DOI,IST REx ID,Research Group,Title of publication
10.15479/AT-ISTA-21854,21854,"GradSch,DaAl",On the utility and effects of efficiency in artificial neural networks
null,21857,"GradSch,DaAl",Panza: Investigating the feasibility of fully-local personalized text generation
10.48550/arXiv.2601.23153,21859,"GradSch,DaAl",Behemoth: Benchmarking unlearning in LLMs using fully synthetic data
10.1145/3710848.3710871,19877,DaAl,MARLIN: Mixed-precision auto-regressive parallel inference on Large Language Models
10.1007/s00446-025-00487-7,19969,DaAl,Near-optimal leader election in population protocols on graphs
null,20032,"DaAl,FrLo",Scalable mechanistic neural networks
null,20034,DaAl,LDAdam: Adaptive optimization from low-dimensional gradient statistics
null,20037,DaAl,"Wasserstein distances, neuronal entanglement, and sparsity"
null,20038,DaAl,The journey matters: Average parameter count over pre-training unifies sparse and dense scaling laws
10.1145/3712256.3726425,20224,DaAl,In the search of optimal tree networks: Hardness and heuristics
null,20684,DaAl,"“Give me BF16 or give me death”? Accuracy-performance trade-offs in LLM quantization"
10.1021/acs.jctc.5c01248,20704,"BiCh,DaAl",Scalable multitemperature free energy sampling of classical Ising spin states
10.1609/aaai.v39i19.34290,19713,DaAl,Hybrid decentralized optimization: Leveraging both first- and zeroth-order optimizers for faster convergence
null,20820,DaAl,EvoPress: Accurate dynamic model compression via evolutionary search
null,20821,DaAl,Layer-wise quantization for quantized optimistic dual averaging
10.4230/LIPIcs.DISC.2025.3,21250,"DaAl,GradSch",An almost-logarithmic lower bound for leader election with bounded value contention
10.1007/978-3-031-85747-8_6,21257,"DaAl,GradSch",Sparse Fine-Tuning for Inference Acceleration of Large Language Models
10.48550/arXiv.2502.06560,21858,"GradSch,DaAl",Position: It's time to act on the risk of efficient personalized text generation
10.1109/ICDCS60910.2024.00084,18070,DaAl,Federated SGD with local asynchrony
null,18113,"DaAl,GradSch",Extreme compression of large language models via additive quantization