相关论文: MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid …

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

Over the past decade, neural network solvers powered by generative artificial intelligence have garnered significant attention in the domain of vehicle routing problems (VRPs), owing to their exceptional computational efficiency and…

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong…

Existing offline reinforcement learning (RL) methods face a few major challenges, particularly the distributional shift between the learned policy and the behavior policy. Offline Meta-RL is emerging as a promising approach to address these…

Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches…

While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical application compared to mainstream reconstruction-based general…

Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains…

This paper considers the problem of multi-target detection for massive multiple input multiple output (MMIMO) cognitive radar (CR). The concept of CR is based on the perception-action cycle that senses and intelligently adapts to the…

Radiologists highly desire fully automated AI for radiology report generation (R2G), yet existing approaches fall short in clinical utility. Reinforcement learning (RL) holds potential to address these shortcomings, but its adoption in this…

For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective representation…

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly…

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…

Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and…

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where…

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified convergence guarantees in agentic scenarios, especially in…

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

Recent advances in reinforcement learning (RL) have demonstrated the powerful exploration capabilities and multimodality of generative diffusion-based policies. While substantial progress has been made in offline RL and off-policy RL…