for why and how the learned adaptive batch learner can achieve OOD generalization error guarantees. Experimental results have demonstrated that AdaO2B significantly outperforms state-of-the-art baselines on both synthetic data and real-world data.

AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization

In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of cooperation and competition, understanding agents' decision-making in such environments is challenging, and humans can benefit from obtaining explanations. However, such environments and scenarios have rarely been explored in the context of explainable AI. While some explanation methods for cooperative environments can be applied in mixed-motive setups, they do not address inter-agent competition, cheap-talk, or implicit communication by actions. In this work, we design explanation methods to address these issues. Then, we proceed to establish generality and demonstrate the applicability of the methods to three games with vastly different properties.
Lastly, we demonstrate the effectiveness and usefulness of the methods for humans in two mixed-motive games. The first is a challenging 7-player game called no-press Diplomacy. The second is a 3-player game inspired by the Prisoner's Dilemma, featuring communication in natural language.

Explaining Decisions of Agents in Mixed-Motive Games

The objective of Composed Image Retrieval (CIR) is to identify a target image that meets the requirement based on a multimodal query (including the reference image and the modification text) provided by the user. Despite the notable success of existing approaches, they fail to adequately address the modification relation between visual entities and modification actions. This limitation is non-trivial due to three challenges: 1) irrelevant factor perturbation, 2) vague semantic boundaries, and 3) implicit modification relations. To address the above challenges, we propose an Entity miNing and modifiCation relatiOn binDing nEtwoRk (ENCODER), which has been designed to mine visual entities and modification actions, and then bind modification relations. Among the various components of the proposed ENCODER, we have initially designed the Latent Factor Filter (LFF) module to filter visual and textual latent factors related to modification semantics based on a threshold gating mechanism. Secondly, we propose Entity-Action Binding (EAB), which comprises modality-shared Learnable Relation Queries (LRQ) that are capable of mining visual entities and modification actions, as well as learning implicit modification relations for entity-action binding. Finally, the Multi-scale Composition module is introduced to achieve multi-scale feature composition, with guidance provided by entity-action binding. Extensive experiments on four benchmark datasets demonstrate the superiority of our proposed method. Our codes and checkpoints are released in the supplement material.

ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval

Dependency parsing is crucial in natural language processing for analyzing syntactic structures. Dependency parsers enhanced by pre-trained language models have achieved outstanding performance in high-resource languages. In contrast, cross-language dependency parsing is an effective strategy to learn useful knowledge from high-resource languages and compensate for the deficiency of low-resource languages. However, the key challenge for cross-language dependency parsing is to reduce distributional biases and excavate in-depth commonalities. To address this issue, we propose the novel dynamic syntactic feature filtering and injecting networks based on the traditional shared-private model which utilizes a shared and two private encoders to separate features from source or target languages. Concretely, a language-specific syntactic feature filtering network (LSFN) on private encoders emphasizes helpful information and ignores irrelevant or harmful information from the source language. Meanwhile, the language-invariant syntactic feature injection network (LIIN) on the shared encoder can combine the advantages of BiLSTM and improved transformer encoders to transcend language boundaries, thus amplifying syntactic commonalities across languages. We perform experiments on seven benchmark datasets to measure the efficacy of our proposed model and observe an average absolute gain of $1.84$ UAS and $3.43$ LAS compared with the shared-private model. Comparative experiments validate that both LSFN and LIIN components are complementary in transferring beneficial knowledge from source to target languages. Detailed analyses highlight that our model can effectively capture linguistic commonalities and minimize differences, showcasing its robustness and efficacy. Our code will be publicly available at https://flamelunar.github.io/.

Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing

Recent advancements in Multimodal Large Language Models (MLLMs) have generated significant interest in their ability to autonomously interact with and interpret Graphical User Interfaces (GUIs). A major challenge in these systems is grounding—accurately identifying critical GUI components such as text or icons based on a GUI image and a corresponding text query. Traditionally, this task has relied on fine-tuning MLLMs with specialized training data to predict component locations directly. However, in this paper, we propose a novel Tuning-free Attention-driven Grounding (TAG) method that leverages the inherent attention patterns in pretrained MLLMs to accomplish this task without the need for additional fine-tuning. Our method involves identifying and aggregating attention maps from specific tokens within a carefully constructed query prompt. Applied to MiniCPM-Llama3-V 2.5, a state-of-the-art MLLM, our tuning-free approach achieves performance comparable to tuning-based methods, with notable success in text localization. Additionally, we demonstrate that our attention map-based grounding technique significantly outperforms direct localization predictions from MiniCPM-Llama3-V 2.5, highlighting the potential of using attention maps from pretrained MLLMs and paving the way for future innovations in this domain.

Attention-Driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models Without Fine-Tuning

Missing values in multivariate time series data can harm machine learning performance and introduce bias. These gaps arise from sensor malfunctions, blackouts, and human error. Previous work has addressed missing at random, complete blackouts, and forecasting scenarios. This paper addresses a more general missing pattern, termed $\textbf{partial blackout}$, where a subset of features is missing for consecutive time steps. This scenario is more common in real-world applications. We introduce a two-stage imputation process using self-attention and diffusion processes to model feature and temporal correlations. Our model outperforms state-of-the-art models in partial blackout scenarios and offers better scalability, promising practical data imputation solutions.

Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios

With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. 
In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving.
However, videos in such a dynamical scene that often contains complex spatial-temporal movements,
which restricts the generalization capacity of the existing MLLMs in this field.
To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving videos.
Specifically, our H-MBA consists of two distinct modules,
including Context Mamba (C-Mamba) and Query Mamba (Q-Mamba).
First, C-Mamba contains various types of structure state space models,
which can effectively capture multi-granularity video context for different temporal resolution.
Second, Q-Mamba flexibly transforms the current frame as the learnable query, 
and attentively select multi-granularity video context into query.
Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding.
Via a plug-and-play paradigm in MLLMs,
our H-MBA shows the remarkable performance on multi-modal video tasks in autonomous driving,
e.g., for risk object detection, it outperforms the previous SOTA method with 5.5\% mIoU improvement.

H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving

Face anti-spoofing (FAS) plays a pivotal role in ensuring the security and reliability of face recognition systems. With advancements in vision-language pretrained (VLP) models, recent two-class FAS techniques have leveraged the advantages of using VLP guidance, while this potential remains unexplored in one-class FAS methods. The one-class FAS focuses on learning intrinsic liveness features solely from live training images to differentiate between live and spoof faces. However, the lack of spoof training data can lead one-class FAS models to inadvertently incorporate domain information irrelevant to the live/spoof distinction (\eg, facial content), causing performance degradation when tested with a new application domain. To address this issue, we propose a novel framework called Spoof-aware one-class face anti-spoofing with Language Image Pretraining (SLIP). Given that live faces should ideally not be obscured by any spoof-attack-related objects (\eg, paper, or masks) and are assumed to yield zero spoof cue maps, we first propose an effective language-guided spoof cue map estimation to enhance one-class FAS models by simulating whether the underlying faces are covered by attack-related objects and generating corresponding nonzero spoof cue maps. Next, we introduce a novel prompt-driven liveness feature disentanglement to alleviate live/spoof-irrelative domain variations by disentangling live/spoof-relevant and domain-dependent information. Finally, we design an effective augmentation strategy by fusing latent features from live images and spoof prompts to generate spoof-like image features and thus diversify latent spoof features to facilitate the learning of one-class FAS. Our extensive experiments and ablation studies support that SLIP consistently outperforms previous one-class FAS methods.

SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining

In this study, we consider an optimization problem with uncertainty dependent on decision variables, which has recently attracted attention due to its importance in applications. In this problem, the gradient of the objective function cannot be obtained explicitly because the decision-dependent distribution is unknown. Therefore, several zeroth-order methods have been proposed, which obtain noisy objective values by sampling and update the iterates.  Although these existing methods have theoretical convergence for optimization problems with decision-dependent uncertainty, they require strong assumptions about the function and distribution or exhibit large variances in their gradient estimators. To overcome these issues, we propose two zeroth-order methods under mild assumptions. First, we develop a zeroth-order method with a new one-point gradient estimator including a variance reduction parameter. The proposed method updates the decision variables while adjusting the variance reduction parameter. Second, we develop a zeroth-order method with a two-point gradient estimator. There are situations where only one-point estimators can be used, but if both one-point and two-point estimators are available, it is more practical to use the two-point estimator. As theoretical results, we show the convergence of our methods to stationary points and provide the worst-case iteration and sample complexity analysis. Our simulation experiments with real data on a retail service application show that our methods output solutions with lower objective values than the conventional zeroth-order methods.

Downloads

Next from AAAI 2025

Few-Shot Domain Adaptation for Learned Image Compression

Similar lecture

Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

Few-Shot Domain Adaptation for Learned Image Compression

Similar lecture

Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models

Downloads