Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2604. 06367v2 Announce Type: replace-cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries.
arXiv:2606. 19259v1 Announce Type: cross Abstract: Text-rich images often contain privacy-sensitive, transactional, or decision-relevant information.
arXiv:2606. 18385v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs.
arXiv:2505. 03646v5 Announce Type: replace-cross Abstract: Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions.
arXiv:2606. 18266v1 Announce Type: cross Abstract: EMORSION is an exploratory proof-of-concept study examining how film audio design shapes audience emotion and immersion in acinema setting.
arXiv:2606. 18839v1 Announce Type: new Abstract: Vision-language models (VLMs) are now widely used in downstream tasks.
arXiv:2606. 18824v1 Announce Type: cross Abstract: Pedestrian trajectory prediction from an ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intention of the pedestrian.
arXiv:2606. 18988v1 Announce Type: new Abstract: Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms.
arXiv:2606. 18976v1 Announce Type: cross Abstract: Automated assessment in software engineering education has advanced significantly for code grading and essay scoring.
arXiv:2606. 19253v1 Announce Type: cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning.
arXiv:2606. 19120v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target.
arXiv:2509. 22363v4 Announce Type: replace Abstract: Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks.
arXiv:2606. 18950v1 Announce Type: new Abstract: Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.
arXiv:2606. 18363v1 Announce Type: cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents.
arXiv:2603. 15988v3 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies.
We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image reconstruction. The image domain is partitioned into non-overlapping square patches, each carrying coefficients for a truncated Fourier basis predicted from shared convolutional-encoder features.
Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control.
AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining.
Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion.
Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference cost from multi-step diffusion.