DOI,IST REx ID,Research Group,Title of publication
10.1021/acs.jctc.5c01248,20704,"BiCh,DaAl",Scalable multitemperature free energy sampling of classical Ising spin states
10.52202/085713-1551,22826,DaAl,Hogwild! Inference: Parallel LLM generation via concurrent attention
10.52202/085713-3163,22830,DaAl,AutoJudge: Judge decoding without manual annotation
10.52202/085713-3966,22827,"DaAl,GradSch",HALO: Hadamard-assisted lower-precision optimization for LLMs
null,19518,"DaAl,MaMo",The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information
null,19519,DaAl,PV-tuning: Beyond straight-through estimation for extreme LLM compression
10.5281/ZENODO.14213091,19884,DaAl,MARLIN: Mixed-precision auto-regressive parallel inference on Large Language Models
10.1109/IPDPS57955.2024.00023,17332,DaAl,Wait-free trees with asymptotically-efficient range queries
null,15011,DaAl,"How to prune your language model: Recovering accuracy on the ""Sparsity May Cry"" benchmark"
10.1109/ICDCS60910.2024.00084,18070,DaAl,Federated SGD with local asynchrony
10.1145/3662158.3662768,17329,"DaAl,KrCh",Game dynamics and equilibrium computation in the population protocol model
null,18121,DaAl,SPADE: Sparsity-guided debugging for deep neural networks
null,18976,DaAl,AsGrad: A sharp unified analysis of asynchronous-SGD algorithms
null,18113,"DaAl,GradSch",Extreme compression of large language models via additive quantization
null,18975,DaAl,Error feedback can accurately compress preconditioners
null,18977,DaAl,SpQR: A sparse-quantized representation for near-lossless LLM weight compression
null,17093,"DaAl,ChLa",Communication-efficient federated learning with data and client heterogeneity
null,18117,"DaAl,GradSch",RoSA: Accurate parameter-efficient fine-tuning via robust adaptation
10.15479/at:ista:17485,17485,"GradSch,DaAl","Compressing large neural networks: Algorithms, systems and scaling laws"
null,18062,DaAl,Scaling laws for sparsely-connected foundation models