Related papers: SLAW: Scaled Loss Approximate Weighting for Effici…
Multi-task reinforcement learning could enable robots to scale across a wide variety of manipulation tasks in homes and workplaces. However, generalizing from one task to another and mitigating negative task interference still remains a…
Scientific document representation learning provides powerful embeddings for various tasks, while current methods face challenges across three approaches. 1) Contrastive training with citation-structural signals underutilizes citation…
In multi-task learning (MTL), we improve the performance of key machine learning algorithms by training various tasks jointly. When the number of tasks is large, modeling task structure can further refine the task relationship model. For…
By leveraging large amounts of product data collected across hundreds of live e-commerce websites, we construct 1000 unique classification tasks that share similarly-structured input data, comprised of both text and images. These…
Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning…
We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…
Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely applied across various domains. However, task imbalance…
Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbalanced training samples. In such scenarios, the number of…
Traditionally, multitask learning (MTL) assumes that all the tasks are related. This can lead to negative transfer when tasks are indeed incoherent. Recently, a number of approaches have been proposed that alleviate this problem by…
Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality? Current AQA and skills assessment approaches propose to learn features that serve only one task -…
Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principled framework for predicting these outcomes. We identify a…
The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, resulting in negative transfer among them. Earlier research…
A fundamental problem in multi-task learning (MTL) is identifying groups of tasks that should be learned together. Since training MTL models for all possible combinations of tasks is prohibitively expensive for large task sets, a crucial…
Multi-task learning (MTL) has been widely applied in online advertising and recommender systems. To address the negative transfer issue, recent studies have proposed optimization methods that thoroughly focus on the gradient alignment of…
Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires substantial human annotation -- a process that is…
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through…
We study and quantify the generalization patterns of multitask learning (MTL) models for sequence labeling tasks. MTL models are trained to optimize a set of related tasks jointly. Although multitask learning has achieved improved…
As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight…
Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. Most…