United States

Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too under-specified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called constrained timeline summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns Tiger Woods’ legal battles, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.

AAAI 2025

Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance

snlp

summarization

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

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.



Tâtonnement is a simple, intuitive market process where prices are iteratively adjusted based on the difference between demand and supply. Many variants under different market assumptions have been studied and shown to converge to a market equilibrium, in some cases at a fast rate. However, the classical case of linear Fisher markets have long eluded the analyses, and it remains unclear whether tâtonnement converges in this case. We show that, for a sufficiently small stepsize, the prices given by the tâtonnement process are guaranteed to converge to equilibrium prices, up to a small approximation radius that depends on the stepsize. To achieve this, we consider the dual Eisenberg-Gale convex program in the price space, view tâtonnement as subgradient descent on this convex program, and utilize novel last-iterate convergence results for subgradient descent under error bound conditions. In doing so, we show that the convex program satisfies a particular error bound condition, the quadratic growth condition, and that the price sequence generated by tâtonnement is bounded above and away from zero. We also show that a similar convergence result holds for tâtonnement in quasi-linear Fisher markets. Numerical experiments are conducted to demonstrate that the theoretical linear convergence aligns with empirical observations.

On the Convergence of Tâtonnement for Linear Fisher Markets

Screen-shooting robust watermarking is an effective means of preventing screen content leakage, as it can trace the leaked source through the watermark extraction thereby providing an effective deterrent. However, current screen-shooting resilient watermarking schemes are limited to scenarios where the watermarked image is fully captured, technically because they need the contours of the image to synchronize the watermarked area. While in practical applications, it's common for only a portion of the image to be captured. In this scenario, none of the previous schemes can be applied. To address this problem, we propose the RoPaSS: a robust watermarking scheme for partial screen-shooting, which effectively constructs symmetric characteristics on the embedding watermark to handle the re-synchronization issue. Specifically, RoPaSS consists of a watermark encoder, a decoder, and three estimators, which are trained in two stages. In the first training stage, RoPaSS integrates the flipping operation into the watermark encoder and decoder training to increase the redundancy of watermark messages and artificially guide the generation of symmetric watermarks. In the second stage, aiming to resynchronize the partially captured watermarked image, estimators utilize the watermark symmetry as an additional reference to estimate the restoration parameters of homography transformation. Experiments have demonstrated the excellent performance of RoPaSS in partial screen-shooting traceability, with extraction accuracy of above 93% in frontal shooting and above 86% in 30° shooting even if only 50% of the image content is captured.

RoPaSS: Robust Watermarking for Partial Screen-Shooting Scenarios

The rapid spread of information in the digital age highlights the critical need for effective fact-checking tools, particularly for languages with limited resources, such as Vietnamese. In response to this challenge, we introduce ViFactCheck, the first publicly available benchmark dataset designed specifically for Vietnamese fact-checking across multiple online news domains. This dataset contains 7,232 human-annotated pairs of claim-evidence combinations sourced from reputable Vietnamese online news, covering 12 diverse topics. It has been subjected to a meticulous annotation process to ensure high quality and reliability, achieving a Fleiss Kappa inter-annotator agreement score of 0.83. Our evaluation leverages state-of-the-art pre-trained and large language models, employing fine-tuning and prompting techniques to assess performance. Notably, the Gemma model demonstrated superior effectiveness, with an impressive macro F1 score of 89.90%, thereby establishing a new standard for fact-checking benchmarks. This result highlights the robust capabilities of Gemma in accurately identifying and verifying facts in Vietnamese. To further promote advances in fact-checking technology and improve the reliability of digital media, we have made the ViFactCheck dataset, model checkpoints, fact-checking pipelines, and source code freely available on GitHub. This initiative aims to inspire further research and enhance the accuracy of information in low-resource languages.

ViFactCheck: A New Benchmark Dataset and Methods for Multi-Domain News Fact-Checking In Vietnamese

In recent years, predicting Big Five personality traits from multimodal data has received significant attention in artificial intelligence (AI). However, existing computational models often fail to achieve satisfactory performance. Psychological research has shown a strong correlation between pose and personality traits, yet previous research has largely ignored pose data in computational models. To address this gap, we develop a novel multimodal dataset that incorporates full-body pose data. The dataset includes video recordings of 287 participants completing a virtual interview with 36 questions, along with self-assessed Big Five personality scores as labels. To effectively utilize this multimodal data, we introduce the Psychology-Inspired Network (PINet), which consists of three key modules: Multimodal Feature Awareness (MFA), Multimodal Feature Interaction (MFI), and Psychology-Informed Modality Correlation Loss (PIMC Loss). The MFA module leverages the Vision Mamba Block to capture comprehensive visual features related to personality, while the MFI module efficiently fuses the multimodal features. The PIMC Loss, grounded in psychological theory, guides the model to emphasize different modalities for different personality dimensions. Experimental results show that the PINet outperforms several state-of-the-art baseline models. Furthermore, the three modules of PINet contribute almost equally to the model’s overall performance. Incorporating pose data significantly enhances the model’s performance, with the pose modality ranking mid-level in importance among the five modalities. These findings address the existing gap in personality-related datasets that lack full-body pose data and provide a new approach for improving the accuracy of personality prediction models, highlighting the importance of integrating psychological insights into AI frameworks.

Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset

Dealing with distribution shift is a significant challenge when building offline reinforcement learning (RL) models that can generalize from a static dataset to out-of-distribution (OOD) scenarios. Previous approaches have employed pessimism or conservatism strategies. More recently, data-driven work has taken a distributional perspective, treating offline data as a domain adaptation problem. However, these methods use heuristic techniques to simulate distribution shifts, resulting in a limited diversity of artificially created distribution gaps. In this paper, we propose a novel perspective: offline datasets inherently contain multiple latent distributions, with behavior data from diverse policies potentially following different distributions and data from the same policy across various time phases also exhibiting distribution variance. We introduce the Latent Distribution Representation Learning (LAD) framework, which aims to characterize the multiple latent distributions within offline data by reducing the distribution gaps between any pair of them. LAD consists of a min-max adversarial process: it first identifies the "worst-case" distributions to enlarge the diversity of distribution gaps and then reduces these gaps to learn invariant representations for generalization. We derive a generalization error bound to support LAD theoretically and verify its effectiveness through extensive experiments.

Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning

Human multimodal language understanding (MLU) is an indispensable component of expression analysis (e.g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviours. Existing works invariably focus on designing sophisticated structures or fusion strategies to achieve impressive improvements. Unfortunately, they all suffer from the subject variation problem due to data distribution discrepancies among subjects. Concretely, MLU models are easily misled by distinct subjects with different expression customs and characteristics in the training data to learn subject-specific spurious correlations, limiting performance and generalizability across new subjects. Motivated by this observation, we introduce a recapitulative causal graph to formulate the MLU procedure and analyze the confounding effect of subjects. Then, we propose SuCI, a simple yet effective causal intervention module to disentangle the impact of subjects acting as unobserved confounders and achieve model training via true causal effects. As a plug-and-play component, SuCI can be widely applied to most methods that seek unbiased predictions. Comprehensive experiments on several MLU benchmarks clearly show the effectiveness of the proposed module.

Debiased Multimodal Understanding for Human Language Sequences

The early diagnosis of Parkinson’s disease (PD) is crucial for potential patients to receive timely treatment and prevent disease progression. Recent studies have shown that PD is closely linked to impairments in facial muscle control, resulting in characteristic “masked face” symptoms. This discovery offers a novel perspective for PD diagnosis by leveraging facial expression recognition and analysis techniques to capture and quantify these features, thereby distinguishing between PD patients and non-PD individuals based on their facial expressions. However, concerns about data privacy and legal restrictions have led to significant “data silos”, posing challenges to data sharing and limiting the accuracy and generalization of existing diagnostic models due to small, localized datasets. To address this issue, we propose an innovative adaptive federated learning approach that aims to jointly analyze facial expression data from multiple medical institutions while preserving data privacy. Our proposed approach comprehensively evaluates each client's contributions in terms of gradient, data, and learning efficiency, overcoming the non-IID issues caused by varying data sizes or heterogeneity across clients. To demonstrate the real-world impact of our approach, we collected a new facial expression dataset of PD patients in collaboration with a hospital. Extensive experiments validate the effectiveness of our proposed method for PD diagnosis and facial expression recognition, offering a promising avenue for rapid, non-invasive initial screening and advancing healthcare intelligence.

Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis

Artificial intelligence has made significant strides in reasoning
over complex structured multimodal and multilingual
data, addressing critical challenges in domains such as finance
and healthcare. This abstract highlights key advancements
in tabular reasoning, temporal analysis, and structured
multimodal reasoning.
One major contributions include TempTabQA (Gupta
et al. 2023), a benchmark for temporal question answering;
novel methods to enhance temporal reasoning in large
language models (LLMs); and a framework for evaluating
mathematical reasoning in financial documents (Srivastava
et al. 2024). These works establish robust approaches for interpreting
time-sensitive and quantitative data. Building on
this foundation, we have developed hybrid SQL-text adaptive
reasoning models, H-STAR, and knowledge-aware reasoning
techniques for semi-structured tables (Mathur et al.
2024), enabling precise and efficient handling of complex
queries.
In the vision-language domain, our contributions include
advancements in spatial reasoning for geographic
data, MAPWise (Mukhopadhyay et al. 2024b), methods
to improve robustness in chart interpretation, FlowVQA
(Singh et al. 2024), and evaluations of LLMs’ ability
to understand visual data, such as charts, RobustCQA
(Mukhopadhyay et al. 2024a). Furthermore, we have addressed
challenges in multilingual and cross-modal robustness
through innovations in multilingual table synchronization,
InfoSync(Khincha et al. 2023), concurrent robustness
evaluation across languages and modalities (Gupta et al.
2024), and numerical reasoning in tabular data (Akhtar et al.
2023).
Our future work focuses on enhancing reasoning for dynamically
evolving data through hybrid LLM-SQL queries,
symbolic query generation, and multi-table retrieval. We
also aim to address challenges in interpreting hierarchical
structures, complex multiple charts, and diverse map types,
while advancing the analysis of real-world multimodal data.
Additionally, we seek to improve table generation for both
closed-book and open-book scenarios and refine evaluation
frameworks for structured data tasks.
These efforts highlight AI’s potential to tackle

Advancements in AI for Reasoning with Complex Data

Artificial Intelligence (AI) and Machine Learning hold immense potential to accelerate scientific discovery and engineering design. A fundamental challenge in these domains involves efficiently exploring a large space of hypotheses using expensive experiments in a resource-efficient manner. My research focuses on developing novel adaptive experimental design methods to address this broad challenge. Specifically, I develop new probabilistic modeling and decision making tools that operate in small data settings. These approaches have yielded substantial improvements in sample-efficiency, particularly for black-box optimization over high-dimensional combinatorial spaces (e.g., sequences and graphs). This cover letter outlines key methods I have developed and their real-world sustainability applications in areas such as nano-porous materials discovery, hardware design, and additive manufacturing. Additionally, I highlight my initiatives to foster collaboration between Science/Engineering and AI communities.

Adaptive Experimental Design to Accelerate Scientific Discovery and Engineering Design

Although Artificial Intelligence (AI) has transformed vision and language modeling, Scientific Machine Learning (SciML) complements data-driven AI via a knowledge-driven approach, enhancing our understanding of the physical world. My work focuses on: 1) automating scientific reasoning with language models, 2) improving geometric interpretation, 3) developing foundation models for multiphysics.

Downloads

Next from AAAI 2025

On the Convergence of Tâtonnement for Linear Fisher Markets

Similar lecture

From Moments to Milestones: Incremental Timeline Summarization Leveraging Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES