相关论文: HR-Pro: Point-supervised Temporal Action Localizat…

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

Parameter-Efficient Transfer Learning (PETL) aims at efficiently adapting large models pre-trained on massive data to downstream tasks with limited task-specific data. In view of the practicality of PETL, previous works focus on tuning a…

In this paper, we introduce Traversal Learning (TL), a novel approach designed to address the problem of decreased quality encountered in popular distributed learning (DL) paradigms such as Federated Learning (FL), Split Learning (SL), and…

Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at…

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both…

Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods…

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformers have limitations in capturing long-range dependencies and…

Video Large Language Models (Video LLMs) have achieved significant success by adopting the paradigm of large-scale pre-training followed by supervised fine-tuning (SFT). However, existing approaches struggle with temporal reasoning due to…

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…

This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist…

The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time…

Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system…

Deep reinforcement learning (RL) is computationally demanding and requires processing of many data points. Synchronous methods enjoy training stability while having lower data throughput. In contrast, asynchronous methods achieve high…

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn,…

Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing solely on vehicle-centric performance. This paper proposes…

Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods…