In this work, we propose Graph Retention Network as a unified architecture for deep learning on dynamic graphs. The GRN extends the core computational manner of retention to dynamic graph data as graph retention, which empowers the model with three key computational paradigms that enable training parallelism, $O(1)$ low-cost inference, and long-term batch training. This architecture achieves an optimal balance of effectiveness, efficiency, and scalability. Extensive experiments conducted on benchmark datasets present the superior performance of the GRN in both edge-level prediction and node-level classification tasks. Our architecture achieves cutting-edge results while maintaining lower training latency, reduced GPU memory consumption, and up to an 86.7x improvement in inference throughput compared to baseline models. The GRNs have demonstrated strong potential to become a widely adopted architecture for dynamic graph learning tasks. Code will be available at https://github.com/Chandler-Q/GraphRetentionNet.

Biological lifeforms can heal, grow, adapt, and reproduce -- abilities essential for sustained survival and development. In contrast, robots today are primarily monolithic machines with limited ability to self-repair, physically develop, or incorporate material from their environments. A key challenge to such physical adaptation has been that while robot minds are rapidly evolving new behaviors through AI, their bodies remain closed systems, unable to systematically integrate new material to grow or heal. We argue that open-ended physical adaptation is only possible when robots are designed using only a small repertoire of simple modules. This allows machines to mechanically adapt by consuming parts from other machines or their surroundings and shedding broken components. We demonstrate this principle using a truss modular robot platform composed of one-dimensional actuated bars. We show how robots in this space can grow bigger, faster, and more capable by consuming materials from their environment and from other robots. We suggest that machine metabolic processes akin to the one demonstrated here will be an essential part of any sustained future robot ecology.

This paper builds upon our previous work on the Reconciled Polynomial Network (RPN). The original RPN model was designed under the assumption of input data independence, presuming the independence among both individual instances within data batches and attributes in each data instance. However, this assumption often proves invalid for function learning tasks involving complex, interdependent data such as language, images, time series, and graphs. Ignoring such data interdependence may inevitably lead to significant performance degradation. To overcome these limitations, we introduce the new Reconciled Polynomial Network (version 2), namely RPN 2, in this paper. By incorporating data and structural interdependence functions, RPN 2 explicitly models data interdependence via new component functions in its architecture. This enhancement not only significantly improves RPN 2's learning performance but also substantially expands its unifying potential, enabling it to encompass a broader range of contemporary dominant backbone models within its canonical representation. These backbones include, but are not limited to, convolutional neural networks (CNNs), recurrent neural networks (RNNs), graph neural networks (GNNs), and Transformers. Our analysis reveals that the fundamental distinctions among these backbone models primarily stem from their diverse approaches to defining the interdependence functions. Furthermore, this unified representation opens up new opportunities for designing innovative architectures with the potential to surpass the performance of these dominant backbones.

Expanding reinforcement learning (RL) to offline domains generates promising prospects, particularly in sectors where data collection poses substantial challenges or risks. Pivotal to the success of transferring RL offline is mitigating overestimation bias in value estimates for state-action pairs absent from data. Whilst numerous approaches have been proposed in recent years, these tend to focus primarily on continuous or small-scale discrete action spaces. Factorised discrete action spaces, on the other hand, have received relatively little attention, despite many real-world problems naturally having factorisable actions. In this work, we undertake a formative investigation into offline reinforcement learning in factorisable action spaces. Using value-decomposition as formulated in DecQN as a foundation, we present the case for a factorised approach and conduct an extensive empirical evaluation of several offline techniques adapted to the factorised setting. In the absence of established benchmarks, we introduce a suite of our own comprising datasets of varying quality and task complexity. Advocating for reproducible research and innovation, we make all datasets available for public use alongside our code base.

Assistive robots interact with humans and must adapt to different users' preferences to be effective. An easy and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, for example, robot movement trajectories or gestures. Existing techniques focus on generating trajectories for users to rank that maximize the outcome of the preference learning process. However, the generated trajectories do not appear to reflect the user's preference over repeated interactions. In this work, we design an algorithm to generate trajectories for users to rank that we call Covariance Matrix Adaptation Evolution Strategies with Information Gain (CMA-ES-IG). CMA-ES-IG prioritizes the user's experience of the preference learning process. We show that users find our algorithm more intuitive and easier to use than previous approaches across both physical and social robot tasks. This project's code is hosted at github.com/interaction-lab/CMA-ES-IG

Language models trained on diverse datasets unlock generalization by in-context learning. Reinforcement Learning (RL) policies can achieve a similar effect by meta-learning within the memory of a sequence model. However, meta-RL research primarily focuses on adapting to minor variations of a single task. It is difficult to scale towards more general behavior without confronting challenges in multi-task optimization, and few solutions are compatible with meta-RL's goal of learning from large training sets of unlabeled tasks. To address this challenge, we revisit the idea that multi-task RL is bottlenecked by imbalanced training losses created by uneven return scales across different tasks. We build upon recent advancements in Transformer-based (in-context) meta-RL and evaluate a simple yet scalable solution where both an agent's actor and critic objectives are converted to classification terms that decouple optimization from the current scale of returns. Large-scale comparisons in Meta-World ML45, Multi-Game Procgen, Multi-Task POPGym, Multi-Game Atari, and BabyAI find that this design unlocks significant progress in online multi-task adaptation and memory problems without explicit task labels.

Recent advances in machine learning have led to increased interest in reproducing kernel Banach spaces (RKBS) as a more general framework that extends beyond reproducing kernel Hilbert spaces (RKHS). These works have resulted in the formulation of representer theorems under several regularized learning schemes. However, little is known about an optimization method that encompasses these results in this setting. This paper addresses a learning problem on Banach spaces endowed with a reproducing kernel, focusing on efficient optimization within RKBS. To tackle this challenge, we propose an algorithm based on mirror descent (MDA). Our approach involves an iterative method that employs gradient steps in the dual space of the Banach space using the reproducing kernel. We analyze the convergence properties of our algorithm under various assumptions and establish two types of results: first, we identify conditions under which a linear convergence rate is achievable, akin to optimization in the Euclidean setting, and provide a proof of the linear rate; second, we demonstrate a standard convergence rate in a constrained setting. Moreover, to instantiate this algorithm in practice, we introduce a novel family of RKBSs with $p$-norm ($p \neq 2$), characterized by both an explicit dual map and a kernel.

Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which measure the comprehensiveness and depth of an LLM or knowledge source respectively. We reveal that the imbalance in the number of prompts and responses can lead to a potential disparity in breadth and depth learning within alignment tuning datasets by showing that even a simple uniform method for balancing the number of instructions and responses can lead to significant improvements. Building on this, we further propose Balanced Preference Optimization (BPO), designed to dynamically augment the knowledge depth of each sample. BPO is motivated by the observation that the usefulness of knowledge varies across samples, necessitating tailored learning of knowledge depth. To achieve this, we introduce gradient-based clustering, estimating the knowledge informativeness and usefulness of each augmented sample based on the model's optimization direction. Our experimental results across various benchmarks demonstrate that BPO outperforms other baseline methods in alignment tuning while maintaining training efficiency. Furthermore, we conduct a detailed analysis of each component of BPO, providing guidelines for future research in preference data optimization.

This study focuses on recognizing Bangladeshi dialects and converting diverse Bengali accents into standardized formal Bengali speech. Dialects, often referred to as regional languages, are distinctive variations of a language spoken in a particular location and are identified by their phonetics, pronunciations, and lexicon. Subtle changes in pronunciation and intonation are also influenced by geographic location, educational attainment, and socioeconomic status. Dialect standardization is needed to ensure effective communication, educational consistency, access to technology, economic opportunities, and the preservation of linguistic resources while respecting cultural diversity. Being the fifth most spoken language with around 55 distinct dialects spoken by 160 million people, addressing Bangla dialects is crucial for developing inclusive communication tools. However, limited research exists due to a lack of comprehensive datasets and the challenges of handling diverse dialects. With the advancement in multilingual Large Language Models (mLLMs), emerging possibilities have been created to address the challenges of dialectal Automated Speech Recognition (ASR) and Machine Translation (MT). This study presents an end-to-end pipeline for converting dialectal Noakhali speech to standard Bangla speech. This investigation includes constructing a large-scale diverse dataset with dialectal speech signals that tailored the fine-tuning process in ASR and LLM for transcribing the dialect speech to dialect text and translating the dialect text to standard Bangla text. Our experiments demonstrated that fine-tuning the Whisper ASR model achieved a CER of 0.8% and WER of 1.5%, while the BanglaT5 model attained a BLEU score of 41.6% for dialect-to-standard text translation.

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.