相关论文: OmniNFT: Modality-wise Omni Diffusion Reinforcemen…

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on…

To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which…

Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the distribution that maximize certain properties: for example,…

Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues…

There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST),…

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like…

Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit…

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Multimodal learning with incomplete modality is practical and challenging. Recently, researchers have focused on enhancing the robustness of pre-trained MultiModal Transformers (MMTs) under missing modality conditions by applying learnable…

Multimodal learning has shown great potentials in numerous scenes and attracts increasing interest recently. However, it often encounters the problem of missing modality data and thus suffers severe performance degradation in practice. To…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essential for tasks such as image matting, object removal, layer decomposition, and multi-layer…

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical…

Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with…

Dynamic radio resource management (RRM) in wireless networks presents significant challenges, particularly in the context of Radio Access Network (RAN) slicing. This technology, crucial for catering to varying user requirements, often…

Robust urban autonomous driving requires reliable 3D scene understanding and stable decision-making under dense interactions. However, existing end-to-end models lack interpretability, while modular pipelines suffer from error propagation…

Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with…

Cross-domain offline reinforcement learning (RL) seeks to enhance sample efficiency in offline RL by utilizing additional offline source datasets. A key challenge is to identify and utilize source samples that are most relevant to the…

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…