SelfAI: Building a Self-Training AI System with LLM Agents

FairT2I has been introduced as an innovative framework aimed at addressing social biases in text-to-image generation, leveraging large language models (LLMs) for bias detection and attribute rebalancing. This framework operates without the need for extensive training, utilizing a mathematically grounded approach to enhance the generation process by adjusting attribute distributions based on user input.

ReSpace has been introduced as a generative framework for text-driven 3D indoor scene synthesis and editing, utilizing autoregressive language models to enhance scene representation and editing capabilities. This approach addresses limitations in current methods, such as oversimplified object semantics and restricted layouts, by providing a structured scene representation with explicit room boundaries.

Recent research introduced SkyLadder, a novel pretraining strategy for large language models (LLMs) that optimizes context window scheduling. This approach transitions from short to long context windows, demonstrating improved performance and efficiency, particularly with models trained on 100 billion tokens.

LLM-NAS introduces a novel approach to Hardware-Aware Neural Architecture Search (HW-NAS), focusing on optimizing neural network designs for accuracy and latency while minimizing search costs. This method addresses the exploration bias observed in traditional LLM-driven approaches, which often limit the diversity of proposed architectures within a constrained search space.

ADORE, or Autonomous Domain-Oriented Relevance Engine, has been introduced as a novel framework aimed at improving relevance modeling in e-commerce search. It addresses challenges posed by traditional term-matching methods and the limitations of neural models, utilizing a combination of a Rule-aware Relevance Discrimination module, an Error-type-aware Data Synthesis module, and a Key-attribute-enhanced Knowledge Distillation module to enhance data generation and reasoning capabilities.

A new benchmark named SurveyEval has been introduced to evaluate automatically generated academic surveys produced by large language models (LLMs). This benchmark assesses surveys based on overall quality, outline coherence, and reference accuracy, extending its evaluation across seven subjects. The findings indicate that specialized survey-generation systems outperform general long-text generation systems in quality.

A new study has introduced LeechHijack, a covert attack vector that exploits the implicit trust in third-party tools within the Model Context Protocol (MCP) used by Large Language Model (LLM)-based agents. This attack allows adversaries to hijack computational resources without breaching explicit permissions, raising significant security concerns in intelligent agent systems.

A recent study has introduced a novel approach to enhance the controllability of large language models (LLMs) by establishing an instruction hierarchy (IH) that prioritizes higher-level directives over lower-priority requests. This framework, termed VerIH, comprises approximately 7,000 aligned and conflicting instructions, enabling LLMs to effectively reconcile competing inputs from users and developers before generating responses.