arXiv AI
Jul 7
Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding
arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.
Multimodal models
Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv Machine Learning
Jul 7
KinEMbed: Decoding Kinematics from Electromyography via Cross-Modal Contrastive Learning
arXiv:2607. 04820v1 Announce Type: new Abstract: Decoding hand kinematics from surface electromyography (EMG) is a core challenge in wearable biosignal processing with clinical relevance for prosthetic control and motor rehabilitation.
arXiv AI
Jul 7
Unveiling Stochasticity: Universal Multi-modal Probabilistic Modeling for Traffic Forecasting
arXiv:2604. 16084v2 Announce Type: replace-cross Abstract: Traffic forecasting is a challenging spatio-temporal modeling task and a critical component of urban transportation management.
arXiv Machine Learning
Jul 7
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
arXiv:2607. 02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling.
arXiv AI
Jul 7
Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
arXiv:2607. 02588v1 Announce Type: cross Abstract: Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally under limited memory.
arXiv AI
Jul 7
MentalThink: Shaping Thoughts in Mental SVG World
arXiv:2607. 03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization.
arXiv AI
Jul 7
Transferability Between Understanding and Generation in Unified Multimodal Models
arXiv:2607. 04423v1 Announce Type: cross Abstract: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied.
arXiv Machine Learning
Jul 7
Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
arXiv:2607. 05019v1 Announce Type: new Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks.
arXiv Machine Learning
Jul 7
USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning
arXiv:2607. 03900v1 Announce Type: cross Abstract: Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision-language models (e.
arXiv AI
Jul 7
ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation
arXiv:2607. 03657v1 Announce Type: cross Abstract: Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sentences without gloss annotations, avoiding costly labeling but requiring fine-grained modeling of hands, body, and facial cues.
arXiv AI
Jul 7
Gemma 4 Technical Report
arXiv:2607. 02770v1 Announce Type: cross Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family.
arXiv AI
Jul 7
VISTA: Auditing Semantic Divergence in Vision-Language Models
arXiv:2607. 02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideological symbols, some models produce unusually uniform responses that differ from what peer models say about the same input.
arXiv Machine Learning
Jul 7
Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features
arXiv:2607. 02553v1 Announce Type: cross Abstract: Introduction: Objective neuroimaging biomarkers may improve Parkinson's disease motor assessment by capturing brain variation not directly observable from clinical examination.
arXiv AI
Jul 7
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
arXiv:2607. 02551v1 Announce Type: cross Abstract: Video multimodal large language models have made strong progress on open-ended video understanding, but they still lack precise local spatiotemporal perception.
arXiv AI
Jul 7
DOSE-I: A Multimodal Biosignal Dataset of Procedural Sedation for Endoscopy -- Technical Report
arXiv:2607. 02570v1 Announce Type: cross Abstract: In this document, we describe characteristics and technical details of the multimodal biosignal dataset DOSE-I of procedural sedation for endoscopy published on zenodo.
arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
arXiv AI
Jul 7
Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering
arXiv:2607. 04079v1 Announce Type: cross Abstract: Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks.
arXiv AI
Jul 7
HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
arXiv:2607. 03449v1 Announce Type: cross Abstract: Current Vision-Language-Action (VLA) models excel at robotic manipulation but often struggle with non-Markovian tasks requiring long-term memory and reasoning due to their reliance on immediate observations.
arXiv AI
Jul 7
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
arXiv:2607. 04591v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation by integrating visual perception, language understanding, and robot action generation.
arXiv AI
Jul 7
VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
arXiv:2607. 02927v1 Announce Type: cross Abstract: Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR).