Related papers: An Adam-enhanced Particle Swarm Optimizer for Late…

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when…

Linkage Tree Genetic Algorithm (LTGA) is an effective Evolutionary Algorithm (EA) to solve complex problems using the linkage information between problem variables. LTGA performs well in various kinds of single-task optimization and yields…

Hierarchical latent tree analysis (HLTA) is recently proposed as a new method for topic detection. It differs fundamentally from the LDA-based methods in terms of topic definition, topic-document relationship, and learning method. It has…

Predicting human decision-making in high-stakes environments remains a central challenge for artificial intelligence. While large language models (LLMs) demonstrate strong general reasoning, they often struggle to generate consistent,…

In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the…

The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…

The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the…

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving…

High-dimensional measurements are often correlated which motivates their approximation by factor models. This holds also true when features are engineered via low-dimensional interactions or kernel tricks. This often results in over…

Large language models (LLMs) are increasingly deployed in real-world applications that require careful balancing of multiple, often conflicting, objectives, such as informativeness versus conciseness, or helpfulness versus creativity.…

One of the key factors influencing the reasoning capabilities of LLM-based agents is their ability to leverage long-term memory. Integrating long-term memory mechanisms allows agents to make informed decisions grounded in historical…

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually…

Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference…

This paper proposes a new generalized two dimensional learning approach for particle swarm based feature selection. The core idea of the proposed approach is to include the information about the subset cardinality into the learning…