New methods create realistic human actions from text, improving gaming and film experiences.
― 8 min read
Ji-Rong Wen
A look into how LLMs shape autonomous agents across various fields.
― 6 min read
REAR enhances computer responses by prioritizing relevant information for better answers.
― 6 min read
A method called Masked Thought Fine-Tuning boosts math problem-solving in language models.
― 6 min read
This paper examines new strategies for enhancing document retrieval through token pruning.
― 6 min read
EulerFormer combines semantic and positional information for better user behavior predictions.
― 6 min read
An overview of how memory enhances the performance of LLM-based agents.
― 7 min read
This article discusses extending context windows in language models using positional vectors.
― 6 min read
A new model improves user interest predictions for video content.
― 6 min read
Explores the challenges of supervising advanced AI models with weaker counterparts.
― 6 min read
Research highlights in-context learning abilities in large language models.
― 6 min read
New techniques improve search engine models by considering user context.
― 6 min read
A new method improves the search for mathematical expressions from data.
― 5 min read
Introducing MemSim, a tool for assessing memory effectiveness in language model assistants.
― 5 min read
TrendSim simulates social media trends to study misinformation effects.
― 7 min read
New benchmark OmniEval enhances evaluation of RAG systems in finance.
― 7 min read