Reinforcement Learning from Human Feedback (RLHF) learns from the preference signal provided by a probabilistic preference model, which takes a prompt and two responses as input, and produces a score indicating the preference of one response against another. So far, the most popular RLHF paradigm is reward-based, which starts with an initial step of reward modeling, and the constructed reward is then used to provide a reward signal for the subsequent reward optimization stage. However, the existence of a reward function is a strong assumption and the reward-based RLHF is limited in expressivity and cannot capture the real-world complicated human preference. In this work, we provide theoretical insights for a recently proposed learning paradigm, Nash learning from human feedback (NLHF), which considered a general preference model and formulated the alignment process as a game between two competitive LLMs. The learning objective is to find a policy that consistently generates responses preferred over any competing policy while staying close to the initial model. The objective is defined as the Nash equilibrium (NE) of the KL-regularized preference model. We aim to make the first attempt to study the theoretical learnability of the KL-regularized NLHF by considering both offline and online settings. For the offline learning from a pre-collected dataset, we propose algorithms that are efficient under suitable coverage conditions of the dataset. For batch online learning from iterative interactions with a preference oracle, our proposed algorithm enjoys a finite sample guarantee under the structural condition of the underlying preference model. Our results connect the new NLHF paradigm with traditional RL theory, and validate the potential of reward-model-free learning under general preference.

The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our research seeks to advance our understanding of these models' capabilities. We propose a novel VQA benchmark based on well-known visual classification datasets which allows a granular evaluation of text-generative vision-language models and their comparison with discriminative vision-language models. To improve the assessment of coarse answers on fine-grained classification tasks, we suggest using the semantic hierarchy of the label space to ask automatically generated follow-up questions about the ground-truth category. Finally, we compare traditional NLP and LLM-based metrics for the problem of evaluating model predictions given ground-truth answers. We perform a human evaluation study upon which we base our decision on the final metric. We apply our benchmark to a suite of vision-language models and show a detailed comparison of their abilities on object, action, and attribute classification. Our contributions aim to lay the foundation for more precise and meaningful assessments, facilitating targeted progress in the exciting field of vision-language modeling.

Sign language to text is a crucial technology that can break down communication barriers for individuals with hearing difficulties. We replicate and try to improve on a recently published study. We evaluate models using BLEU and rBLEU metrics to ensure translation quality. During our ablation study, we found that the model's performance is significantly influenced by optimizers, activation functions, and label smoothing. Further research aims to refine visual feature capturing, enhance decoder utilization, and integrate pre-trained decoders for better translation outcomes. Our source code is available to facilitate replication of our results and encourage future research.

The solution of a PDE over varying initial/boundary conditions on multiple domains is needed in a wide variety of applications, but it is computationally expensive if the solution is computed de novo whenever the initial/boundary conditions of the domain change. We introduce a general operator learning framework, called DIffeomorphic Mapping Operator learNing (DIMON) to learn approximate PDE solutions over a family of domains $\{\Omega_{\theta}}_\theta$, that learns the map from initial/boundary conditions and domain $\Omega_\theta$ to the solution of the PDE, or to specified functionals thereof. DIMON is based on transporting a given problem (initial/boundary conditions and domain $\Omega_{\theta}$) to a problem on a reference domain $\Omega_{0}$, where training data from multiple problems is used to learn the map to the solution on $\Omega_{0}$, which is then re-mapped to the original domain $\Omega_{\theta}$. We consider several problems to demonstrate the performance of the framework in learning both static and time-dependent PDEs on non-rigid geometries; these include solving the Laplace equation, reaction-diffusion equations, and a multiscale PDE that characterizes the electrical propagation on the left ventricle. This work paves the way toward the fast prediction of PDE solutions on a family of domains and the application of neural operators in engineering and precision medicine.

This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These components include not only the reward function and transition probability matrices, but also the action space and state space that are not exactly known but are known to belong to given uncertainty sets. We address two key challenges in GIRL: first, the need to quantify the discrepancy between the observed policy and the underlying optimal policy; second, the difficulty of mathematically characterizing the underlying optimal policy when the basic components of an MDP are unobservable or partially observable. Then, we propose the mathematical formulation for GIRL and develop a fast heuristic algorithm. Numerical results on both finite and infinite state problems show the merit of our formulation and algorithm.

Natural language processing (NLP) is a key component of intelligent transportation systems (ITS), but it faces many challenges in the transportation domain, such as domain-specific knowledge and data, and multi-modal inputs and outputs. This paper presents TransGPT, a novel (multi-modal) large language model for the transportation domain, which consists of two independent variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is finetuned on a single-modal Transportation dataset (STD) that contains textual data from various sources in the transportation domain. TransGPT-MM is finetuned on a multi-modal Transportation dataset (MTD) that we manually collected from three areas of the transportation domain: driving tests, traffic signs, and landmarks. We evaluate TransGPT on several benchmark datasets for different tasks in the transportation domain, and show that it outperforms baseline models on most tasks. We also showcase the potential applications of TransGPT for traffic analysis and modeling, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic-related questions, providing traffic recommendations, and generating traffic reports. This work advances the state-of-the-art of NLP in the transportation domain and provides a useful tool for ITS researchers and practitioners.

A temporal graph can be considered as a stream of links, each of which represents an interaction between two nodes at a certain time. On temporal graphs, link prediction is a common task, which aims to answer whether the query link is true or not. To do this task, previous methods usually focus on the learning of representations of the two nodes in the query link. We point out that the learned representation by their models may encode too much information with side effects for link prediction because they have not utilized the information of the query link, i.e., they are link-unaware. Based on this observation, we propose a link-aware model: historical links and the query link are input together into the following model layers to distinguish whether this input implies a reasonable pattern that ends with the query link. During this process, we focus on the modeling of link evolution patterns rather than node representations. Experiments on six datasets show that our model achieves strong performances compared with state-of-the-art baselines, and the results of link prediction are interpretable. The code and datasets are available on the project website: https://github.com/lbq8942/TGACN.

Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale "in-the-wild" video datasets have driven progress in computer vision through self-supervised techniques. Translating this to robotics, recent works have explored learning manipulation skills by passively watching abundant videos sourced online. Showing promising results, such video-based learning paradigms provide scalable supervision while reducing dataset bias. This survey reviews foundations such as video feature representation learning techniques, object affordance understanding, 3D hand/body modeling, and large-scale robot resources, as well as emerging techniques for acquiring robot manipulation skills from uncontrolled video demonstrations. We discuss how learning only from observing large-scale human videos can enhance generalization and sample efficiency for robotic manipulation. The survey summarizes video-based learning approaches, analyses their benefits over standard datasets, survey metrics, and benchmarks, and discusses open challenges and future directions in this nascent domain at the intersection of computer vision, natural language processing, and robot learning.

Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This has inspired the emergence of model-heterogeneous personalized federated learning (MHPFL). Nevertheless, the problem of ensuring data and model privacy, while achieving good model performance and keeping communication and computation costs low remains open in MHPFL. To address this problem, we propose a model-heterogeneous personalized Federated learning with Mixture of Experts (pFedMoE) method. It assigns a shared homogeneous small feature extractor and a local gating network for each client's local heterogeneous large model. Firstly, during local training, the local heterogeneous model's feature extractor acts as a local expert for personalized feature (representation) extraction, while the shared homogeneous small feature extractor serves as a global expert for generalized feature extraction. The local gating network produces personalized weights for extracted representations from both experts on each data sample. The three models form a local heterogeneous MoE. The weighted mixed representation fuses generalized and personalized features and is processed by the local heterogeneous large model's header with personalized prediction information. The MoE and prediction header are updated simultaneously. Secondly, the trained local homogeneous small feature extractors are sent to the server for cross-client information fusion via aggregation. Overall, pFedMoE enhances local model personalization at a fine-grained data level, while supporting model heterogeneity.

Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years. In federated learning, a central server periodically coordinates models with clients and aggregates the models trained locally by clients without necessitating access to local data. Despite its potential, the implementation of federated learning continues to encounter several challenges, predominantly the slow convergence that is largely due to data heterogeneity. The slow convergence becomes particularly problematic in cross-device federated learning scenarios where clients may be strongly limited by computing power and storage space, and hence counteracting methods that induce additional computation or memory cost on the client side such as auxiliary objective terms and larger training iterations can be impractical. In this paper, we propose a novel federated aggregation strategy, TurboSVM-FL, that poses no additional computation burden on the client side and can significantly accelerate convergence for federated classification task, especially when clients are "lazy" and train their models solely for few epochs for next global aggregation. TurboSVM-FL extensively utilizes support vector machine to conduct selective aggregation and max-margin spread-out regularization on class embeddings. We evaluate TurboSVM-FL on multiple datasets including FEMNIST, CelebA, and Shakespeare using user-independent validation with non-iid data distribution. Our results show that TurboSVM-FL can significantly outperform existing popular algorithms on convergence rate and reduce communication rounds while delivering better test metrics including accuracy, F1 score, and MCC.