firstbacksecondback
48 Results
|
Poster
|
Tue 4:30 |
Calibration Bottleneck: Over-compressed Representations are Less Calibratable Deng-Bao Wang · Min-Ling Zhang |
|
|
Oral
|
Wed 7:45 |
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking Wenshuo Li · Xinghao Chen · Han Shu · Yehui Tang · Yunhe Wang |
|
|
Poster
|
Tue 4:30 |
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging Jinuk Kim · Marwa El Halabi · Mingi Ji · Hyun Oh Song |
|
|
Poster
|
Thu 2:30 |
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference Harry Dong · Xinyu Yang · Zhenyu Zhang · Zhangyang “Atlas” Wang · Yuejie Chi · Beidi Chen |
|
|
Poster
|
Tue 4:30 |
Compressing Large Language Models by Joint Sparsification and Quantization Jinyang Guo · Jianyu Wu · Zining Wang · Jiaheng Liu · Ge Yang · Yifu Ding · Ruihao Gong · Haotong Qin · Xianglong Liu |
|
|
Poster
|
Wed 4:30 |
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression Junyuan Hong · Jinhao Duan · Chenhui Zhang · Zhangheng Li · Chulin Xie · Kelsey Lieberman · James Diffenderfer · Brian Bartoldson · Ajay Jaiswal · Kaidi Xu · Bhavya Kailkhura · Dan Hendrycks · Dawn Song · Zhangyang “Atlas” Wang · Bo Li |
|
|
Poster
|
Thu 4:30 |
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference Piotr Nawrot · Adrian Łańcucki · Marcin Chochowski · David Tarjan · Edoardo Ponti |
|
|
Poster
|
Tue 2:30 |
Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth Kevin Kögler · Aleksandr Shevchenko · Hamed Hassani · Marco Mondelli |
|
|
Poster
|
Wed 4:30 |
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking Wenshuo Li · Xinghao Chen · Han Shu · Yehui Tang · Yunhe Wang |
|
|
Poster
|
Tue 4:30 |
Debiased Distribution Compression Lingxiao Li · Raaz Dwivedi · Lester Mackey |
|
|
Poster
|
Thu 2:30 |
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models guangyan li · Yongqiang Tang · Wensheng Zhang |
|
|
Oral
|
Thu 7:45 |
Data-free Neural Representation Compression with Riemannian Neural Dynamics Zhengqi Pei · Anran Zhang · Shuhui Wang · Xiangyang Ji · Qingming Huang |