Related papers: Dynamic Multi-Scale Loss Optimization for Object D…

In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four…

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to…

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

This paper introduces a novel framework for model adaptivity in the context of heterogeneous multiscale problems. The framework is based on the idea to interpret model adaptivity as a minimization problem of local error indicators, that are…

Instance recognition is rapidly advanced along with the developments of various deep convolutional neural networks. Compared to the architectures of networks, the training process, which is also crucial to the success of detectors, has…

Anomaly detection (AD) is often focused on detecting anomaly areas for industrial quality inspection and medical lesion examination. However, due to the specific scenario targets, the data scale for AD is relatively small, and evaluation…

Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods mostly focus on the design of pos weighting function, while…

In Multi-Task Learning (MTL), it is a common practice to train multi-task networks by optimizing an objective function, which is a weighted average of the task-specific objective functions. Although the computational advantages of this…

Multi-task learning (MTL) can improve performance on a task by sharing representations with one or more related auxiliary-tasks. Usually, MTL-networks are trained on a composite loss function formed by a constant weighted combination of the…

With the development of multimedia time, one sample can always be described from multiple views which contain compatible and complementary information. Most algorithms cannot take information from multiple views into considerations and fail…

RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of…

Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring…

Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores (e.g., PSNR and SSIM), but often results in blurry images due to insufficient recovery of high-frequency…

We study a persistent failure mode in multi-objective alignment for large language models (LLMs): training improves performance on only a subset of objectives while causing others to degrade. We formalize this phenomenon as cross-objective…

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance,…

Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging problem to evaluate the training samples collected from…

We propose a novel Dynamic Restrained Uncertainty Weighting Loss to experimentally handle the problem of balancing the contributions of multiple tasks on the ICML ExVo 2022 Challenge. The multitask aims to recognize expressed emotions and…

Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of LLM pre-training. We show that data mixtures that perform well at smaller…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Numerous studies attempt to mitigate classification bias caused by class imbalance. However, existing studies have yet to explore the collaborative optimization of imbalanced learning and model training. This constraint hinders further…