Papers with FFN layers
OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing structured pruning methods fail to identify outlier-triggering tokens and uniform layer-wise sparsity misaligns with heterogeneous outlier distributions. |
| Approach: | They propose a framework that prioritizes capturing outlier-triggering tokens rather than reconstructing full hidden distributions. |
| Outcome: | Experiments on LLaMA2, LLama3 and OPT show that the proposed framework outperforms state-of-the-art methods and achieves 25% perplexity reduction at 1.6 speedup. |
Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression (2026.acl-long)
Copied to clipboard
Luoyang Sun, Guangyan Li, Cheng Deng, Haifeng Zhang, Jian Zhao, Yongqiang Tang, Wensheng Zhang, Jun Wang
| Challenge: | Large language models (LLMs) excel at natural language tasks but face deployment bottlenecks due to computational demands. |
| Approach: | They propose a training-free framework that exploits activation and weight sparsity . they use a three-tier routing strategy that uses magnitude-based pruning . |
| Outcome: | Experiments on Llama and Mistral models show that DAWS outperforms activation-weight sparsity pruning methods. |
LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies reveal that much of the knowledge in a Transformer-based Large Language Model (LLM) is encoded in its feed-forward (FFN) layers, where each FNN layer can be interpreted as the summation of sub-updates, each corresponding to a weighted column vector from the FFN’s value parameter matrix. |
| Approach: | They propose a method that computes relevance scores associated with value vectors in FFN layers and leverages these scores to dynamically adjust the contribution of sub-updates. |
| Outcome: | The proposed framework outperforms baseline approaches in fine-tuning and zero-shot settings while requiring significantly fewer tunable parameters. |
Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained large language models can be fine-tuned with instruction tuning to align the model responses with human intentions. |
| Approach: | They investigate the effectiveness of parameter efficient fine-tuning (PEFT) of the Q-Former with visual reasoning benchmarks ScienceQA and IconQA. |
| Outcome: | The proposed model achieves comparable performance to full fine-tuning using under 2% of the trainable parameters. |
Deputy: Accelerating Large Language Model Inference with Dynamic Low-Rank Substitution (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dynamic schemes such as early-exit and layer-drop reduce FLOPs but break batch processing or introduce KV-cache inconsistency. |
| Approach: | They propose a dynamic low-rank substitution framework that employs a lightweight decision module at each layer to dynamically determine the execution branch for different tokens. |
| Outcome: | The proposed model reduces computation by approximately 40% compared to the original dense model while outperforming existing baseline methods. |
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)
Copied to clipboard
Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu
| Challenge: | Existing sparsification methods like pruning can lose model knowledge through parameter removal. |
| Approach: | They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. |
| Outcome: | The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints. |