paper
Braun et al. 2025 Compressed Computation
paperactiveprovisional
braun-et-al-2025-compressed-computation-9d88f275·1 events·first seen 2d agoAliases: Braun et al. 2025 Compressed Computation
Co-occurring entities
More like this (12)
Compressed Computation is (probably) not Computation in Superpositionthought compressioncomputational imagingEnd-to-End Context Compression at ScaleNNCF (Neural Network Compression Framework)SKIM (SKIll coMpression)gradient compressionAdaptive Multi-Resolution Procedural Knowledge Compression for Large Language Modelsvisual-token compressionOn Subquadratic Architectures: From Applications to PrinciplesContext-Driven Incremental CompressionPlanning-aligned Token Compression for Long-Context Autonomous Driving
Recent events (1)
Paper argues Compressed Computation toy model is not computation in superposition
A new arXiv preprint challenges the Compressed Computation (CC) toy model introduced by Braun et al. (2025), which appeared to compute 100 ReLU functions using only 50 neurons. The authors show that apparent performance gains arise from unintended input mixing via a noisy residual stream rather than genuine superposition, with learned neuron directions concentrating in the subspace of the top 50 eigenvalues of the mixing matrix. A semi-non-negative matrix factorization baseline derived purely from the mixing matrix reproduces the qualitative loss profile, supporting the conclusion that CC is not a valid toy model of computation in superposition.