WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing semantically accurate, coherent, and contextually appropriate images in real-world scenarios. To address this gap, we introduce \textbf{WorldGenBench}, a benchmark designed to systematically evaluate T2I models' world knowledge grounding and implicit inferential capabilities, covering both the humanities and nature domains. We propose the \textbf{Knowledge Checklist Score}, a structured metric that measures how well generated images satisfy key semantic expectations. Experiments across 21 state-of-the-art models reveal that while diffusion models lead among open-source methods, proprietary auto-regressive models like GPT-4o exhibit significantly stronger reasoning and knowledge integration. Our findings highlight the need for deeper understanding and inference capabilities in next-generation T2I systems. Project Page: \href{https://dwanzhang-ai.github.io/WorldGenBench/}{https://dwanzhang-ai.github.io/WorldGenBench/}

RadioFormer: A Multiple-Granularity Radio Map Estimation Transformer with 1\textpertenthousand Spatial Sampling

The task of radio map estimation aims to generate a dense representation of electromagnetic spectrum quantities, such as the received signal strength at each grid point within a geographic region, based on measurements from a subset of spatially distributed nodes (represented as pixels). Recently, deep vision models such as the U-Net have been adapted to radio map estimation, whose effectiveness can be guaranteed with sufficient spatial observations (typically 0.01% to 1% of pixels) in each map, to model local dependency of observed signal power. However, such a setting of sufficient measurements can be less practical in real-world scenarios, where extreme sparsity in spatial sampling can be widely encountered. To address this challenge, we propose RadioFormer, a novel multiple-granularity transformer designed to handle the constraints posed by spatial sparse observations. Our RadioFormer, through a dual-stream self-attention (DSA) module, can respectively discover the correlation of pixel-wise observed signal power and also learn patch-wise buildings' geometries in a style of multiple granularities, which are integrated into multi-scale representations of radio maps by a cross stream cross-attention (CCA) module. Extensive experiments on the public RadioMapSeer dataset demonstrate that RadioFormer outperforms state-of-the-art methods in radio map estimation while maintaining the lowest computational cost. Furthermore, the proposed approach exhibits exceptional generalization capabilities and robust zero-shot performance, underscoring its potential to advance radio map estimation in a more practical setting with very limited observation nodes.

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $\tau$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source both the synthetic data collected and the trained xLAM-2-fc-r models to advance research in AI agents. Models are available on HuggingFace at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4 and project website is https://apigen-mt.github.io

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models

Action models are essential for enabling autonomous agents to perform complex tasks. However, training large action models remains challenging due to the diversity of agent environments and the complexity of agentic data. Despite growing interest, existing infrastructure provides limited support for scalable, agent-specific fine-tuning. We present ActionStudio, a lightweight and extensible data and training framework designed for large action models. ActionStudio unifies heterogeneous agent trajectories through a standardized format, supports diverse training paradigms including LoRA, full fine-tuning, and distributed setups, and integrates robust preprocessing and verification tools. We validate its effectiveness across both public and realistic industry benchmarks, demonstrating strong performance and practical scalability. We open-sourced code and data at https://github.com/SalesforceAIResearch/xLAM to facilitate research in the community.

Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment

Despite the similar structures of human faces, existing face alignment methods cannot learn unified knowledge from multiple datasets with different landmark annotations. The limited training samples in a single dataset commonly result in fragile robustness in this field. To mitigate knowledge discrepancies among different datasets and train a task-agnostic unified face alignment (TUFA) framework, this paper presents a strategy to unify knowledge from multiple datasets. Specifically, we calculate a mean face shape for each dataset. To explicitly align these mean shapes on an interpretable plane based on their semantics, each shape is then incorporated with a group of semantic alignment embeddings. The 2D coordinates of these aligned shapes can be viewed as the anchors of the plane. By encoding them into structure prompts and further regressing the corresponding facial landmarks using image features, a mapping from the plane to the target faces is finally established, which unifies the learning target of different datasets. Consequently, multiple datasets can be utilized to boost the generalization ability of the model. The successful mitigation of discrepancies also enhances the efficiency of knowledge transferring to a novel dataset, significantly boosts the performance of few-shot face alignment. Additionally, the interpretable plane endows TUFA with a task-agnostic characteristic, enabling it to locate landmarks unseen during training in a zero-shot manner. Extensive experiments are carried on seven benchmarks and the results demonstrate an impressive improvement in face alignment brought by knowledge discrepancies mitigation.

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI models to access and interpret a user's private data (e.g., conversation history, user-AI interactions, app usage) to understand personal details such as biographical information, preferences, and social connections. However, due to the sensitive nature of such data, there are no publicly available datasets that allow us to assess an AI model's ability to understand users through direct access to personal information. To address this gap, we introduce a synthetic data generation pipeline that creates diverse, realistic user profiles and private documents simulating human activities. Leveraging this synthetic data, we present PersonaBench, a benchmark designed to evaluate AI models' performance in understanding personal information derived from simulated private user data. We evaluate Retrieval-Augmented Generation (RAG) pipelines using questions directly related to a user's personal information, supported by the relevant private documents provided to the models. Our results reveal that current retrieval-augmented AI models struggle to answer private questions by extracting personal information from user documents, highlighting the need for improved methodologies to enhance personalization capabilities in AI.

Unsupervised Patch-GAN with Targeted Patch Ranking for Fine-Grained Novelty Detection in Medical Imaging

Detecting novel anomalies in medical imaging is challenging due to the limited availability of labeled data for rare abnormalities, which often display high variability and subtlety. This challenge is further compounded when small abnormal regions are embedded within larger normal areas, as whole-image predictions frequently overlook these subtle deviations. To address these issues, we propose an unsupervised Patch-GAN framework designed to detect and localize anomalies by capturing both local detail and global structure. Our framework first reconstructs masked images to learn fine-grained, normal-specific features, allowing for enhanced sensitivity to minor deviations from normality. By dividing these reconstructed images into patches and assessing the authenticity of each patch, our approach identifies anomalies at a more granular level, overcoming the limitations of whole-image evaluation. Additionally, a patch-ranking mechanism prioritizes regions with higher abnormal scores, reinforcing the alignment between local patch discrepancies and the global image context. Experimental results on the ISIC 2016 skin lesion and BraTS 2019 brain tumor datasets validate our framework's effectiveness, achieving AUCs of 95.79% and 96.05%, respectively, and outperforming three state-of-the-art baselines.

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. Despite notable progress in recent years, current RVOS models remain struggle to handle complicated object descriptions due to their limited video-language understanding. To address this limitation, we present \textbf{ReferDINO}, an end-to-end RVOS model that inherits strong vision-language understanding from the pretrained visual grounding foundation models, and is further endowed with effective temporal understanding and object segmentation capabilities. In ReferDINO, we contribute three technical innovations for effectively adapting the foundation models to RVOS: 1) an object-consistent temporal enhancer that capitalizes on the pretrained object-text representations to enhance temporal understanding and object consistency; 2) a grounding-guided deformable mask decoder that integrates text and grounding conditions to generate accurate object masks; 3) a confidence-aware query pruning strategy that significantly improves the object decoding efficiency without compromising performance. We conduct extensive experiments on five public RVOS benchmarks to demonstrate that our proposed ReferDINO outperforms state-of-the-art methods significantly. Project page: \url{https://isee-laboratory.github.io/ReferDINO}

Hengqin-RA-v1: Advanced Large Language Model for Diagnosis and Treatment of Rheumatoid Arthritis with Dataset based Traditional Chinese Medicine

Large language models (LLMs) primarily trained on English texts, often face biases and inaccuracies in Chinese contexts. Their limitations are pronounced in fields like Traditional Chinese Medicine (TCM), where cultural and clinical subtleties are vital, further hindered by a lack of domain-specific data, such as rheumatoid arthritis (RA). To address these issues, this paper introduces Hengqin-RA-v1, the first large language model specifically tailored for TCM with a focus on diagnosing and treating RA. We also present HQ-GCM-RA-C1, a comprehensive RA-specific dataset curated from ancient Chinese medical literature, classical texts, and modern clinical studies. This dataset empowers Hengqin-RA-v1 to deliver accurate and culturally informed responses, effectively bridging the gaps left by general-purpose models. Extensive experiments demonstrate that Hengqin-RA-v1 outperforms state-of-the-art models, even surpassing the diagnostic accuracy of TCM practitioners in certain cases.

Bridging the Data Provenance Gap Across Text, Speech and Video

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video.