5 papers
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
Yuchen Guan, Xiao Li, Zongyu Guo +4
We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tok…
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Runxi Cheng, Yuchen Guan, Yongxian Wei +7
Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-trainin…
Mixture of Neuron Experts
Runxi Cheng, Yuchen Guan, Yucheng Ding +6
In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE…
Text-guided Visual Prompt DINO for Generic Segmentation
Yuchen Guan, Chong Sun, Canmiao Fu +3
Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation,…
Enhancing Logits Distillation with Plug\&Play Kendall's Ranking Loss
Yuchen Guan, Runxi Cheng, Kang Liu +1
Knowledge distillation typically minimizes the Kullback-Leibler (KL) divergence between teacher and student logits. However, optimizing the KL divergence can be challenging for the…