Related papers: CORAL: Scalable Multi-Task Robot Learning via LoRA…

Collaborative perception has garnered significant attention as a crucial technology to overcome the perceptual limitations of single-agent systems. Many state-of-the-art (SOTA) methods have achieved communication efficiency and high…

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…

In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present CORA, a platform for Continual…

Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal…

Quadrupedal locomotion is a complex, open-ended problem vital to expanding autonomous vehicle reach. Traditional reinforcement learning approaches often fall short due to training instability and sample inefficiency. We propose a novel…

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle…

While Multimodal Large Language Models (MLLMs) excel at generalizing across modalities and tasks, effectively adapting them to specific downstream tasks while simultaneously retaining both general and specialized knowledge remains…

Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resource languages such as…

In real-world industrial settings, large language models (LLMs) must learn continually to keep pace with diverse and evolving tasks, requiring self-evolution to refine knowledge under dynamic data distributions. However, existing continual…

Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models with multi-task abilities, we observe that conventional…

Replicating In-Context Learning (ICL) in computer vision remains challenging due to task heterogeneity. We propose \textbf{VIRAL}, a framework that elicits visual reasoning from a pre-trained image editing model by formulating ICL as…

Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy. We consider learning of linear classification and regression models, in the setting where the training data is…

Current Vision-Language-Action (VLA) models rely on fixed computational depth, expending the same amount of compute on simple adjustments and complex multi-step manipulation. While Chain-of-Thought (CoT) prompting enables variable…

Autonomous Driving (AD) systems have made notable progress, but their performance in long-tail, safety-critical scenarios remains limited. These rare cases contribute a disproportionate number of accidents. Vision-Language Action (VLA)…

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single…

Balancing competing objectives remains a fundamental challenge in multi-task learning (MTL), primarily due to conflicting gradients across individual tasks. A common solution relies on computing a dynamic gradient update vector that…

Vision-Language-Action (VLA) models enable instruction-following robotic manipulation, but they are typically pretrained on 2D data and lack 3D spatial understanding. An effective approach is representation alignment, where a strong vision…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs…

This paper investigates the multi-UAV multi-task coordination problem in infrastructure-less emergency scenarios, where UAVs collaboratively are required to jointly perform aerial image acquisition and ground-user communication. To tackle…