Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.
arXiv:2607. 02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns.
arXiv:2607. 03210v1 Announce Type: cross Abstract: Standard machine learning training presents data as discrete endpoint pairs, omitting the structure of the space between them.
arXiv:2607. 05276v1 Announce Type: cross Abstract: Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstream applications.
arXiv:2607. 03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost.
arXiv:2607. 04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaque latent feature spaces.
arXiv:2607. 04814v1 Announce Type: cross Abstract: Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the prohibitive demands of data collection at scale.
arXiv:2607. 05364v1 Announce Type: cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or inference-time post-processing.
arXiv:2508. 01858v3 Announce Type: replace-cross Abstract: Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition.
arXiv:2607. 04727v1 Announce Type: cross Abstract: Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static charts and overlook the interactive dashboards commonly used for real-world data exploration.
arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.
arXiv:2607. 03358v1 Announce Type: cross Abstract: We study how visual information is routed in vision-language models (VLMs).
arXiv:2607. 04147v1 Announce Type: cross Abstract: Automated fine-grained perception of calligraphy styles--a task vital to cultural heritage preservation--remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels.
arXiv:2607. 04163v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering.
arXiv:2607. 05377v1 Announce Type: cross Abstract: While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations.
arXiv:2512. 14926v2 Announce Type: replace-cross Abstract: Focusing on low-resource languages is an essential step toward democratizing generative AI.
arXiv:2607. 04541v1 Announce Type: cross Abstract: Camera-radar (CR) fusion is a practical sensing configuration for autonomous driving, but existing models are typically trained with task-specific supervision, limiting reusable representation learning.
arXiv:2601. 06550v3 Announce Type: replace-cross Abstract: Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding.
arXiv:2510. 05681v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control.
arXiv:2602. 14401v2 Announce Type: replace-cross Abstract: Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns.