Related papers: PLAN: Proactive Low-Rank Allocation for Continual …

Object packing by autonomous robots is an im-portant challenge in warehouses and logistics industry. Most conventional data-driven packing planning approaches focus on regular cuboid packing, which are usually heuristic and limit the…

Continual learning (CL) - the ability to progressively acquire and integrate new concepts - is essential to intelligent systems to adapt to dynamic environments. However, deep neural networks struggle with catastrophic forgetting (CF) when…

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and…

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this…

Post-training, particularly reinforcement learning (RL) using self-play-generated data, has become a new learning paradigm for large language models (LLMs). However, scaling RL to develop a general reasoner remains a research challenge, as…

Biological agents are known to learn many different tasks over the course of their lives, and to be able to revisit previous tasks and behaviors with little to no loss in performance. In contrast, artificial agents are prone to…

Low-rank approximation is a fundamental technique in modern data analysis, widely utilized across various fields such as signal processing, machine learning, and natural language processing. Despite its ubiquity, the mechanics of low-rank…

Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level…

Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts frequently.…

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data…

Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize in several specific…

Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals that this degradation is primarily driven by antagonistic…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

In recent years, the planning community has observed that techniques for learning heuristic functions have yielded improvements in performance. One approach is to use offline learning to learn predictive models from existing heuristics in a…

In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language models have shown…

Large Language Models (LLMs) possess encompassing capabilities that can process diverse language-related tasks. However, finetuning on LLMs will diminish this general skills and continual finetuning will further cause severe degradation on…

Despite large neural networks demonstrating remarkable abilities to complete different tasks, they require excessive memory usage to store the optimization states for training. To alleviate this, the low-rank adaptation (LoRA) is proposed…

The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned tasks when the model…

We propose a new approach for solving planning problems with a hierarchical structure, fusing reinforcement learning and MPC planning. Our formulation tightly and elegantly couples the two planning paradigms. It leverages reinforcement…

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new…