activity
20212026
most citedEmbracing Federated Learning: Enabling Weak Client Participation via Partial Model Training

13 citations · 28 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2026

Output-Aware Rotation for INT2 KV-Cache Quantization

Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4

The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important…

cs.LG2026

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Vincent-Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy +1

Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the…

cs.LG2026

Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning

Minkyu Kim, Vincent-Daniel Yun, Youngrae Kim +3

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural prop…

cs.LG2026

Locality-Aware Redundancy Pruning for LLM Depth Compression

Vincent-Daniel Yun, Youngrae Kim, Woosang Lim +3

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing…

cs.LG2025

Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity

Vincent-Daniel Yun, Junhyuk Jo, Sunwoo Lee

Deep neural networks achieve outstanding performance across vision and language tasks, yet their large parameter counts limit deployment in resource-constrained settings. One-shot…

cs.LG202413 cited

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training

Sunwoo Lee, Tuo Zhang, Saurav Prakash +2

In Federated Learning (FL), clients may have weak devices that cannot train the full model or even hold it in their memory space. To implement large-scale FL applications, thus, it…