DASH discovers stronger hybrid attention architectures for LLMs via minutes-scale differentiable search, outperforming selector baselines and Jet-Nemotron on RULER while using 0.006% of prior search tokens.
hub
arXiv preprint arXiv:2402.02834 , volume=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Performance collapse in layer-pruned LLMs stems from disrupting the Silent Phase of decision-making, which blocks the transition to correct predictions, while the later Decisive Phase is robust to pruning.
SimDiff uses similarity and difference metrics to prune LLM layers more effectively than cosine similarity alone, retaining over 91% performance at 25% pruning on LLaMA2-7B.
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
Width pruning in Llama-3.2 models reduces parametric knowledge while enhancing instruction-following and preserving reasoning.
Pruning pretrained MoE models outperforms training from scratch under fixed budget, different expert compression methods converge after continued training, and progressive pruning plus multi-token KD improves the final 23A2B model.
Layer pruning preserves classification performance in LLMs but fundamentally limits recovery of generative reasoning capabilities even after extensive self-supervised finetuning.
TALE selectively prunes task-detrimental layers in LLMs at inference time to match or exceed baseline performance with lower computational cost across multiple models and tasks.
citing papers explorer
-
DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU
DASH discovers stronger hybrid attention architectures for LLMs via minutes-scale differentiable search, outperforming selector baselines and Jet-Nemotron on RULER while using 0.006% of prior search tokens.
-
Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
Performance collapse in layer-pruned LLMs stems from disrupting the Silent Phase of decision-making, which blocks the transition to correct predictions, while the later Decisive Phase is robust to pruning.
-
SimDiff: Depth Pruning via Similarity and Difference
SimDiff uses similarity and difference metrics to prune LLM layers more effectively than cosine similarity alone, retaining over 91% performance at 25% pruning on LLaMA2-7B.
-
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
-
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
Width pruning in Llama-3.2 models reduces parametric knowledge while enhancing instruction-following and preserving reasoning.
-
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
Pruning pretrained MoE models outperforms training from scratch under fixed budget, different expert compression methods converge after continued training, and progressive pruning plus multi-token KD improves the final 23A2B model.
-
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
Layer pruning preserves classification performance in LLMs but fundamentally limits recovery of generative reasoning capabilities even after extensive self-supervised finetuning.
-
TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
TALE selectively prunes task-detrimental layers in LLMs at inference time to match or exceed baseline performance with lower computational cost across multiple models and tasks.