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
25 results for “keyword:"deep learning theory"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Gradient-Descent Based Convergence and Error Analysis of Flow Matching in Deep ReLU Networks▼1.2k1.67
[PDF]A Framework for Analyzing DNN Representation Quality: Dynamics of Interaction Generalizability▼71.25
[PDF]Two Timescales of Forgetting in Fine-tuning of Language Models: Fast Behavioral Suppression and Slow Representational Drift▲2843.00
[PDF]Learning Abstract Disentangled Factors from Entangled Conjunctive Codes through Compositional Tasks▼5.8k2.33
[PDF]Understanding and Mitigating the Overcorrection in Machine Unlearning via Feature Learning▼4.3k2.00
[PDF]How Much Rank Does LoRA Need? Task-Dependent Rank-Error Bounds for Transformer Attention▼1.2k1.67
[PDF]Support-Aware Shielding Restores Safety for Predictive World-Model Control under Shift▼1.2k1.67
[PDF]When the Change Carries No Energy: A Detectable Regime Change That No Learned Monitor Detects▼1351.33
[PDF]Your World Model Is Not Blind, Your Detector Is: Native Prediction Errors for Regime Detection▲3.0k2.33
[PDF]When Conditional Generators Cannot Extrapolate: An Exactly Measurable Decomposition of Out-of-Distribution Error▼4.3k2.00
Withdrawn or desk rejected (5)
[PDF]A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data SelectionDesk rejected
[PDF]Representations have Trajectories: Characterizing Temporal Representation Dynamics in Neural NetworksWithdrawn1.00