Related papers: Baichuan-Omni-1.5 Technical Report

The evolution of Omni-Modal Large Language Models~(Omni-LLMs) has revolutionized human--computer interaction, enabling unified audio-visual perception and speech response. However, existing Omni-LLMs struggle with complex real-world…

Large language models (LLMs) have unified diverse linguistic tasks within a single framework, yet such unification remains unexplored in human motion generation. Existing methods are confined to isolated tasks, limiting flexibility for…

Accurate and timely prediction of tool conditions is critical for intelligent manufacturing systems, where unplanned tool failures can lead to quality degradation and production downtime. In modern industrial environments, predictive…

Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures,…

The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on…

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides…

Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often face challenges in fine-grained cross-modal understanding and have difficulty with multimodal alignment. To address…

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning…

Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that…

The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides, achieving cohesive multimodal customization for the simultaneous preservation of visual…

We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, time series,…

We introduce Baichuan Alignment, a detailed analysis of the alignment techniques employed in the Baichuan series of models. This represents the industry's first comprehensive account of alignment methodologies, offering valuable insights…

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,…

This tutorial explores recent advancements in multimodal pretrained and large models, capable of integrating and processing diverse data forms such as text, images, audio, and video. Participants will gain an understanding of the…

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

Multimodal Large Language Models (MLLMs) have increasingly supported omni-modal processing across text, vision, and speech. However, existing evaluation frameworks for such models suffer from critical limitations, including modality…

We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-quality web and synthetic data, significantly outperforming recent…

Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under heterogeneous imaging modalities. Such…

We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features:…

Multimodal spatiotemporal learning on real-world experimental data is constrained by two challenges: within-modality measurements are sparse, irregular, and noisy (QA/QC artifacts) but cross-modally correlated; the set of available…