United States

In many RL applications, ensuring an agent&#39;s actions adhere to constraints is crucial for safety.
Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers.
Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue.
However, generative models require training using samples from the constrained action space, which itself is challenging. To address such limitations, first, we define a target distribution for feasible actions based on constraint violation signals, and train normalizing flows by minimizing the KL divergence between an approximated distribution over feasible actions and the target. This eliminates the need to generate feasible action samples, greatly simplifying the flow model learning. Second, 
we integrate the learned flow model with existing deep RL methods, which restrict it to exploring only the feasible action space. Third, we extend our approach beyond ACRL to handle state-wise constraints by learning the constraint violation signal from the environment.
Empirically, our approach has significantly fewer constraint violations while achieving similar or better quality in several control tasks than previous best methods.

AAAI 2025

Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning

reinforcement learning

In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety.
Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers.
Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue.
However, generative models require training using samples from the constrained action space, which itself is challenging. To address such limitations, first, we define a target distribution for feasible actions based on constraint violation signals, and train normalizing flows by minimizing the KL divergence between an approximated distribution over feasible actions and the target. This eliminates the need to generate feasible action samples, greatly simplifying the flow model learning. Second, 
we integrate the learned flow model with existing deep RL methods, which restrict it to exploring only the feasible action space. Third, we extend our approach beyond ACRL to handle state-wise constraints by learning the constraint violation signal from the environment.
Empirically, our approach has significantly fewer constraint violations while achieving similar or better quality in several control tasks than previous best methods.

technical paper

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.



Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as generating random artifacts and the incapacity to repaint foreground object areas with appropriate content after removal. To tackle these problems, we propose Attentive Eraser, a tuning-free method to empower pre-trained diffusion models for stable and effective object removal. Firstly, in light of the observation that the self-attention maps influence the structure and shape details of the generated images, we propose Attention Activation and Suppression (ASS), which re-engineers the self-attention mechanism within the pre-trained diffusion models based on the given mask, thereby prioritizing the background over the foreground object during the reverse generation process. Moreover, we introduce Self-Attention Redirection Guidance (SARG), which utilizes the self-attention redirected by ASS to guide the generation process, effectively removing foreground objects within the mask while simultaneously generating content that is both plausible and coherent. Experiments demonstrate the stability and effectiveness of Attentive Eraser in object removal across a variety of pre-trained diffusion models, outperforming even training-based methods. Furthermore, Attentive Eraser can be implemented in various diffusion model architectures and checkpoints, enabling excellent scalability.

Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance

Rent division is the well-studied problem of fairly assigning rooms and dividing rent among a set of roommates within a single apartment. A shortcoming of existing solutions is that renters are assumed to be considering apartments in isolation, whereas in reality, renters can choose among multiple apartments. In this paper, we generalize the rent division problem to the multi-apartment setting, where the goal is to both fairly choose an apartment among a set of alternatives and fairly assign rooms and rents within the chosen apartment. Our main contribution is a generalization of envy-freeness called *negotiated envy-freeness*. We show that a solution satisfying negotiated envy-freeness is guaranteed to exist and that it is possible to optimize over all negotiated envy-free solutions in polynomial time. We also define an even stronger fairness notion called *universal envy-freeness* and study its existence when values are drawn randomly.

Multi-Apartment Rent Division

Personality identification plays important roles in understanding user behavior and offering foresight ability for downstream applications. The key challenge is how to address the scarcity of labeled personality data. Recently, some studies have adopted data augmentation and prompt learning to perform personality identification. However, they still heavily require a large amount of labeled data to learn an appropriate distance strategy, which limits the generalization and flexibility of the model. This study proposes a knowledge-enhanced hierarchical heterogeneous graph model, which adopts a global multi-view graph node encoding to acquire comprehensive personality features and their inherent associations, where  three types of knowledge including part-of-speech (POS) tag, entity, and Linguistic Inquiry and Word Count (LIWC) are introduced. Then, a hierarchical heterogeneous graph with a “post-word-diverse knowledge” structure is constructed for each post to obtain enhanced representation. Finally, a relation guided representation optimization that considers intra-user relationships and inter-label relationships is further developed to learn more discriminative semantic representation. Experimental results on three widely used datasets demonstrate that the model outperforms state-of-the-art methods when training with only 100 samples (approximately 1% of the total data set).

Knowledge-Enhanced Hierarchical Heterogeneous Graph for Personality Identification with Limited Training Data

The pervasive spread of misinformation on social networks highlights the critical necessity for effective fact verification systems. 
Traditional approaches primarily focus on pairwise correlations between claims and evidence, often neglecting comprehensive multi-hop retrieval and reasoning, which results in suboptimal performance when dealing with complex claims.
In this paper, we propose MRR-FV, a generative retrieval-enhanced model designed to address the novel challenge of Multi-hop Retrieval and Reasoning for Fact Verification, which integrates two core modules: Generative Multi-hop Evidence Retrieval and the Hierarchical Interaction Reasoner. 
MRR-FV utilizes an autoregressive model for iterative multi-hop evidence retrieval, complemented by a pre-trained compressor to address the challenge of intention shift across retrieval hops.
For claim verification, we propose a hierarchical interaction reasoner that conducts intra-sentence reasoning to capture long-term semantic dependencies and inter-sentence reasoning across multi-hop evidence subgraphs to reveal complex evidence interactions. 
Experimental evaluations on the FEVER and HOVER datasets demonstrate the superior performance of our model in both claim verification and evidence retrieval tasks.

MRR-FV: Unlocking Complex Fact Verification with Multi-hop Retrieval and Reasoning

The autoregressive decoding paradigm endows large language models (LLMs) with superior language generation capabilities; however, its step-by-step decoding process inherently limits decoding speed. To mitigate these constraints, the prevalent “draft and validation” strategy enables parallel validation of candidate drafts, allowing LLMs to decode multiple tokens simultaneously during one model forward propagation. 
However, existing methodologies for obtaining drafts often incur additional overhead in communication or training process, or statistical biases from the corpus.
To this end, we propose and innovative draft generation and maintenance approach that leverages the capabilities of LLM itself. Specifically, we extend the autoregressive decoding method to a multi-branch drafting procedure, which can efficiently generate draft sequences without any additional models or training process, while preserving the quality of the generated content by maintaining LLM parameters. 
Experiments across various open-source benchmarks show that our method generates 2.0 to 3.2 tokens per forward step and achieves around 2 times improvement of end-to-end throughput compared to the autoregressive decoding strategy. Our code will be available at: https://anonymous.4open.science/r/Self-Draft-B434.

Multi-Branch Self-Drafting for LLM Inference Acceleration

Embedding links in brand logos is a promising technology, which allows consumers to access the online information of products by capturing physical logo images. Previous physical data hiding methods primarily embed data within cover media in a global manner, making them ineffective for processing brand logos in vector graphics format with a transparent background. To address this issue, we propose in this paper a novel physical deep hiding scheme for invisibly embedding links in printed trademarks. Specifically, the encoder embeds links only into the area of the brand logo under the constraints of a mask, which is generated from the transparency information of the logo image. A background variation distortion is introduced into the distortion layer that approximate practical logo print-camera environments, such that the decoder could be learnt to retrieve the link from the camera-captured logo with various backgrounds. A feature prompt subspace modulator is further proposed and employed in the encoder to enhance the invisibility of the encoded logo pattern and in the decoder to boost hyperlink extraction accuracy. Various experiments have been conducted to demonstrate the advantage of our proposed method for embedding links in printed brand logos, which provides reliable extraction accuracy under both simulated and real scenarios.

Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks

Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit them, which overlooks the relative positional relationships among joints. To this end, we provide a new perspective, constraining joint associations and gesture details by modeling the limb bones to improve the accuracy and naturalness of the generated poses. In this work, we propose a pioneering iconicity disentangled diffusion framework, termed Sign-IDD, specifically designed for SLP. Sign-IDD incorporates a novel Iconicity Disentanglement (ID) module to bridge the gap between relative positions among joints. The ID module disentangles the conventional 3D joint representation into a 4D bone representation, comprising the 3D spatial direction vector and 1D spatial distance vector between adjacent joints. Additionally, an Attribute Controllable Diffusion (ACD) module is introduced to further constrain joint associations, in which the attribute separation layer aims to separate the bone direction and length attributes, and the attribute control layer is designed to guide the pose generation by leveraging the above attributes. The ACD module utilizes the gloss embeddings as semantic conditions and finally generates sign poses from noise embeddings. Extensive experiments on PHOENIX14T and USTC-CSL datasets validate the effectiveness of our method.

Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production

Despite multimodal sentiment analysis being a fertile research ground that merits further investigation, current approaches take up high annotation cost and suffer from label ambiguity, non-amicable to high-quality labeled data acquisition. Furthermore, choosing the right interactions is essential because the significance of intra- or inter-modal interactions can differ among various samples. To this end, we propose Semi-IIN, a Semi-supervised Intra-inter modal Interaction learning Network for multimodal sentiment analysis. Semi-IIN integrates masked attention and gating mechanisms, enabling effective dynamic selection after independently capturing intra- and inter-modal interactive information. Combined with the self-training approach, Semi-IIN fully utilizes the knowledge learned from unlabeled data. Experimental results on two public datasets, MOSI and MOSEI, demonstrate the effectiveness of Semi-IIN, establishing a new state-of-the-art on several metrics.

Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis

Unified detection of digital and physical attacks in facial recognition systems has become a focal point of research in recent years. However, current multi-modal methods typically ignore the intra-class and inter-class variability across different types of attacks, leading to degraded performance. To address this limitation, we propose MoAE-CR, a framework that effectively leverages class-aware information for improved attack detection. Our improvements manifest at two levels, i.e., the feature and loss level. At the feature level, we propose Mixture-of-Attack-Experts (MoAEs) to capture more subtle differences among various types of fake faces. At the loss level, we introduce Class Regularization (CR) through the Disentanglement Module (DM) and the Cluster Distillation Module (CDM). The DM enhances class separability by increasing the distance between the centers of live and fake face classes. However, center-to-center constraints alone are insufficient to ensure distinctive representations for individual features. Thus, we propose the CDM to further cluster features around their class centers while maintaining separation from other classes. Moreover, specific attacks that significantly deviate from common attack patterns are often overlooked. To address this issue, our distance calculation prioritizes more distant features. Extensive experiments on two unified physical-digital attack datasets demonstrate the state-of-the-art performance of the proposed method.

Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be effective, particularly in robotics manipulation tasks. However, recursion-based approaches are often inference inefficient in working from noise distributions to policy distributions, posing a challenging trade-off between efficiency and quality. This motivates us to propose FlowPolicy, a novel framework for fast policy generation based on consistency flow matching and 3D vision. Our approach refines the flow dynamics by normalizing the self-consistency of the velocity field, enabling the model to derive task execution policies in a single inference step. Specifically, FlowPolicy conditions on the observed 3D point cloud, where consistency flow matching directly defines straight-line flows from different time states to the same action space, while simultaneously constraining their velocity values, that is, we approximate the trajectories from noise to robot actions by normalizing the self-consistency of the velocity field within the action space, thus improving the inference efficiency. We validate the effectiveness of FlowPolicy on Adroit and Metaworld, demonstrating a 7$\times$ increase in inference speed while maintaining competitive average success rates compared to state-of-the-art policy models. Codes will be made publicly available.

Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning

Downloads

Next from AAAI 2025

Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning

.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

Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads