The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by the challenges of interacting with the live internet, which is inefficient, costly, and fraught with risks. Model-based reinforcement learning (MBRL) offers a promising solution by learning a world model of the environment to enable simulated interaction. This paper introduces DynaWeb, a novel MBRL framework that trains web agents through interacting with a web world model trained to predict naturalistic web page representations given agent actions. This model serves as a synthetic web environment where an agent policy can dream by generating vast quantities of rollout action trajectories for efficient online reinforcement learning. Beyond free policy rollouts, DynaWeb incorporates real expert trajectories from training data, which are randomly interleaved with on-policy rollouts during training to improve stability and sample efficiency. Experiments conducted on the challenging WebArena and WebVoyager benchmarks demonstrate that DynaWeb consistently and significantly improves the performance of state-of-the-art open-source web agent models. Our findings establish the viability of training web agents through imagination, offering a scalable and efficient way to scale up online agentic RL.

Gloss-free Sign Language Translation (SLT) avoids costly gloss annotations but remains limited by weak visual-text alignment. Recent MLLM-based methods use frame descriptions as auxiliary supervision, yet these descriptions are often repetitive, producing nearly identical text features; meanwhile, global pooling washes out sparse but meaningful gestures. We propose FiMA (Fine-grained Multimodal Alignment), a pre-training framework for redundancy-aware description enhancement. FiMA combines a Description Enhancement Module, which removes shared template redundancy from description features, with a Multimodal Alignment Module, which aligns each text token to its most relevant visual frame through Max-Sim matching. On PHOENIX14T and CSL-Daily, FiMA achieves state-of-the-art gloss-free SLT performance and visualizations show clearer feature separation and temporal grounding. The code will be released at https://github.com/Ryeliu/FiMA.

Deep generative modeling of natural languages has achieved many successes, such as producing fluent sentences and translating from one language into another. However, the development of generative modeling techniques for paraphrase generation still lags behind largely due to the challenges in addressing the complex conflicts between expression diversity and semantic preservation. This paper proposes to generate diverse and high-quality paraphrases by exploiting the pre-trained models with instance-dependent prompts. To learn generalizable prompts, we assume that the number of abstract transforming patterns of paraphrase generation (governed by prompts) is finite and usually not large. Therefore, we present vector-quantized prompts as the cues to control the generation of pre-trained models. Extensive experiments demonstrate that the proposed method achieves new state-of-art results on three benchmark datasets, including Quora, Wikianswers, and MSCOCO. We will release all the code upon acceptance.