Ajay Kumar Jaiswal
17 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (12)
π
Cross-Pollinator
(12)
π€
Dynamic Duo
(13)
β
The Questioner
β‘
Prolific Year
(5)
π
Century Club
(17)
π
Trend Setter
Conferences
ICML (10)
ICLR (4)
EMNLP (3)
Top co-authors
Keywords
model compression
(4)
large language model
(3)
chain-of-thought prompting
(2)
lottery ticket hypothesis
(2)
neural network pruning
(2)
distributed learning
(1)
graph partitioning
(1)
code generation
(1)
model pruning
(1)
autoregressive decoding
(1)
early exit
(1)
weight averaging
(1)
weight pruning
(1)
sparse training
(1)
hierarchical representation
(1)
inference acceleration
(1)
layer skipping
(1)
skip connection
(1)
network pruning
(1)
in-context learning
(1)
Papers
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
ICML 2025
SEBRA : Debiasing through Self-Guided Bias Ranking
ICLR 2025
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework
EMNLP 2025
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
EMNLP 2024
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
EMNLP 2024
Compressing LLMs: The Truth is Rarely Pure and Never Simple
ICLR 2024
LLaGA: Large Language and Graph Assistant
ICML 2024
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
ICML 2024
Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
ICML 2024
Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textitIrreversibly$ and $\textitMonotonically$ Impairs βDifficult" Downstream Tasks in LLMs
ICML 2024
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
ICML 2024
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
ICLR 2023
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
ICLR 2023
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
ICML 2023
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
ICML 2023
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
ICML 2023
Training Your Sparse Neural Network Better with Any Mask
ICML 2022