Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths of reinforcement learning with adversarial imitation learning. This enables smaller student VLMs not only to mimic the sophisticated text generation of large teacher models but also to systematically improve their generative capabilities through reinforcement signals. Key to our imitation framework is a LLM-based discriminator that adeptly distinguishes between student and teacher outputs, complemented by guidance from multiple large teacher VLMs to ensure diverse learning. This unified learning strategy, leveraging both reinforcement and imitation, empowers student models to achieve significant performance gains, making them competitive with leading closed-source VLMs. Extensive experiments on diverse vision-language benchmarks demonstrate that RIL significantly narrows the performance gap with state-of-the-art open-and closed-source VLMs and, in several instances, surpasses them.

In this paper, we study an online strategic classification problem, where a principal aims to learn an accurate binary linear classifier from sequentially arriving agents. For each agent, the principal announces a classifier. The agent can strategically exercise costly manipulations on his features to be classified as the favorable positive class. The principal is unaware of the true feature-label distribution, but observes all reported features and only labels of positively classified agents. We assume that the true feature-label distribution is given by a halfspace model subject to arbitrary feature-dependent bounded noise (i.e., Massart Noise). This problem faces the combined challenges of agents' strategic feature manipulations, partial label observations, and label noises. We tackle these challenges by a novel learning algorithm. We show that the proposed algorithm yields classifiers that converge to the clairvoyant optimal one and attains a regret rate of $ O(\sqrt{T})$ up to poly-logarithmic and constant factors over $T$ cycles.

Data fusion techniques integrate information from heterogeneous data sources to improve learning, generalization, and decision-making across data sciences. In causal inference, these methods leverage rich observational data to improve causal effect estimation, while maintaining the trustworthiness of randomized controlled trials. Existing approaches often relax the strong no unobserved confounding assumption by instead assuming exchangeability of counterfactual outcomes across data sources. However, when both assumptions simultaneously fail--a common scenario in practice--current methods cannot identify or estimate causal effects. We address this limitation by proposing a novel partial identification framework that enables researchers to answer key questions such as: and Our approach introduces interpretable sensitivity parameters that quantify assumption violations and derives corresponding causal effect bounds. We develop doubly robust estimators for these bounds and operationalize breakdown frontier analysis to understand how causal conclusions change as assumption violations increase. We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance. Our analysis reveals that the Project STAR results are robust to simultaneous violations of key assumptions, both on average and across various subgroups of interest. This strengthens confidence in the study's conclusions despite potential unmeasured biases in the data.

Multi-Agent Reinforcement Learning (MARL) has achieved remarkable success in various real-world scenarios, but its high cost of online training makes it impractical to learn each task from scratch. To enable effective policy reuse, we consider the problem of zero-shot generalization from offline data across multiple tasks. While prior work focuses on transferring individual skills of agents, we argue that the effective policy transfer across tasks should also capture the team-level coordination knowledge. In this paper, we propose Bi-Level Knowledge Transfer (BiKT) for Multi-Task MARL, which performs knowledge transfer at both the individual and team levels. At the individual level, we extract transferable individual skill embeddings from offline MARL trajectories.

Weak-to-strong generalization--where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher--has been widely observed, but the mechanisms that enable it have remained poorly understood. In this paper, through a theoretical analysis of simple models, we uncover three core mechanisms that can drive this phenomenon. First, by analyzing ridge linear regression, we study the interplay between the teacher and student regularization parameters and prove that a student can compensate for a teacher's under-regularization and achieve lower test error. We also analyze the role of the parameterization regime of the models and show that qualitatively different phenomena can happen in different regimes. Second, by analyzing weighted ridge linear regression, we show that a student model with a regularization structure better aligned to the target function, can outperform its teacher. Third, in a nonlinear multi index learning setting, we demonstrate that a student can learn easy, task-specific features from the teacher while leveraging its own broader pre-training to learn hard to learn features that the teacher cannot capture.

Self-knowledge distillation (SKD) enables single-model training by distilling knowledge from the model's own output, eliminating the need for a separate teacher network required in conventional distillation methods. However, current SKD methods focus mainly on replicating common features in the student model, neglecting the extraction of key features that significantly enhance student learning. Inspired by this, we devise a self-knowledge distillation framework entitled Self-Distillation training via Proximal Gradient Optimization or SDPGO, which utilizes gradient information to identify and assign greater weight to features that significantly impact classification performance, enabling the network to learn the most relevant features during training. Specifically, the proposed framework refines the gradient information into a dynamically changing weighting factor to evaluate the distillation knowledge via the dynamic weight adjustment scheme. Meanwhile, we devise the sequential iterative learning module to dynamically optimize knowledge transfer by leveraging historical predictions and real-time gradients, stabilizing training through mini-batch-based KL divergence refinement while adaptively prioritizing task-critical features for efficient self-distillation. Comprehensive experiments on image classification, object detection, and semantic segmentation demonstrate that our method consistently surpasses recent state-of-the-art knowledge distillation techniques.

Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework, STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.

End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achieving robustness to varying camera viewpoints, a common real-world challenge due to diverse vehicle configurations, remains an open problem. In this work, we propose VR-Drive, a novel E2E-AD framework that addresses viewpoint generalization by jointly learning 3D scene reconstruction as an auxiliary task to enable planning-aware view synthesis. Unlike prior scene-specific synthesis approaches, VR-Drive adopts a feed-forward inference strategy that supports online training-time augmentation from sparse views without additional annotations. To further improve viewpoint consistency, we introduce a viewpoint-mixed memory bank that facilitates temporal interaction across multiple viewpoints and a viewpoint-consistent distillation strategy that transfers knowledge from original to synthesized views. Trained in a fully end-to-end manner, VR-Drive effectively mitigates synthesis-induced noise and improves planning under viewpoint shifts. In addition, we release a new benchmark dataset to evaluate E2E-AD performance under novel camera viewpoints, enabling comprehensive analysis. Our results demonstrate that VR-Drive is a scalable and robust solution for the real-world deployment of end-to-end autonomous driving systems.

Despite the impressive performance of large language models (LLMs), the process of endowing them with new capabilities---such as mathematical reasoning---remains largely empirical and opaque. A critical open question is whether reasoning abilities stem from the entire model, specific modules, or are merely artifacts of overfitting. In this work, we hypothesize that the reasoning capabilities in well-trained LLMs are primarily attributed to the output projection module (o proj plays a central role in enabling reasoning, whereas other modules contribute more to fluent dialogue. These findings offer a new perspective on LLM interpretability and open avenues for more targeted training strategies, potentially enabling more efficient and specialized LLMs.

Federated Multi-Task Learning (FL-MTL) enables clients with heterogeneous data to collaboratively train models capable of handling multiple downstream tasks. However, FL-MTL faces key challenges, including statistical heterogeneity, task interference, and the need to balance local learning with global knowledge sharing. Traditional methods like FedAvg struggle in such settings due to the lack of explicit mechanisms to address these issues. In this paper, we propose FedRAM, a three-step framework that progressively updates two scalar hyperparameters: the task importance weight and the client aggregation coefficient. FedRAM introduces a reference-proxy-agent strategy, where the proxy model serves as an intermediate between the local reference model and the global agent model. This design reduces the need for repeated local training while preserving local performance. Extensive experiments on six real-world FL-MTL benchmarks show that FedRAM improves performance by at least 3$\%$ over the most baseline on both in-domain and out-of-domain tasks, while reducing computational cost by 15$\times$. These results make FedRAM a robust and practical solution for large-scale FL-MTL applications. The code is available at \url{https://github.com/wwffvv/FedRAM}.