Disentangling Representation Evolution in Transformers through Directional Decomposition
Paper • 2609.15975 • Published • 5
Heathcliff Bennet
hc-bennet
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 months ago
What Matters in Transformers? Not All Attention is Needed upvoted a paper 5 months ago
Making Large Language Models Efficient Dense RetrieversOrganizations
None yet
upvoted a paper 2 days ago
upvoted 4
papers 5 months ago
What Matters in Transformers? Not All Attention is Needed
Paper • 2406.15786 • Published • 33
Making Large Language Models Efficient Dense Retrievers
Paper • 2512.20612 • Published • 5
Understanding and Harnessing Sparsity in Unified Multimodal Models
Paper • 2512.02351 • Published • 6
Demystifying When Pruning Works via Representation Hierarchies
Paper • 2603.24652 • Published • 17