Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera speech, background noise, or motion outside the field of view often mislead fusion models that weight all streams equally. We present RAVEN, a unified QA architecture whose core is QuART, a query-conditioned cross-modal gating module that assigns scalar relevance scores to each token across modalities, enabling the model to amplify informative signals and suppress distractors before fusion. RAVEN is trained through a three-stage pipeline comprising unimodal pretraining, query-aligned fusion, and disagreement-oriented fine-tuning -- each stage targeting a distinct challenge in multi-modal reasoning: representation quality, cross-modal relevance, and robustness to modality mismatch. To support training and evaluation, we release AVS-QA, a dataset of 300K synchronized Audio--Video-Sensor streams paired with automatically generated question-answer pairs. Experimental results on seven multi-modal QA benchmarks -- including egocentric and exocentric tasks -- show that RAVEN achieves up to 14.5\% and 8.0\% gains in accuracy compared to state-of-the-art multi-modal large language models, respectively. Incorporating sensor data provides an additional 16.4\% boost, and the model remains robust under modality corruption, outperforming SOTA baselines by 50.23\%. Our code and dataset are available at https://github.com/BASHLab/RAVEN.
Academic posters are vital for scholarly communication, yet their manual creation is time-consuming. However, automated academic poster generation faces significant challenges in preserving intricate scientific details and achieving effective visual-textual integration. Existing approaches often struggle with semantic richness and structural nuances, and lack standardized benchmarks for evaluating generated academic posters comprehensively. To address these limitations, we introduce P2P, the first flexible, LLM-based multi-agent framework that generates high-quality, HTML-rendered academic posters directly from research papers, demonstrating strong potential for practical applications. P2P employs three specialized agents-for visual element processing, content generation, and final poster assembly-each integrated with dedicated checker modules to enable iterative refinement and ensure output quality. To foster advancements and rigorous evaluation in this domain, we construct and release P2PInstruct, the first large-scale instruction dataset comprising over 30,000 high-quality examples tailored for the academic paper-to-poster generation task. Furthermore, we establish P2PEval, a comprehensive benchmark featuring 121 paper-poster pairs and a dual evaluation methodology (Universal and Fine-Grained) that leverages LLM-as-a-Judge and detailed, human-annotated checklists. Our contributions aim to streamline research dissemination and provide the community with robust tools for developing and evaluating next-generation poster generation systems.
Artificial intelligence and machine learning models deployed on edge devices, e.g., for quality control in Additive Manufacturing (AM), are frequently small in size. Such models usually have to deliver highly accurate results within a short time frame. Methods that are commonly employed in literature start out with larger trained models and try to reduce their memory and latency footprint by structural pruning, knowledge distillation, or quantization. It is, however, also possible to leverage hardware-aware Neural Architecture Search (NAS), an approach that seeks to systematically explore the architecture space to find optimized configurations. In this study, a hardware-aware NAS workflow is introduced that couples an edge device located in Belgium with a powerful High-Performance Computing system in Germany, to train possible architecture candidates as fast as possible while performing real-time latency measurements on the target hardware. The approach is verified on a use case in the AM domain, based on the open RAISE-LPBF dataset, achieving ~8.8 times faster inference speed while simultaneously enhancing model quality by a factor of ~1.35, compared to a human-designed baseline.
Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks, and are increasingly deployed as agents in dynamic environments such as code generation and recommendation systems. However, many real-world applications, such as high-frequency trading and real-time competitive gaming, require decisions under strict latency constraints, where faster responses directly translate into higher rewards. Despite the importance of this latency quality trade off, it remains underexplored in the context of LLM based agents. In this work, we present the first systematic study of this trade off in real time decision making tasks. To support our investigation, we introduce two new benchmarks: HFTBench, a high frequency trading simulation, and StreetFighter, a competitive gaming platform. Our analysis reveals that optimal latency quality balance varies by task, and that sacrificing quality for lower latency can significantly enhance downstream performance. To address this, we propose FPX, an adaptive framework that dynamically selects model size and quantization level based on real time demands. Our method achieves the best performance on both benchmarks, improving win rate by up to 80% in Street Fighter and boosting daily yield by up to 26.52% in trading, underscoring the need for latency aware evaluation and deployment strategies for LLM based agents. These results demonstrate the critical importance of latency aware evaluation and deployment strategies for real world LLM based agents. Our benchmarks are available at Latency Sensitive Benchmarks.
Combinatorial optimization (CO) problems are traditionally addressed using Operations Research (OR) methods, including metaheuristics. In this study, we introduce a demand selection problem for the Vehicle Routing Problem (VRP) with an emission quota, referred to as QVRP. The objective is to minimize the number of omitted deliveries while respecting the pollution quota. We focus on the demand selection part, called Maximum Feasible Vehicle Assignment (MFVA), while the construction of a routing for the VRP instance is solved using classical OR methods. We propose several methods for selecting the packages to omit, both from machine learning (ML) and OR. Our results show that, in this static problem setting, classical OR-based methods consistently outperform ML-based approaches.
Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https://github.com/PKU-SDS-lab/POQD-ICML25.
We present AIOS 1.0, a novel platform designed to advance computer-use agent (CUA) capabilities through environmental contextualization. While existing approaches primarily focus on building more powerful agent frameworks or enhancing agent models, we identify a fundamental limitation: the semantic disconnect between how language models understand the world and how computer interfaces are structured. AIOS 1.0 addresses this challenge by transforming computers into contextual environments that language models can natively comprehend, implementing a Model Context Protocol (MCP) server architecture to abstract computer states and actions. This approach effectively decouples interface complexity from decision complexity, enabling agents to reason more effectively about computing environments. To demonstrate our platform's effectiveness, we introduce LiteCUA, a lightweight computer-use agent built on AIOS 1.0 that achieves a 14.66% success rate on the OSWorld benchmark, outperforming several specialized agent frameworks despite its simple architecture. Our results suggest that contextualizing computer environments for language models represents a promising direction for developing more capable computer-use agents and advancing toward AI that can interact with digital systems. The source code of LiteCUA is available at https://github.com/agiresearch/LiteCUA, and it is also integrated into the AIOS main branch as part of AIOS at https://github.com/agiresearch/AIOS.
Exercise-based rehabilitation improves quality of life and reduces morbidity, mortality, and rehospitalization, though transportation constraints and staff shortages lead to high dropout rates from rehabilitation programs. Virtual platforms enable patients to complete prescribed exercises at home, while AI algorithms analyze performance, deliver feedback, and update clinicians. Although many studies have developed machine learning and deep learning models for exercise quality assessment, few have explored the use of large language models (LLMs) for feedback and are limited by the lack of rehabilitation datasets containing textual feedback. In this paper, we propose a new method in which exercise-specific features are extracted from the skeletal joints of patients performing rehabilitation exercises and fed into pre-trained LLMs. Using a range of prompting techniques, such as zero-shot, few-shot, chain-of-thought, and role-play prompting, LLMs are leveraged to evaluate exercise quality and provide feedback in natural language to help patients improve their movements. The method was evaluated through extensive experiments on two publicly available rehabilitation exercise assessment datasets (UI-PRMD and REHAB24-6) and showed promising results in exercise assessment, reasoning, and feedback generation. This approach can be integrated into virtual rehabilitation platforms to help patients perform exercises correctly, support recovery, and improve health outcomes.
We study the high-dimensional asymptotics of empirical risk minimization (ERM) in over-parametrized two-layer neural networks with quadratic activations trained on synthetic data. We derive sharp asymptotics for both training and test errors by mapping the $\ell_2$-regularized learning problem to a convex matrix sensing task with nuclear norm penalization. This reveals that capacity control in such networks emerges from a low-rank structure in the learned feature maps. Our results characterize the global minima of the loss and yield precise generalization thresholds, showing how the width of the target function governs learnability. This analysis bridges and extends ideas from spin-glass methods, matrix factorization, and convex optimization and emphasizes the deep link between low-rank matrix sensing and learning in quadratic neural networks.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a decoupled design, consisting of (1) an RFT-core that unifies and generalizes synchronous/asynchronous, on-policy/off-policy, and online/offline modes of RFT, (2) seamless integration for agent-environment interaction with high efficiency and robustness, and (3) systematic data pipelines optimized for RFT. Trinity-RFT can be easily adapted for diverse application scenarios, and serves as a unified platform for exploring advanced reinforcement learning paradigms. This technical report outlines the vision, features, design and implementations of Trinity-RFT, accompanied by extensive examples demonstrating the utility and user-friendliness of the proposed framework.
We present Qiskit Machine Learning (ML), a high-level Python library that combines elements of quantum computing with traditional machine learning. The API abstracts Qiskit's primitives to facilitate interactions with classical simulators and quantum hardware. Qiskit ML started as a proof-of-concept code in 2019 and has since been developed to be a modular, intuitive tool for non-specialist users while allowing extensibility and fine-tuning controls for quantum computational scientists and developers. The library is available as a public, open-source tool and is distributed under the Apache version 2.0 license.
As Large Language Models (LLMs) increasingly participate in human-AI interactions, evaluating their Theory of Mind (ToM) capabilities - particularly their ability to track dynamic mental states - becomes crucial. While existing benchmarks assess basic ToM abilities, they predominantly focus on static snapshots of mental states, overlooking the temporal evolution that characterizes real-world social interactions. We present \textsc{DynToM}, a novel benchmark specifically designed to evaluate LLMs' ability to understand and track the temporal progression of mental states across interconnected scenarios. Through a systematic four-step framework, we generate 1,100 social contexts encompassing 5,500 scenarios and 78,100 questions, each validated for realism and quality. Our comprehensive evaluation of ten state-of-the-art LLMs reveals that their average performance underperforms humans by 44.7\%, with performance degrading significantly when tracking and reasoning about the shift of mental states. This performance gap highlights fundamental limitations in current LLMs' ability to model the dynamic nature of human mental states.
Graphical User Interface (GUI) agents, which autonomously operate on digital interfaces through natural language instructions, hold transformative potential for accessibility, automation, and user experience. A critical aspect of their functionality is grounding - the ability to map linguistic intents to visual and structural interface elements. However, existing GUI agents often struggle to adapt to the dynamic and interconnected nature of real-world digital environments, where tasks frequently span multiple platforms and applications while also being impacted by version updates. To address this, we introduce TransBench, the first benchmark designed to systematically evaluate and enhance the transferability of GUI agents across three key dimensions: cross-version transferability (adapting to version updates), cross-platform transferability (generalizing across platforms like iOS, Android, and Web), and cross-application transferability (handling tasks spanning functionally distinct apps). TransBench includes 15 app categories with diverse functionalities, capturing essential pages across versions and platforms to enable robust evaluation. Our experiments demonstrate significant improvements in grounding accuracy, showcasing the practical utility of GUI agents in dynamic, real-world environments. Our code and data will be publicly available at GitHub.
This paper presents an adaptive framework for edge inference based on a dynamically configurable transformer-powered deep joint source channel coding (DJSCC) architecture. Motivated by a practical scenario where a resource constrained edge device engages in goal oriented semantic communication, such as selectively transmitting essential features for object detection to an edge server, our approach enables efficient task aware data transmission under varying bandwidth and channel conditions. To achieve this, input data is tokenized into compact high level semantic representations, refined by a transformer, and transmitted over noisy wireless channels. As part of the DJSCC pipeline, we employ a semantic token selection mechanism that adaptively compresses informative features into a user specified number of tokens per sample. These tokens are then further compressed through the JSCC module, enabling a flexible token communication strategy that adjusts both the number of transmitted tokens and their embedding dimensions. We incorporate a resource allocation algorithm based on Lyapunov stochastic optimization to enhance robustness under dynamic network conditions, effectively balancing compression efficiency and task performance. Experimental results demonstrate that our system consistently outperforms existing baselines, highlighting its potential as a strong foundation for AI native semantic communication in edge intelligence applications.
LLM-based digital twin simulation, where large language models are used to emulate individual human behavior, holds great promise for research in AI, social science, and digital experimentation. However, progress in this area has been hindered by the scarcity of real, individual-level datasets that are both large and publicly available. This lack of high-quality ground truth limits both the development and validation of digital twin methodologies. To address this gap, we introduce a large-scale, public dataset designed to capture a rich and holistic view of individual human behavior. We survey a representative sample of $N = 2,058$ participants (average 2.42 hours per person) in the US across four waves with 500 questions in total, covering a comprehensive battery of demographic, psychological, economic, personality, and cognitive measures, as well as replications of behavioral economics experiments and a pricing survey. The final wave repeats tasks from earlier waves to establish a test-retest accuracy baseline. Initial analyses suggest the data are of high quality and show promise for constructing digital twins that predict human behavior well at the individual and aggregate levels. By making the full dataset publicly available, we aim to establish a valuable testbed for the development and benchmarking of LLM-based persona simulations. Beyond LLM applications, due to its unique breadth and scale the dataset also enables broad social science research, including studies of cross-construct correlations and heterogeneous treatment effects.
Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time. Yet current vision-language models (VLMs) often produce verbose, redundant outputs that hinder task performance. Existing video caption evaluation depends on costly human annotations and overlooks the summaries' utility in downstream tasks. We address these gaps with Video-to-text Information Bottleneck Evaluation (VIBE), an annotation-free method that scores VLM outputs using two metrics: grounding (how well the summary aligns with visual content) and utility (how informative it is for the task). VIBE selects from randomly sampled VLM outputs by ranking them according to the two scores to support effective human decision-making. Human studies on LearningPaper24, SUTD-TrafficQA, and LongVideoBench show that summaries selected by VIBE consistently improve performance-boosting task accuracy by up to 61.23% and reducing response time by 75.77% compared to naive VLM summaries or raw video.
Generative artificial intelligence (GenAI) is increasingly used to support a wide range of human tasks, yet empirical evidence on its effect on creativity remains scattered. Can GenAI generate ideas that are creative? To what extent can it support humans in generating ideas that are both creative and diverse? In this study, we conduct a meta-analysis to evaluate the effect of GenAI on the performance in creative tasks. For this, we first perform a systematic literature search, based on which we identify n = 28 relevant studies (m = 8214 participants) for inclusion in our meta-analysis. We then compute standardized effect sizes based on Hedges' g. We compare different outcomes: (i) how creative GenAI is; (ii) how creative humans augmented by GenAI are; and (iii) the diversity of ideas by humans augmented by GenAI. Our results show no significant difference in creative performance between GenAI and humans (g = -0.05), while humans collaborating with GenAI significantly outperform those working without assistance (g = 0.27). However, GenAI has a significant negative effect on the diversity of ideas for such collaborations between humans and GenAI (g = -0.86). We further analyze heterogeneity across different GenAI models (e.g., GPT-3.5, GPT-4), different tasks (e.g., creative writing, ideation, divergent thinking), and different participant populations (e.g., laypeople, business, academia). Overall, our results position GenAI as an augmentative tool that can support, rather than replace, human creativity-particularly in tasks benefiting from ideation support.
Recent text-to-SQL models have achieved strong performance, but their effectiveness remains largely confined to SQLite due to dataset limitations. However, real-world applications require SQL generation across multiple dialects with varying syntax and specialized features, which remains a challenge for current models. The main obstacle in building a dialect-aware model lies in acquiring high-quality dialect-specific data. Data generated purely through static prompting - without validating SQLs via execution - tends to be noisy and unreliable. Moreover, the lack of real execution environments in the training loop prevents models from grounding their predictions in executable semantics, limiting generalization despite surface-level improvements from data filtering. This work introduces ExeSQL, a text-to-SQL framework with execution-driven, agentic bootstrapping. The method consists of iterative query generation, execution-based filtering (e.g., rejection sampling), and preference-based training, enabling the model to adapt to new SQL dialects through verifiable, feedback-guided learning. Experiments show that ExeSQL bridges the dialect gap in text-to-SQL, achieving average improvements of 15.2%, 10.38%, and 4.49% over GPT-4o on PostgreSQL, MySQL, and Oracle, respectively, across multiple datasets of varying difficulty.
This chapter explores the evolution, classification, and health implications of food processing, while emphasizing the transformative role of machine learning, artificial intelligence (AI), and data science in advancing food informatics. It begins with a historical overview and a critical review of traditional classification frameworks such as NOVA, Nutri-Score, and SIGA, highlighting their strengths and limitations, particularly the subjectivity and reproducibility challenges that hinder epidemiological research and public policy. To address these issues, the chapter presents novel computational approaches, including FoodProX, a random forest model trained on nutrient composition data to infer processing levels and generate a continuous FPro score. It also explores how large language models like BERT and BioBERT can semantically embed food descriptions and ingredient lists for predictive tasks, even in the presence of missing data. A key contribution of the chapter is a novel case study using the Open Food Facts database, showcasing how multimodal AI models can integrate structured and unstructured data to classify foods at scale, offering a new paradigm for food processing assessment in public health and research.
Central banks around the world play a crucial role in maintaining economic stability. Deciphering policy implications in their communications is essential, especially as misinterpretations can disproportionately impact vulnerable populations. To address this, we introduce the World Central Banks (WCB) dataset, the most comprehensive monetary policy corpus to date, comprising over 380k sentences from 25 central banks across diverse geographic regions, spanning 28 years of historical data. After uniformly sampling 1k sentences per bank (25k total) across all available years, we annotate and review each sentence using dual annotators, disagreement resolutions, and secondary expert reviews. We define three tasks: Stance Detection, Temporal Classification, and Uncertainty Estimation, with each sentence annotated for all three. We benchmark seven Pretrained Language Models (PLMs) and nine Large Language Models (LLMs) (Zero-Shot, Few-Shot, and with annotation guide) on these tasks, running 15,075 benchmarking experiments. We find that a model trained on aggregated data across banks significantly surpasses a model trained on an individual bank's data, confirming the principle "the whole is greater than the sum of its parts." Additionally, rigorous human evaluations, error analyses, and predictive tasks validate our framework's economic utility. Our artifacts are accessible through the HuggingFace and GitHub under the CC-BY-NC-SA 4.0 license.