Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning

Developing lifelong learning agents is crucial for artificial general intelligence. However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt during training. Despite its significance, this field lacks unified benchmarks and evaluation protocols. We introduce Plasticine, the first open-source framework for benchmarking plasticity optimization in deep RL. Plasticine provides single-file implementations of over 13 mitigation methods, 10 evaluation metrics, and learning scenarios with increasing non-stationarity levels from standard to open-ended environments. This framework enables researchers to systematically quantify plasticity loss, evaluate mitigation strategies, and analyze plasticity dynamics across different contexts. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/Plasticine.

T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models

The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of harmful or unsafe content. Such vulnerabilities undermine the reliability and security of simulation based applications. In this paper, we propose T2VShield, a comprehensive and model agnostic defense framework designed to protect text to video models from jailbreak threats. Our method systematically analyzes the input, model, and output stages to identify the limitations of existing defenses, including semantic ambiguities in prompts, difficulties in detecting malicious content in dynamic video outputs, and inflexible model centric mitigation strategies. T2VShield introduces a prompt rewriting mechanism based on reasoning and multimodal retrieval to sanitize malicious inputs, along with a multi scope detection module that captures local and global inconsistencies across time and modalities. The framework does not require access to internal model parameters and works with both open and closed source systems. Extensive experiments on five platforms show that T2VShield can reduce jailbreak success rates by up to 35 percent compared to strong baselines. We further develop a human centered audiovisual evaluation protocol to assess perceptual safety, emphasizing the importance of visual level defense in enhancing the trustworthiness of next generation multimodal simulators.

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant document from external knowledge sources. By referencing this external knowledge, RAG effectively reduces the generation of factually incorrect content and addresses hallucination issues within LLMs. Recently, there has been growing attention to improving the performance and efficiency of RAG systems from various perspectives. While these advancements have yielded significant results, the application of RAG in domains with considerable societal implications raises a critical question about fairness: What impact does the introduction of the RAG paradigm have on the fairness of LLMs? To address this question, we conduct extensive experiments by varying the LLMs, retrievers, and retrieval sources. Our experimental analysis reveals that the scale of the LLMs plays a significant role in influencing fairness outcomes within the RAG framework. When the model scale is smaller than 8B, the integration of retrieval mechanisms often exacerbates unfairness in small-scale LLMs (e.g., LLaMA3.2-1B, Mistral-7B, and LLaMA3-8B). To mitigate the fairness issues introduced by RAG for small-scale LLMs, we propose two approaches, FairFT and FairFilter. Specifically, in FairFT, we align the retriever with the LLM in terms of fairness, enabling it to retrieve documents that facilitate fairer model outputs. In FairFilter, we propose a fairness filtering mechanism to filter out biased content after retrieval. Finally, we validate our proposed approaches on real-world datasets, demonstrating their effectiveness in improving fairness while maintaining performance.

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion.

A Physics-guided Multimodal Transformer Path to Weather and Climate Sciences

With the rapid development of machine learning in recent years, many problems in meteorology can now be addressed using AI models. In particular, data-driven algorithms have significantly improved accuracy compared to traditional methods. Meteorological data is often transformed into 2D images or 3D videos, which are then fed into AI models for learning. Additionally, these models often incorporate physical signals, such as temperature, pressure, and wind speed, to further enhance accuracy and interpretability. In this paper, we review several representative AI + Weather/Climate algorithms and propose a new paradigm where observational data from different perspectives, each with distinct physical meanings, are treated as multimodal data and integrated via transformers. Furthermore, key weather and climate knowledge can be incorporated through regularization techniques to further strengthen the model's capabilities. This new paradigm is versatile and can address a variety of tasks, offering strong generalizability. We also discuss future directions for improving model accuracy and interpretability.

Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and ensuring robust detection against various attacks. To address these issues, we propose a novel watermarking scheme that improves both detectability and text quality by introducing a cumulative watermark entropy threshold. Our approach is compatible with and generalizes existing sampling functions, enhancing adaptability. Experimental results across multiple LLMs show that our scheme significantly outperforms existing methods, achieving over 80\% improvements on widely-used datasets, e.g., MATH and GSM8K, while maintaining high detection accuracy.

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate, step-by-step thinking. While existing methods have explored text-based slow thinking or rudimentary visual assistance, they fall short of capturing the intricate, interleaved nature of human visual-verbal reasoning processes. To overcome these limitations and inspired by the mechanisms of slow thinking in human cognition, we introduce VisuoThink, a novel framework that seamlessly integrates visuospatial and linguistic domains. VisuoThink facilitates multimodal slow thinking by enabling progressive visual-textual reasoning and incorporates test-time scaling through look-ahead tree search. Extensive experiments demonstrate that VisuoThink significantly enhances reasoning capabilities via inference-time scaling, even without fine-tuning, achieving state-of-the-art performance in tasks involving geometry and spatial reasoning.

Fast-Slow-Thinking: Complex Task Solving with Large Language Models

Nowadays, Large Language Models (LLMs) have been gradually employed to solve complex tasks. To face the challenge, task decomposition has become an effective way, which proposes to divide a complex task into multiple simpler subtasks and then solve them separately so that the difficulty of the original task can be reduced. However, the performance of existing task decomposition methods can be suboptimal when the task contains overly complex logic and constraints. In this situation, the solution generated by LLMs may deviate from the original purpose of the task, or contain redundant or even erroneous content. Therefore, inspired by the fact that humans possess two thinking systems including fast thinking and slow thinking, this paper introduces a new task decomposition method termed ``Fast-Slow-Thinking'' (FST), which stimulates LLMs to solve tasks through the cooperation of Fast Thinking (FT) and Slow Thinking (ST) steps. Here FT focuses more on the general and concise aspect of the task, and ST focuses more on the details of the task. In FT, LLMs are prompted to remove the constraints of the original task, therefore simplifying it to a general and concise one. In ST, we recall the constraints removed in FT, so that LLMs can improve the answer generated in FT to meet the requirements of the original task. Therefore, our FST method enables LLMs to consider a complex problem via a human-like cognition process from coarse to fine, the effectiveness of which has been well demonstrated by the experiments on three types of tasks.

Supervised Optimism Correction: Be Confident When LLMs Are Sure

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit $Q$-function for inference. Through this theoretical lens, we demonstrate that the widely used beam search method suffers from unacceptable over-optimism, where inference errors are inevitably amplified due to inflated $Q$-value estimations of suboptimal steps. To address this limitation, we propose Supervised Optimism Correction(SOC), which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations during supervised fine-tuning. Specifically, the auxiliary loss employs implicit value regularization to boost model confidence in expert-demonstrated responses, thereby suppressing over-optimism toward insufficiently supervised responses. Extensive experiments on mathematical reasoning benchmarks, including GSM8K, MATH, and GAOKAO, showcase the superiority of the proposed SOC with beam search across a series of open-source models.