Related papers: From Blind Spots to Gains: Diagnostic-Driven Itera…

Pre-trained model-based continual learning (PTMCL) has garnered growing attention, as it enables more rapid acquisition of new knowledge by leveraging the extensive foundational understanding inherent in pre-trained model (PTM). Most…

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Recently reinforcement learning (RL) has emerged as a promising approach for quadrupedal locomotion, which can save the manual effort in conventional approaches such as designing skill-specific controllers. However, due to the complex…

Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various…

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample…

Multimodal Large Models (MLLMs) have achieved remarkable progress in vision-language understanding and generation tasks. However, existing MLLMs typically rely on static modality fusion strategies, which treat all modalities equally…

This paper introduces Recurrent Expansion (RE) as a new learning paradigm that advances beyond conventional Machine Learning (ML) and Deep Learning (DL). While DL focuses on learning from static data representations, RE proposes an…

Continual multimodal instruction tuning is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving tasks. However, most existing methods adopt a fixed architecture, struggling with adapting to new tasks due to static model…

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial…

Machine learning for scientific applications faces the challenge of limited data. We propose a framework that leverages a priori known physics to reduce overfitting when training on relatively small datasets. A deep neural network is…

Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these models is prohibitively expensive, and they often lack…

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…

Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers…

Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference efficiency of MoE LLMs, the training of extensive experts…

Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging receptive fields and reducing interference when aggregating…

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…

Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression toward earlier and better patient-specific pathology management. However, conventional approaches rarely take advantage of…

Detecting anomalies in time series data is crucial for finance, healthcare, sensor networks, and industrial monitoring applications. However, time series anomaly detection often suffers from sparse labels, complex temporal patterns, and…

(This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.) To improve the efficiency of deep reinforcement learning (DRL)-based…

High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples. To address these problems, data filtering is commonly used…