Related papers: AdaFRUGAL: Adaptive Memory-Efficient Training with…

Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries. Existing efforts to mitigate this issue are fundamentally limited by…

Lifelong learning (LL) aims to continuously acquire new knowledge while retaining previously learned knowledge. A central challenge in LL is the stability-plasticity dilemma, which requires models to balance the preservation of previous…

Training large language models (LLMs) typically relies on adaptive optimizers like Adam (Kingma & Ba, 2015) which store additional state information to accelerate convergence but incur significant memory overhead. Recent efforts, such as…

Despite the success of Large Language Models (LLMs) on various tasks following human instructions, controlling model generation at inference time poses a persistent challenge. In this paper, we introduce Ctrl-G, an adaptable framework that…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

The capacity of a ML model refers to the range of functions this model can approximate. It impacts both the complexity of the patterns a model can learn but also memorization, the ability of a model to fit arbitrary labels. We propose…

Ensuring that reinforcement learning (RL) controllers satisfy safety and reliability constraints in real-world settings remains challenging: state-avoidance and constrained Markov decision processes often fail to capture trajectory-level…

Large Language Models (LLMs) have fundamentally altered how we approach scaling in machine learning. However, these models pose substantial computational and memory challenges, primarily due to the reliance on matrix multiplication (MatMul)…

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform…

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models…

Pre-trained Language Models (PLMs) have demonstrated impressive performance in various NLP tasks. However, traditional fine-tuning methods for leveraging PLMs for downstream tasks entail significant computational overhead. Prompt-tuning has…

Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…

We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…

Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge devices. In this paper, we introduce Developmental Federated…

Dynamic treatment regimens (DTRs) are sequential decision rules tailored at each stage by potentially time-varying patient features and intermediate outcomes observed in previous stages. The complexity, patient heterogeneity and chronicity…

Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typically formulate forgetting and retention as a regularized…

As Large Language Models (LLMs) are pre-trained on ultra-large-scale corpora, the problem of data contamination is becoming increasingly serious, and there is a risk that static evaluation benchmarks overestimate the performance of LLMs. To…

Training efficiency in large-scale models is typically assessed through memory consumption, training time, and model performance. Current methods often exhibit trade-offs among these metrics, as optimizing one generally degrades at least…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…