Related papers: Ruyi2.5 Technical Report

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making,…

Current research on trajectory prediction primarily relies on data collected by onboard sensors of an ego vehicle. With the rapid advancement in connected technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I)…

Unified vision-language models have made significant progress in multimodal understanding and generation, yet they largely fall short in producing multimodal interleaved outputs, which is a crucial capability for tasks like visual…

With the advancement of Artificial Intelligence (AI) towards multiple modalities (language, vision, speech, etc.), multi-modal models have increasingly been used across various applications (e.g., visual question answering or image…

GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging. In this report, we present UI-Venus-1.5, a…

We present DeFlow, a decoupled offline RL framework that leverages flow matching to faithfully capture complex behavior manifolds. Optimizing generative policies is computationally prohibitive, typically necessitating backpropagation…

Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity…

Multimodal sentiment analysis benefits various applications such as human-computer interaction and recommendation systems. It aims to infer the users' bipolar ideas using visual, textual, and acoustic signals. Although researchers affirm…

This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two…

Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge: the extrapolation error stemming from out-of-distribution…

The next generation of AI applications will continuously interact with the environment and learn from these interactions. These applications impose new and demanding systems requirements, both in terms of performance and flexibility. In…

Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to…

Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…

The exponential growth of the number of multihomed mobile devices is changing the way how we can connect to the Internet. Our mobile devices are demanding for more network resources, in terms of traffic volume and QoS requirements.…

Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which…

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To…

Pedestrian action recognition and intention prediction is one of the core issues in the field of autonomous driving. In this research field, action recognition is one of the key technologies. A large number of scholars have done a lot of…

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a…

In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises of following three…

We present Qianfan-VL, a series of multimodal large language models ranging from 3B to 70B parameters, achieving state-of-the-art performance through innovative domain enhancement techniques. Our approach employs multi-stage progressive…