Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems. To overcome these issues, we introduce a decentralized state-based value learning algorithm that enables agents to independently discover optimal states. Furthermore, we introduce a novel mechanism for multi-agent interaction, wherein less proficient agents follow and adopt policies from more experienced ones, thereby indirectly guiding their learning process. Our theoretical analysis shows that our approach leads decentralized agents to an optimal collective policy. Empirical experiments further demonstrate that our method outperforms existing decentralized state-based and action-based value learning strategies by effectively identifying and aligning optimal objectives.
相關內容
Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding layers, coupled with an absolute position encoding expansion. Additionally, we enrich text prompts by large vision-language model, leading to better images captions and possess higher visual quality. These enhancements are subsequently applied to downstream text-to-image models. Our empirical results indicate that the developed CLIP model excels in bilingual image-text retrieval.Furthermore, the bilingual image generation capabilities of Taiyi-Diffusion-XL surpass previous models. This research leads to the development and open-sourcing of the Taiyi-Diffusion-XL model, representing a notable advancement in the field of image generation, particularly for Chinese language applications. This contribution is a step forward in addressing the need for more diverse language support in multimodal research. The model and demonstration are made publicly available at \href{//huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B/}{this https URL}, fostering further research and collaboration in this domain.
Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and independent client treatment. To address these challenges, we propose GPFL, which measures client value by comparing local and global descent directions. We also employ an Exploit-Explore mechanism to enhance performance. Experimental results on FEMINST and CIFAR-10 datasets demonstrate that GPFL outperforms baselines in Non-IID scenarios, achieving over 9\% improvement in FEMINST test accuracy. Moreover, GPFL exhibits shorter computation times through pre-selection and parameter reuse in federated learning.
Handling bound identifiers correctly and efficiently is critical in implementations of compilers, proof assistants, and theorem provers. When choosing a representation for abstract syntax with binders, implementors face a trade-off between type safety with intrinsic scoping, efficiency, and generality. The "foil" by Maclaurin, Radul, and Paszke combines an efficient implementation of the Barendregt convention with intrinsic scoping through advanced type system features in Haskell, such as rank-2 polymorphism and generalized algebraic data types. Free scoped monads of Kudasov, on the other hand, combine intrinsic scoping with de Bruijn indices as nested data types with Sweirstra's data types \`a la carte approach to allow generic implementation of algorithms such as higher-order unification. In this paper, we suggest two approaches of making the foil more affordable. First, we marry free scoped monads with the foil, allowing to generate efficient, type-safe, and generic abstract syntax representation with binders for any language given its second-order signature. Second, we provide Template Haskell functions that allow generating the scope-safe representation from a na\"ive one. The latter approach enables us to use existing tools like BNF Converter to very quickly prototype complete implementation of languages, including parsing, pretty-printing, and efficient intrinsically scoped abstract syntax. We demonstrate both approaches using $\lambda\Pi$ with pairs and patterns as our example object language. Finally, we provide benchmarks comparing our implementation against the foil, free scoped monads with nested de Bruijn indices, and some traditional implementations.
In order for robots to interact with objects effectively, they must understand the form and function of each object they encounter. Essentially, robots need to understand which actions each object affords, and where those affordances can be acted on. Robots are ultimately expected to operate in unstructured human environments, where the set of objects and affordances is not known to the robot before deployment (i.e. the open-vocabulary setting). In this work, we introduce OVAL-Prompt, a prompt-based approach for open-vocabulary affordance localization in RGB-D images. By leveraging a Vision Language Model (VLM) for open-vocabulary object part segmentation and a Large Language Model (LLM) to ground each part-segment-affordance, OVAL-Prompt demonstrates generalizability to novel object instances, categories, and affordances without domain-specific finetuning. Quantitative experiments demonstrate that without any finetuning, OVAL-Prompt achieves localization accuracy that is competitive with supervised baseline models. Moreover, qualitative experiments show that OVAL-Prompt enables affordance-based robot manipulation of open-vocabulary object instances and categories. Project Page: //ekjt.github.io/OVAL-Prompt/
Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations similar to those encountered in supervised learning, e.g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size. In this work, we consider the problem of automatic curation of high-quality datasets for self-supervised pre-training. We posit that such datasets should be large, diverse and balanced, and propose a clustering-based approach for building ones satisfying all these criteria. Our method involves successive and hierarchical applications of $k$-means on a large and diverse data repository to obtain clusters that distribute uniformly among data concepts, followed by a hierarchical, balanced sampling step from these clusters. Extensive experiments on three different data domains including web-based images, satellite images and text show that features trained on our automatically curated datasets outperform those trained on uncurated data while being on par or better than ones trained on manually curated data.
Soft tissue tracking is crucial for computer-assisted interventions. Existing approaches mainly rely on extracting discriminative features from the template and videos to recover corresponding matches. However, it is difficult to adopt these techniques in surgical scenes, where tissues are changing in shape and appearance throughout the surgery. To address this problem, we exploit optical flow to naturally capture the pixel-wise tissue deformations and adaptively correct the tracked template. Specifically, we first implement an inter-frame matching mechanism to extract a coarse region of interest based on optical flow from consecutive frames. To accommodate appearance change and alleviate drift, we then propose an adaptive-template matching method, which updates the tracked template based on the reliability of the estimates. Our approach, Ada-Tracker, enjoys both short-term dynamics modeling by capturing local deformations and long-term dynamics modeling by introducing global temporal compensation. We evaluate our approach on the public SurgT benchmark, which is generated from Hamlyn, SCARED, and Kidney boundary datasets. The experimental results show that Ada-Tracker achieves superior accuracy and performs more robustly against prior works. Code is available at //github.com/wrld/Ada-Tracker.
We construct quantum public-key encryption from one-way functions. In our construction, public keys are quantum, but ciphertexts are classical. Quantum public-key encryption from one-way functions (or weaker primitives such as pseudorandom function-like states) are also proposed in some recent works [Morimae-Yamakawa, eprint:2022/1336; Coladangelo, eprint:2023/282; Barooti-Grilo-Malavolta-Sattath-Vu-Walter, eprint:2023/877]. However, they have a huge drawback: they are secure only when quantum public keys can be transmitted to the sender (who runs the encryption algorithm) without being tampered with by the adversary, which seems to require unsatisfactory physical setup assumptions such as secure quantum channels. Our construction is free from such a drawback: it guarantees the secrecy of the encrypted messages even if we assume only unauthenticated quantum channels. Thus, the encryption is done with adversarially tampered quantum public keys. Our construction is the first quantum public-key encryption that achieves the goal of classical public-key encryption, namely, to establish secure communication over insecure channels, based only on one-way functions. Moreover, we show a generic compiler to upgrade security against chosen plaintext attacks (CPA security) into security against chosen ciphertext attacks (CCA security) only using one-way functions. As a result, we obtain CCA secure quantum public-key encryption based only on one-way functions.
Collaborative trajectory prediction can comprehensively forecast the future motion of objects through multi-view complementary information. However, it encounters two main challenges in multi-drone collaboration settings. The expansive aerial observations make it difficult to generate precise Bird's Eye View (BEV) representations. Besides, excessive interactions can not meet real-time prediction requirements within the constrained drone-based communication bandwidth. To address these problems, we propose a novel framework named "Drones Help Drones" (DHD). Firstly, we incorporate the ground priors provided by the drone's inclined observation to estimate the distance between objects and drones, leading to more precise BEV generation. Secondly, we design a selective mechanism based on the local feature discrepancy to prioritize the critical information contributing to prediction tasks during inter-drone interactions. Additionally, we create the first dataset for multi-drone collaborative prediction, named "Air-Co-Pred", and conduct quantitative and qualitative experiments to validate the effectiveness of our DHD framework.The results demonstrate that compared to state-of-the-art approaches, DHD reduces position deviation in BEV representations by over 20% and requires only a quarter of the transmission ratio for interactions while achieving comparable prediction performance. Moreover, DHD also shows promising generalization to the collaborative 3D object detection in CoPerception-UAVs.
This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies. Motivated by critical applications, we move beyond point estimators. Instead, we adopt the principle of pessimism where we construct upper bounds that assess a policy's worst-case performance, enabling us to confidently select and learn improved policies. Precisely, we introduce novel, fully empirical concentration bounds for a broad class of importance weighting risk estimators. These bounds are general enough to cover most existing estimators and pave the way for the development of new ones. In particular, our pursuit of the tightest bound within this class motivates a novel estimator (LS), that logarithmically smooths large importance weights. The bound for LS is provably tighter than all its competitors, and naturally results in improved policy selection and learning strategies. Extensive policy evaluation, selection, and learning experiments highlight the versatility and favorable performance of LS.
Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: //github.com/MikeWangWZHL/Solo-Performance-Prompting.git.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191