Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression Paper • 2503.02812 • Published Mar 4 • 9
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression Paper • 2503.02812 • Published Mar 4 • 9
Q-Filters Collection Pre-computed Q-Filters for efficient KV cache compression. • 15 items • Updated Mar 3 • 6
Pre-Trianing Data Packing Collection [ACL'24] Analysing the Impact of Sequence Composition on Language Model Pre-Training. https://github.com/yuzhaouoe/pretraining-data-packing • 10 items • Updated Mar 3
SAE-Based Representation Engineering Collection [NAACL'25] SAE-Based RepE github.com/yuzhaouoe/SAE-based-representation-engineering • 5 items • Updated Mar 3
SAE-Based Representation Engineering Collection [NAACL'25] SAE-Based RepE github.com/yuzhaouoe/SAE-based-representation-engineering • 5 items • Updated Mar 3
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20 • 3
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Paper • 2410.16090 • Published Oct 21, 2024 • 7 • 2
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations Paper • 2410.18860 • Published Oct 24, 2024 • 11
HIT-TMG/KaLM-embedding-multilingual-mini-v1 Sentence Similarity • Updated Jan 3 • 6.57k • • 21
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 Sentence Similarity • Updated 23 days ago • 32.6k • • 32
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20 • 3