7 papers
A Survey of Audio Reasoning in Multimodal Foundation Models
Zhihan Guo, Wenqian Cui, Guan-Ting Lin +8
Reasoning has become a defining capability of modern foundation models, yet its development in the audio modality remains limited. Audio poses challenges that are distinct from tho…
CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
Jingyao Li, Jingyun Wang, Molin Tan +6
Cross-Video Reasoning (CVR) presents a significant challenge in video understanding, which requires simultaneous understanding of multiple videos to aggregate and compare informati…
Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
Chuanyang Zheng, Jiankai Sun, Yihang Gao +13
Mixture-of-Experts (MoE) has become a cornerstone in recent state-of-the-art large language models (LLMs). Traditionally, MoE relies on as the router score funct…
Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models
Minbin Huang, Runhui Huang, Chuanyang Zheng +4
Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by direct…
Logits-Based Finetuning
Jingyao Li, Senqiao Yang, Sitong Wu +4
In recent years, developing compact and efficient large language models (LLMs) has emerged as a thriving area of research. Traditional Supervised Fine-Tuning (SFT), which relies on…
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
Chuanyang Zheng, Yihang Gao, Han Shi +8
Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional enc…