132 citations · 177 across the 9 of their papers we have counts for
9 papers
How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle
Zongfang Liu, Jinghui Zhang, Zijian Ma +2
Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the full expert pool, making one-shot…
Efficient Inference of Vision Instruction-Following Models with Elastic Cache
Zuyan Liu, Benlin Liu, Jiahui Wang +5
In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of the…
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
Hanqi Yan, Yanzheng Xiang, Guangyi Chen +3
To better interpret the intrinsic mechanism of large language models (LLMs), recent studies focus on monosemanticity on its basic units. A monosemantic neuron is dedicated to a sin…
Narrative Action Evaluation with Prompt-Guided Multimodal Interaction
Shiyi Zhang, Sule Bai, Guangyi Chen +4
In this paper, we investigate a new problem called narrative action evaluation (NAE). NAE aims to generate professional commentary that evaluates the execution of an action. Unlike…
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
Yongming Rao, Wenliang Zhao, Guangyi Chen +5
Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natur…
Person Re-identification via Attention Pyramid
Guangyi Chen, Tianpei Gu, Jiwen Lu +2
In this paper, we propose an attention pyramid method for person re-identification. Unlike conventional attention-based methods which only learn a global attention map, our attenti…
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Yongming Rao, Guangyi Chen, Jiwen Lu +1
Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more ef…
Human Trajectory Prediction via Counterfactual Analysis
Guangyi Chen, Junlong Li, Jiwen Lu +1
Forecasting human trajectories in complex dynamic environments plays a critical role in autonomous vehicles and intelligent robots. Most existing methods learn to predict future tr…
Personalized Trajectory Prediction via Distribution Discrimination
Guangyi Chen, Junlong Li, Nuoxing Zhou +2
Trajectory prediction is confronted with the dilemma to capture the multi-modal nature of future dynamics with both diversity and accuracy. In this paper, we present a distribution…