Related papers: Adaptive Data Exploitation in Deep Reinforcement L…
Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…
Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and…
Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because…
The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting…
In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…
Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel…
Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…
Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of…
Retrieval Augmented Generation (RAG) has proven to be highly effective in boosting the generative performance of language model in knowledge-intensive tasks. However, existing RAG framework either indiscriminately perform retrieval or rely…
Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive interaction data, limiting practical deployment. A common remedy is to leverage priors, such as…
We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years for characterizing human and animal…
Adaptations facilitate efficient training of large backbone models, including diffusion models for image generation and transformer-based language models. While various adaptation techniques enhance performance with minimal computational…
This work proposes a procedure for designing algorithms for specific adaptive data collection tasks like active learning and pure-exploration multi-armed bandits. Unlike the design of traditional adaptive algorithms that rely on…
This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…
Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…
Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-inefficient, requiring extensive training. In this work, we…
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…
Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training…
The performance of worst-case optimal join algorithms depends on the order in which the join attributes are processed. Selecting good orders before query execution is hard, due to the large space of possible orders and unreliable execution…
Addressing the imperative need for efficient artificial intelligence in IoT and edge computing, this study presents RepAct, a re-parameterizable adaptive activation function tailored for optimizing lightweight neural networks within the…