1 citations · 1 across the 11 of their papers we have counts for
11 papers
Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
Boyu Shi, Chang Liu, ChuanBao Gao +2
Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to…
Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
Ruiming Chen, Junming Yang, Shiyu Xia +3
CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, th…
Mimic In-Context Learning for Multimodal Tasks
Yuchu Jiang, Jiale Fu, Chenduo Hao +4
Recently, In-context Learning (ICL) has become a significant inference paradigm in Large Multimodal Models (LMMs), utilizing a few in-context demonstrations (ICDs) to prompt LMMs f…
Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization
Huiyi Chen, Jiawei Peng, Kaihua Tang +2
In-context learning (ICL) enables Large Vision-Language Models (LVLMs) to adapt to new tasks without parameter updates, using a few demonstrations from a large support set. However…
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Yingzhe Peng, Gongrui Zhang, Miaosen Zhang +7
Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B…
Fast Large Language Model Collaborative Decoding via Speculation
Jiale Fu, Yuchu Jiang, Junkai Chen +3
Large Language Model (LLM) collaborative decoding techniques improve output quality by combining the outputs of multiple models at each generation step, but they incur high computa…
LIVE: Learnable In-Context Vector for Visual Question Answering
Yingzhe Peng, Chenduo Hao, Xu Yang +3
As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefi…
Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
Shi-Yu Xia, Wenxuan Zhu, Xu Yang +1
In practice, we usually need to build variable-sized models adapting for diverse resource constraints in different application scenarios, where weight initialization is an importan…
Transformer as Linear Expansion of Learngene
Shiyu Xia, Miaosen Zhang, Xu Yang +3
We propose expanding the shared Transformer module to produce and initialize Transformers of varying depths, enabling adaptation to diverse resource constraints. Drawing an analogy…
Building Variable-sized Models via Learngene Pool
Boyu Shi, Shiyu Xia, Xu Yang +3
Recently, Stitchable Neural Networks (SN-Net) is proposed to stitch some pre-trained networks for quickly building numerous networks with different complexity and performance trade…
Manipulating the Label Space for In-Context Classification
Haokun Chen, Xu Yang, Yuhang Huang +3
After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task co…