Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Paper • 2604.10098 • Published • 27
zunhaisu
zunhai
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation submitted a paper about 3 hours ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation upvoted a paper 19 days ago
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and PlanningOrganizations
None yet
submitted a
paper to Daily Papers about 3 hours ago
authored a
paper 3 months ago
authored 4
papers 5 months ago
RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
Paper • 2501.16383 • Published
AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models
Paper • 2501.15021 • Published
LongCat-Flash Technical Report
Paper • 2509.01322 • Published • 8
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 98
authored a
paper 8 months ago