DOI,IST REx ID,Research Group,Title of publication
null,18977,DaAl,SpQR: A sparse-quantized representation for near-lossless LLM weight compression
null,18996,FrLo,Identifying general mechanism shifts in linear causal representations
10.18653/v1/2024.findings-emnlp.705,18998,"GradSch,HeEd",The shape of word embeddings: Quantifying non-isometry with topological data analysis
10.48550/ARXIV.2406.04102,18999,"GradSch,HeEd",Chromatic topological data analysis
null,19005,"CaMu,FrLo",Marrying causal representation learning with dynamical systems for science
null,19007,FrLo,Identifiable object-centric representation learning via probabilistic slot attention
10.48550/arXiv.2412.14923,19013,TiBr,Terminal singularities of the moduli space of curves on low degree hypersurfaces and the circle method
10.1145/3680528.3687591,19028,,A statistical approach to Monte Carlo denoising
10.1093/imrn/rnae066,19051,TiBr,The polynomial sieve and equal sums of like polynomials
10.48550/arXiv.2403.06833,19063,"GradSch,ChLa",Can LLMs separate instructions from data? And what do we even mean by that?
10.5281/ZENODO.10687169,19307,CaMu,Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation
null,19408,ChLa,Continual learning: Applications and the road forward
10.1038/s44220-024-00316-z,19446,GaNo,Large-scale population data enrichment in mental health research
10.1016/j.cmet.2024.11.009,19470,,Acute and circadian feedforward regulation of agouti-related peptide hunger neurons
10.1093/imrn/rnad266,19486,,The 3-isogeny selmer groups of the elliptic curves y2=x3+n2
null,19510,DaAl,MICROADAM: Accurate adaptive optimization with low space overhead and provable convergence
null,19511,DaAl,QuaRot: Outlier-free 4-bit inference in rotated LLMs
null,19512,MoHe,Continual counting with gradual privacy expiration
null,19515,FrLo,Latent functional maps: A spectral framework for representation alignment
null,19517,FrLo,C2M3: Cycle-consistent multi-model merging