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
252 results for “keyword:"stability"” in ICLR 2027. 61 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis▲3.0k2.33
[PDF]The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow▼4.5k2.67
[PDF]Retrieval Metastability and Centroid Hopping in Continuous Log-Sum-ReLU Dense Associative Memory▲3.0k2.33
[PDF]MovieRoll: Rolling Out Long-Form Videos with Hierarchical KV Caching and Cumulative Long Tuning▼4.3k2.00
[PDF]Silent Collapse: Diagnosing and Repairing Low-Precision Robot Policy Training at the Action Level▼4.3k2.00
[PDF]Auditing Permanence: Exact Write Accounting and a Matched-Volume Control for Optimizer-State Gates▼4.3k2.00
[PDF]Towards Robust Reasoning Trajectories: Certifying Chain-of-Thought Prefix Stability under Local Perturbations▲3952.67
[PDF]Seed-Level Instability in LLM Safety Alignment: Regime Shifts in Large-Margin Preference Optimization▼4.3k2.00
[PDF]Stable States as Block-Uniform Flips of the Symbolic Centroid in Binary Hopfield Neural Networks▼4.3k2.00
[PDF]Global Relevance Is Not Enough: Representative Candidate Construction and Residual-Based Evidence Preservation for Efficient, Reliable Medical MLLM Inference▲9.2k2.67
[PDF]When the Judge Changes the Verdict: Rank Instability and an Auditing Protocol for LLM-as-a-Judge▲6.1k2.00
[PDF]The Stored Action Does Not Identify the Sampled Latent: Finite-Precision Likelihood Replay in Squashed Policies▼1.2k1.67
[PDF]When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation▼4.3k2.00
[PDF]One Pixel Wider, a Different Click: How Image Preprocessing Destabilizes GUI Grounding▼5.9k2.50
[PDF]Beyond Static Embeddings: Finite-Query Certificates for Local Representation Stability▲5.4k3.00
[PDF]Locating, Removing, and Restoring: Auditing the Modular Account of Safety in Instruction-Tuned LLMs▼4.3k2.00
Withdrawn or desk rejected (61)
[PDF]Stability and Generalization of Noisy signSGD: From Sign Discontinuity to Gaussian SmoothingWithdrawn
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00
[PDF]The More The Merrier: Numerically Accurate Coded Computing for Machine Learning InferenceDesk rejected
[PDF]Beyond Fixed Precision: Measuring and Tracking Minimum Sufficient Precision in LearningWithdrawn2.00
[PDF]Restoring Co-Adaptation: An Endpoint Audit of Asymmetric Training in Multi-Agent Market MakingWithdrawn1.00