Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
Paper • 2605.09649 • Published • 13
👋 Open to Work
anton tuzov
antontuzovAI
AI & ML interests
AI Researcher
Recent Activity
liked a model about 6 hours ago
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 liked a dataset about 7 hours ago
inference-optimization/Gemma4-Responses-Nemotron liked a dataset about 7 hours ago
inference-optimization/dflash-code-multilingual-teacher-responses-qwen235bOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted 4
papers about 2 months ago
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Paper • 2607.28568 • Published • 188
Kronos: A Foundation Model for the Language of Financial Markets
Paper • 2508.02739 • Published • 57
VibeVoice Technical Report
Paper • 2508.19205 • Published • 180
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 525
upvoted an article about 2 months ago
Article
GPU Management: Why Idle GPUs Are the New Grounded Aircraft
Dharma-AI
• • 97