Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
While text-based hallucination detection has been extensively studied, spoken hallucination detection remains largely unexplored, particularly for low-resource languages. We present the first multilin...
Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, sensor types, viewpoints, and domains to enable co...
Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability...
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only...
The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distinct behavioral, emotional, and cognitive states. A...
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendatio...
arXiv:2608.21928v1 Announce Type: new Abstract: In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied...
arXiv:2608.23138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action tokens, creating brittle...
arXiv:2608.22214v1 Announce Type: new Abstract: In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. Howev...
arXiv:2608.23224v1 Announce Type: cross Abstract: Retrieval can efficiently and effectively augment a frozen vision--language--action (VLA) policy without retraining, yet retrieved text becomes a con...
arXiv:2608.22143v1 Announce Type: new Abstract: Qualitative mechanical problem-solving (QMPS) refers to solving qualitative problems from the mechanical domain. Qualitative problems can be solved wit...
arXiv:2608.21430v1 Announce Type: new Abstract: Multimodal language models increasingly show promise for enabling the large-scale computational analysis of film, opening up new avenues for learning a...
arXiv:2608.22965v1 Announce Type: new Abstract: Accurate extrinsic calibration between event-based and frame-based cameras remains a practical bottleneck for heterogeneous stereo systems. Existing ap...
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv:2608.22713v1 Announce Type: new Abstract: Clinical diagnosis requires progressive integration of patient history, physical examination, laboratory findings, medical images, and diagnostic-infor...
arXiv:2608.23234v1 Announce Type: new Abstract: In this technical report, we present a training-free framework for audio-guided video object segmentation, which integrates Multimodal Large Language M...
arXiv:2608.21830v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diver...
The paper presents a method for the BIC-MAC challenge, aiming to generate pseudo‑CT images from NAC‑PET, DIXON MRI, and a topogram, and to evaluate both the pseudo‑CT and the resulting attenuation‑corrected PET. The authors improve upon a 3D U‑Net baseline by focusing on loss design: they compute an L1 error in the Carney attenuation‑coefficient space, weighted by anatomical region, and incorporate DIXON MRI as additional input only after this loss was applied. Finally, they fuse two independently trained models via a fixed convex combination, achieving better performance than either model alone and topping the public validation leaderboard.
Object-Uni is a unified model that integrates pose perception, spatial reasoning, pose-conditioned generation, and novel view synthesis for object-centric spatial understanding and controllable image generation. It treats object pose as an explicit geometric variable shared across tasks and introduces a viewpoint-based orientation abstraction to make pose interpretable by multimodal large language models. The authors also create a new benchmark, UniSpatial-80K, and demonstrate that Object‑Uni improves both pose understanding and pose‑controllable generation compared to existing models.