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
140 results for “keyword:"collapse"” in ICLR 2027. 29 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Efficient Multi-Agent Reinforcement Learning under Sparse Binary Team Rewards with Few Suboptimal Prior Trajectories▲3.8k2.50
[PDF]From Set Diversity to Output Diversity: Progressive Selection for Inference-Time Alignment▲5103.00
[PDF]What Does Neural Collapse Indicate for Generalization?: A Singular Learning Theory Perspective▲3.9k1.67
[PDF]When High ROC-AUC Fails: Score Collapse and the Gradient Exposure Deficit in Anomaly Detection▼1361.33
[PDF]Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?▼5.8k2.33
[PDF]Mean Mode Screaming: Mean–Variance Split Residuals for 1000-Layer Diffusion Transformers▼5.8k2.33
[PDF]Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model Analysis▼1.2k3.00
[PDF]When Simulator Targets Suppress Diversity in Conditional Diffusion: Evidence from ECG Generation▲3.0k2.33
[PDF]GeMoT: Encoding Class Knowledge in Geometry and Moments for Source-Free EEG Domain Adaptation▲11.00
[PDF]Deeper Is Not Better for Quantized CLIP: Early Readout Recovers Accuracy While Cutting Compute▼5.8k2.33
[PDF]Model Collapse Is Avoidable Even as Real Data Vanishes: A Sharp Criterion for Iterative Gaussian Estimation▲3972.67
[PDF]The Vanishing Middle: Reinforcement Learning Erases the Uncertain Category in Ordinal Classification▲5.4k3.00
[PDF]Neutralizing 0th-Order Residual Interferences in Layer-wise Relevance Propagation via Geometric Trajectory Realignment▼1.2k1.67
[PDF]WebMix-Collapse: A Rewrite Benchmark for Sizing the Length Confound in Short-Form Synthetic-Text Detection▲11k2.00
[PDF]RST: Routes for Certifying and Constructing Prescribed Information in Variational Autoencoders▼1.2k1.67
[PDF]Winner-Take-All: Where Exponential Entropy Collapse Comes From in Reinforcement Learning for LLMs▲5.4k3.00
[PDF]Broadcast, Reinforce, Repeat: Attention Dynamics Behind Repetition Collapse in Diffusion Language Model Forecasting▲1.7k3.33
[PDF]Beyond Self-Consensus: Mitigating Self-Reinforcing Exploration Bias in Test-Time Reinforcement Learning▼4.3k2.00
[PDF]What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives▼4.3k2.00
Withdrawn or desk rejected (29)
[PDF]The Normalization Landscape in Continual Learning: Resolving Moving-Average Breakdown and Subspace Interference for Buffer-Free Edge IntelligenceWithdrawn
[PDF]Predicting the Predictable: Feature Suppression in Joint-Embedding Predictive ArchitecturesDesk rejected
[PDF]Geometry is Not the Trap: A Spectral‑Reopening Diagnostic for Protocol-Bounded Optimization LockingWithdrawn2.00
[PDF]The Retrieval Paradox: Why RAG Fails Medical Vision-Language Models Across ArchitecturesWithdrawn1.00
[PDF]Symmetry-Projected Neural Collapse: Anisotropic Contraction of Structured Within-Class NuisanceDesk rejected