Latest papers

70 papers28 papers in the last four weeks, up 367% on the four weeks before. 0.2% of all new papers.

Feb 28, 2026

UNICBench: UNIfied Counting Benchmark for MLLM

Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi level counting benchmark and evaluation toolkit with accurate ground truth, deterministic numeric parsing, and stratified reporting. The corpus comprises 5,300 images (5,508 QA), 872 documents (5,888 QA), and 2,069 audio clips (2,905 QA), annotated with a three level capability taxonomy and difficulty tags. Under a standardized protocol with fixed splits/prompts/seeds and modality specific matching rules, we evaluate 45 state-of-the-art MLLMs across modalities. Results show strong performance on some basic counting tasks but significant gaps on reasoning and the hardest partitions, highlighting long-tail errors and substantial headroom for improving general counting. UNICBench offers a rigorous and comparable basis for measurement and a public toolkit to accelerate progress.
Feb 23, 2026

Multimodal Dataset Distillation Made Simple by Prototype-Guided Data Synthesis

Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in dataset filtering and pruning attempt to mitigate this issue, but still require relatively large subsets to maintain performance and fail under very small subsets. Dataset distillation offers a promising alternative, yet existing multimodal dataset distillation methods require full-dataset training and joint optimization of image pixels and text features, making them architecture-dependent and limiting cross-architecture generalization. To overcome this, we propose a learning-free dataset distillation framework that eliminates the need for large-scale training and optimization while enhancing generalization across architectures. Our method uses CLIP to extract aligned image-text embeddings, obtains prototypes, and employs an unCLIP decoder to synthesize images, enabling efficient and scalable multimodal dataset distillation. Extensive experiments demonstrate that our approach consistently outperforms optimization-based dataset distillation and subset selection methods, achieving state-of-the-art cross-architecture generalization.
Jan 29, 2026

SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding

Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process sequential audio-video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting. We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of 60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summarization, multiple-choice question (MCQ) answering, and temporal localization with supporting rationales (reasoning). Across closed- and open-source models, we find that the MCQ accuracy shows the smallest gap between model families, but the best closed-source model outperforms the best open-source model by 22.6% on temporal localization. We further observe accuracy gaps of up to 21.4% on temporal localization across demographic groups, indicating persistent disparities in model behaviour. SONIC-O1 provides an open evaluation suite for temporally grounded and demographically robust multimodal understanding. SONIC-O1 is publicly available for research: Project page (https://vectorinstitute.github.io/sonic-o1/), Dataset (https://huggingface.co/datasets/vector-institute/sonic-o1), GitHub (https://github.com/vectorinstitute/sonic-o1), Leaderboard (https://huggingface.co/spaces/vector-institute/sonic-o1-leaderboard).
Jan 17, 2026

DAOS: A Multimodal In-cabin Behavior Monitoring with Driver Action-Object Synergy Dataset

Multimodal action understanding requires complementary sensory observations to be connected with structured semantic knowledge. This is particularly challenging in vehicle cabins, where fine-grained actions exhibit similar upper-body motion, relevant objects may be small or occluded, and appearance varies substantially across illumination conditions. Existing in-cabin datasets, however, rarely provide synchronized visual modalities together with dense object annotations and explicit action--object alignment, limiting the study of object-grounded multimodal recognition. To address this gap, we introduce the Driver Action with Object Synergy (DAOS) dataset, containing 9,787 video clips, 36 fine-grained actions, 15 object categories, and more than 2.5 million annotated object instances. DAOS provides synchronized RGB, infrared, and depth observations from four camera views, thereby combining complementary appearance, low-light, and geometric information. Building on DAOS, we propose the Action-Object-Relation Network (AOR-Net), a vision-language framework that organizes multimodal understanding at three semantic levels: action, object, and human-object relation. Its Chain-of-action Prompting mechanism progressively grounds global motion with localized object and relation cues, while a textual prototype bank supplies corresponding semantic descriptions. A Mixture of Thoughts module then dynamically selects and integrates the most informative semantic levels and visual modalities under object-rich and object-scarce conditions. Extensive experiments show that AOR-Net consistently outperforms strong baselines on DAOS, demonstrating the effectiveness of combining heterogeneous visual sensing with structured action-object-relation semantics for fine-grained multimodal video understanding.
Nov 20, 2025

Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report

Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial governance, transforming capital allocation architectures, regulatory frameworks, and systemic risk coordination mechanisms. However, as the core medium for assessing corporate ESG performance, the ESG reports present significant challenges for large-scale understanding, due to chaotic reading order from slide-like irregular layouts and implicit hierarchies arising from lengthy, weakly structured content. To address these challenges, we propose Pharos-ESG, a unified framework that transforms ESG reports into structured representations through multimodal parsing, contextual narration, and hierarchical labeling. It integrates a reading-order modeling module based on layout flow, hierarchy-aware segmentation guided by table-of-contents anchors, and a multi-modal aggregation pipeline that contextually transforms visual elements into coherent natural language. The framework further enriches its outputs with ESG, GRI, and sentiment labels, yielding annotations aligned with the analytical demands of financial research. Extensive experiments on annotated benchmarks demonstrate that Pharos-ESG consistently outperforms both dedicated document parsing systems and general-purpose multimodal models. In addition, we release Aurora-ESG, the first large-scale public dataset of ESG reports, spanning Mainland China, Hong Kong, and U.S. markets, featuring unified structured representations of multi-modal content, enriched with fine-grained layout and semantic annotations to better support ESG integration in financial governance and decision-making.
Oct 27, 2025

M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset

Existing real-world datasets for multimodal fact-checking have multiple limitations: they contain few instances, cover only one or two languages, focus on a single task, or rely on external news article sets to source true claims. To address these shortcomings, we introduce M4FC, a new real-world dataset comprising 4,982 images paired with 6,980 claims. The images, verified by professional fact-checkers from 22 organizations, represent a diverse range of cultural and geographic contexts. Each claim is available in one or two out of ten languages. M4FC spans six multimodal fact-checking tasks: visual claim extraction, claimant intent prediction, fake image detection, image contextualization, location verification, and verdict prediction. We provide baseline results for all tasks and analyze how combining intermediate tasks affects verdict prediction performance. We make our dataset and code publicly available.
Sep 1, 2025

REVELIO: Universal Multimodal Task Load Estimation for Cross-Domain Generalization

Adaptive interactive systems that respond to user mental state require task load estimation that stays reliable outside its training context. Models built in one setting rarely transfer, limiting real-world use. This work presents Robust Estimation Via End-to-End Learning of Multimodal Observations (REVELIO), a unified framework, dataset and evaluation protocol for cross-domain task load estimation. Cardiac, electrodermal, muscle, respiration, skin temperature, eye tracking and facial signals were recorded in 96 sessions, spanning a laboratory working memory task, a driving simulator and two games under consistent hardware and annotation. Multimodal fusion reached up to 0.87 area under the receiver operating characteristic curve, above single input eye tracking (0.83), facial action units (0.74) and biosignals (0.62). Multi-domain training stayed calibrated on domains seen in training, whereas removing the target domain caused the classifier to collapse in some applications. REVELIO provides a standardized foundation for measuring modality contributions and cross-domain generalization toward deployable workload-aware systems.
May 22, 2025

MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph

Medical deep learning models depend heavily on domain-specific knowledge to perform well on knowledge-intensive clinical tasks. Prior work has primarily leveraged unimodal knowledge graphs, such as the Unified Medical Language System (UMLS), to enhance model performance. However, integrating multimodal medical knowledge graphs remains largely underexplored, mainly due to the lack of resources linking imaging data with clinical concepts. To address this gap, we propose MEDMKG, a Medical Multimodal Knowledge Graph that unifies visual and textual medical information through a multi-stage construction pipeline. MEDMKG fuses the rich multimodal data from MIMIC-CXR with the structured clinical knowledge from UMLS, utilizing both rule-based tools and large language models for accurate concept extraction and relationship modeling. To ensure graph quality and compactness, we introduce Neighbor-aware Filtering (NaF), a novel filtering algorithm tailored for multimodal knowledge graphs. We evaluate MEDMKG across three tasks under two experimental settings, benchmarking twenty-four baseline methods and four state-of-the-art vision-language backbones on six datasets. Results show that MEDMKG not only improves performance in downstream medical tasks but also offers a strong foundation for developing adaptive and robust strategies for multimodal knowledge integration in medical artificial intelligence.
Mar 9, 2025

PDB: Not All Drivers Are the Same -- A Personalized Dataset for Understanding Driving Behavior

Driving behavior varies across individuals, yet most existing driving datasets do not preserve driver identity or control for factors that may affect driving style. We introduce the Personalized Driving Behavior (PDB) dataset, a multimodal dataset collected from 9 drivers using the same vehicle and route under comparable conditions. PDB includes data from a 128-line LiDAR, external and driver-facing cameras, GNSS, IMU, CAN-bus signals, and heart-rate measurements, with 111,060 frames of LiDAR point cloud data and more than 1.33 million images. Based on these recordings, we construct PDB-Traj, a personalized trajectory prediction benchmark with 1,309 10-second trajectory segments sampled at 10 Hz. Each segment includes the ego trajectory, surrounding-agent trajectories, and driver identity. We further introduce Gated Selective Personalization (Gate-SP), a driver-aware baseline that selectively incorporates driver identity into trajectory prediction. Experiments on PDB-Traj provide reference results for personalized motion forecasting and show that driver information can improve prediction when applied selectively. PDB and PDB-Traj provide a benchmark for studying driver-specific behavior and personalized trajectory prediction.
Feb 14, 2025

MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception

The ability to observe the world is fundamental to reasoning and making informed decisions on how to interact with the environment. However, optical perception can often be disrupted due to common occurrences like occlusions, which can pose challenges to existing vision systems. We present MITO, the first millimeter-wave (mmWave) dataset of diverse, everyday objects, collected using a UR5 robotic arm with two mmWave radars operating at different frequencies and an RGB-D camera. Unlike visible light, mmWave signals can penetrate common occlusions (e.g., cardboard boxes, fabric, plastic). MITO captures over 24 million mmWave frames and uses them to generate 550 high-resolution mmWave images in line-of-sight and non-light-of-sight (NLOS), as well as RGB-D images, segmentation masks, and raw mmWave signals, taken from 76 different objects. We develop an open-source simulation tool that can be used to generate synthetic mmWave images for any 3D triangle mesh. Finally, we establish benchmarks for NLOS segmentation and classification to demonstrate the utility of our dataset and simulator for enabling broader NLOS perception.