NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
18 results for “keyword:"intrinsic dimension"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]OUTPUT WITHOUT WARRANT: SPECTRAL DIMENSION READOUTS CANNOT CERTIFY THEIR OWN HYPOTHESES▲6.1k2.00
[PDF]Intrinsic Dimension Reads Within-Class Structure Below the Class Size and Class-Mean Geometry Above It▼1.3k1.75
[PDF]How to escape the alignment resistance dilemma of LLM? An extended elasticity theory from data dimension perspective.▲3952.67
[PDF]Dimension Is Free, Horizon Is Not: When Evolution Strategies Rival Policy Gradients for LLM Fine-Tuning▼4.5k2.67
[PDF]Challenging the Manifold Hypothesis: A Geometric Diagnostic for Data and Representation Spaces▼1361.33
[PDF]Learning Long-Horizon Flow Maps in High Dimensions: From a Regression Surrogate to Efficient Statistical Learning▲3952.67
[PDF]Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data▲6.1k2.00
[PDF]Apparent Compression, Real Stability: The Intrinsic Dimension of Learning a Quantum Wavefunction▲3952.67
Withdrawn or desk rejected (4)
[PDF]LIFE: LOCAL INTRINSIC DIMENSION-GUIDED FEATURE EDITING FOR ONE-TOKEN, ONE-LAYER HALLUCINATION REPAIR IN VISION-LANGUAGE MODELSWithdrawn1.67