Related papers: Sig2Model: A Boosting-Driven Model for Updatable L…

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

Conventional Intent Detection (ID) models are usually trained offline, which relies on a fixed dataset and a predefined set of intent classes. However, in real-world applications, online systems usually involve continually emerging new user…

Boosting techniques from the field of statistical learning have grown to be a popular tool for estimating and selecting predictor effects in various regression models and can roughly be separated in two general approaches, namely gradient…

Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and…

Accurate downlink channel state information (CSI) is vital to achieving high spectrum efficiency in massive MIMO systems. Existing works on the deep learning (DL) model for CSI feedback have shown efficient compression and recovery in…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inherent asymmetry: they…

Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy, leveraging aggregated updates to build robust global models. However, this training paradigm faces significant…

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…

Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…

This paper presents a novel method for utilizing fine-tuned Large Language Models (LLMs) to minimize data requirements in load profile analysis, demonstrated through the restoration of missing data in power system load profiles. A two-stage…

Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Learned optimizers are powerful alternatives to hand-designed update rules like Adam, yet they have seen limited practical adoption since they often fail to meta-generalize beyond their training distribution and incur high meta-training…

Learned indexes, which use machine learning models to replace traditional index structures, have shown promising results in recent studies. However, existing learned indexes exhibit a performance gap between synthetic and real-world…