相关论文: Helix: Evolutionary Reinforcement Learning for Ope…
The reasoning frontier of Large Language Models (LLMs) has advanced significantly through modern post-training paradigms (e.g., Reinforcement Learning from Verifiable Rewards (RLVR)). However, the efficacy of these methods remains…
Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…
Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the…
Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck…
The efficient distributed training of Large Language Models (LLMs) is severely hampered by the extreme variance in context lengths. This data heterogeneity, amplified by conventional packing strategies and asymmetric forward-backward costs,…
Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes…
Heuristic algorithms such as simulated annealing, Concorde, and METIS are effective and widely used approaches to find solutions to combinatorial optimization problems. However, they are limited by the high sample complexity required to…
Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…
Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutionary search with large…
While systems designed for solving planning tasks vastly outperform Large Language Models (LLMs) in this domain, they usually discard the rich semantic information embedded within task descriptions. In contrast, LLMs possess parametrised…
In autonomous exploration tasks, robots are required to explore and map unknown environments while efficiently planning in dynamic and uncertain conditions. Given the significant variability of environments, human operators often have…
Designing effective heuristics for NP-hard combinatorial optimization problems remains challenging and often requires substantial domain expertise. Recent LLM-guided evolutionary methods have shown promise for automated heuristic…
We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…
The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability…
The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…
Large Language Models (LLMs) have demonstrated remarkable performance in solving math problems, a hallmark of human intelligence. Despite high success rates on current benchmarks; however, these often feature simple problems with only one…
Large Language Models (LLMs) have achieved remarkable success in various fields, prompting several studies to explore their potential in recommendation systems. However, these attempts have so far resulted in only modest improvements over…
This paper explores the application of Reinforcement Learning (RL) to the two-dimensional rectangular packing problem. We propose a reduced representation of the state and action spaces that allow us for high granularity. Leveraging UNet…
This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning…
We study the two-dimensional hierarchical rectangle packing problem, motivated by applications in analog integrated circuit layout, facility layout, and logistics. Unlike classical strip or bin packing, the dimensions of the container are…