Multimodal models

Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.

4,396 stories · RSS feed

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

arXiv AI

Jun 30

Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?

arXiv:2606. 29613v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability.

By Yeji Kim, Housam Babiker, Mi-Young Kim, Randy Goebel

diffusion multimodal benchmarks safety

arXiv Machine Learning

Jun 30

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

arXiv:2606. 30319v1 Announce Type: cross Abstract: Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscience.

By Haitao Wu, Qirui Zhang, Zhouheng Yao, Shangquan Sun, Qihao Zheng, Mianxin Liu, Chi Zhang, Wanli Ouyang, Chunfeng Song, Changqing Zhang, Jiamin Wu

nlp multimodal benchmarks safety

arXiv Machine Learning

Jun 30

RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception

arXiv:2606. 28396v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) radar perception is limited by data scarcity: models trained on existing radar datasets fail to generalize to new objects, environments, and sensing trajectories.

By Emily Bejerano, Federico Tondolo, Devang Gupta, Aaron Mano Cherian, Taeyoo Kim, Ayaan Qayyum, Xiaofan Yu, Xiaofan Jiang

llms robotics multimodal

arXiv Machine Learning

Jun 30

From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation

arXiv:2606. 30059v1 Announce Type: new Abstract: Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation to platform-specific data distributions, policy-specific objectives, and product-level safety constraints.

By Shuchang Ye, Jinqiang Yu, Zhujun Xiao, Yajing Kong, Yist Y. Lin, Yang Ma, Jiaxi Liu, Xiaolei Xu, Zheng Yu

llms multimodal benchmarks safety

arXiv AI

Jun 30

GROW$^2$: Grounding Which and Where for Robot Tool Use

arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?

By Yuhong Deng, Yuyao Liu, David Hsu

llms agents robotics multimodal benchmarks

arXiv Machine Learning

Jun 30

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

arXiv:2606. 29719v1 Announce Type: new Abstract: Measurements of proprietary LLM evaluators can become invalid within weeks -- we document one case and provide the diagnostic framework to detect it.

By Liu Zewen

llms agents multimodal benchmarks

arXiv Machine Learning

Jun 30

STEMGym: Benchmarking Sequential Decision-Making under Dose Budgets in Autonomous Electron Microscopy

arXiv:2606. 29592v1 Announce Type: new Abstract: A central premise of autonomous scientific imaging is that smarter navigation, whether Bayesian, RL-based, or otherwise adaptive, is the principal lever for sample-efficient acquisition.

By Can Polat, Erchin Serpedin, Mustafa Kurban, Hasan Kurban

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

Jun 30

Feature-level Interaction Explanations in Multimodal Transformers

arXiv:2603. 13326v2 Announce Type: replace-cross Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision.

By Yeji Kim, Housam Khalifa Bashier Babiker, Mi-Young Kim, Randy Goebel

llms multimodal benchmarks

arXiv AI

Jun 30

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

arXiv:2603. 22282v2 Announce Type: replace-cross Abstract: We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture.

By Ziyi Wang, Xinshun Wang, Shuang Chen, Yang Cong, Mengyuan Liu

llms nlp efficiency multimodal benchmarks safety

arXiv AI

Jun 30

Demonstration-Free Robotic Control via LLM Agents

arXiv:2601. 20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift.

By Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu

llms agents robotics fine-tuning multimodal benchmarks

arXiv AI

Jun 30

EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation

arXiv:2509. 12159v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency.

By Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan, Yintong Huo, Yang Liu, Michael R. Lyu

llms multimodal

arXiv AI

Jun 30

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

arXiv:2606. 30645v1 Announce Type: cross Abstract: Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion.

By Yen-Jen Wang, Jiaman Li, Sirui Chen, Takara E. Truong, Pei Xu, Pieter Abbeel, Rocky Duan, Koushil Sreenath, Angjoo Kanazawa, Carmelo Sferrazza, Guanya Shi, Karen Liu

robotics multimodal

arXiv AI

Jun 30

Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization

arXiv:2606. 30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.

By Liyao Wang, Ruipu Wu, Haojun Xu, Lei Shi, Linjiang Huang, Si Liu

computer-vision robotics multimodal benchmarks

arXiv AI

Jun 30

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

arXiv:2606. 30026v1 Announce Type: cross Abstract: Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.

By Yuxuan Fan, Gyusik Seo, Jing Hao, Jaemin Cho, Mohit Bansal, Jaehong Yoon

llms multimodal benchmarks safety

arXiv AI

Jun 30

Automating the Design of Embodied AgentArchitectures

arXiv:2606. 30111v1 Announce Type: cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.

By Jian Zhou, Sihao Lin, Jin Li, Shuai Fu, Gengze Zhou, Qi Wu

agents nlp robotics efficiency multimodal

arXiv AI

Jun 30

LLM-based Multimodal Personality Recognition via Facial Action Unit-Text Semantic Fusion

arXiv:2606. 29900v1 Announce Type: cross Abstract: Personality recognition in asynchronous video interviews (AVIs) has become increasingly important due to their widespread adoption in modern recruitment.

By Tianyi Zhang, Wei Shan, Yuan Zong, Tianhua Qi, Wenming Zheng

llms rag multimodal benchmarks safety

arXiv AI

Jun 30

Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature

arXiv:2606. 29667v1 Announce Type: cross Abstract: The materials science literature encodes decades of experimental knowledge in figures, yet this visual record remains locked away and inaccessible to AI at scale.

By Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari

llms fine-tuning multimodal safety

arXiv AI

Jun 30

Hybrid Retriever Evolution for Multimodal Document Reasoning Agents

arXiv:2606. 29648v1 Announce Type: cross Abstract: Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that cannot adapt to the demands of individual reasoning steps.

By Bohan Yao, Shruthan Radhakrishna, Vikas Yadav

agents nlp multimodal

arXiv AI

Jun 30

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.

By Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon

llms rag efficiency multimodal benchmarks safety

Get the daily briefing