Aditya Desai
8 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (3) π Interdisciplinary Bridge π Cross-Pollinator (7)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(13)
π₯
Unstoppable
(5)
Conferences
NIPS (4)
ICML (3)
ICLR (1)
Top co-authors
Keywords
parameter sharing
(3)
model compression
(3)
representation learning
(1)
attention mechanism
(1)
knowledge distillation
(1)
multi-modal learning
(1)
efficient inference
(1)
deep learning
(1)
neural network optimization
(1)
sparse matrix
(1)
memory efficiency
(1)
memory optimization
(1)
recommendation system
(1)
inference optimization
(1)
inference efficiency
(1)
weight quantization
(1)
kv cache compression
(1)
inference acceleration
(1)
kv cache
(1)
sketch structured transform
(1)
Papers
HashAttention: Semantic Sparsity for Faster Inference
ICML 2025
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
ICML 2025
In defense of parameter sharing for model-compression
ICLR 2024
SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform
NIPS 2024
Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing
ICML 2023
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
NIPS 2023
The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model
NIPS 2022
Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler
NIPS 2021