Aditya Guru

Adignite's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 4 months ago

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization

Paper • 2506.22396 • Published Jun 27

ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering

Paper • 2508.07321 • Published Aug 10