31 papers
Towards Atoms of Large Language Models
Chenhui Hu, Pengfei Cao, Yubo Chen +2
The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underlying mechanisms. In this paper, we int…
Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
Chenxi Zhou, Pengfei Cao, Jiang Li +4
Post-Training Quantization (PTQ) is a critical strategy for efficient Large Language Models (LLMs) deployment. However, existing scaling laws primarily focus on general performance…
MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
Jiachun Li, Shaoping Huang, Zhuoran Jin +5
Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathemati…
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
Jiachun Li, Pengfei Cao, Zhuoran Jin +6
Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on trainin…
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
Sirui Liang, Pengfei Cao, Jian Zhao +4
Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed repre…
EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
Pengfei Cao, Zeao Ji, Daojian Zeng +2
Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which…