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140 results for “keyword:"collapse"” in ICLR 2027. 29 withdrawn or desk rejected listed apart.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]Intrinsic Dimension Reads Within-Class Structure Below the Class Size and Class-Mean Geometry Above It▼1.3k1.75
[PDF]Branch-JEPA: Learning Dynamics-Aware State Representations through Dual-Branch Patch Routing▼1361.33
[PDF]Which Updates Erase What the Base Model Knew? Optimizer-Conditioned Attribution of Reasoning-Support Loss in RLVR▼5.8k2.33
[PDF]Excitation Collapse in In-Context Control: Symmetric Freezing and Symmetry-Broken Imitation▼4.3k2.00
[PDF]When Agents Choose What to Observe: BEATS – Answer-Free Test-Time Selection for Verifiable-Reward Agents▼1.2k1.67
[PDF]Breaking the Historical Action Shortcut: Mitigating Visual Modality Collapse in Gaming VLA Models via Historical Action Noise Injection▼5.9k2.50
[PDF]Asymptotically Optimal Quantizer-Guided Sinkhorn Alignment for Mitigating Codebook Collapse▲3972.67
[PDF]LeDreamer: Bridging the Understanding of Representation Collapse Between JEPA and Sample-Efficient World Models▼5.8k2.33
[PDF]Where Should a Fixed Budget of Human Data Go? Allocating Across Time and Modes in Recursive Training▲3.9k1.67
[PDF]Information Present, Pathway Shut: A Conditional Flow Model That Never Used Its Diffraction Pattern▼4.3k2.00
[PDF]Rank Collapse Is Recoverable, Growing Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic▼1.2k1.67
[PDF]Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy▼1.2k1.67
[PDF]Harmonic Variance Embedding: A Positional-Style Representation for Counteracting Depth Dilution in Pre-Norm Transformers▲11.00
[PDF]From Neural Collapse Geometry to Structural Memory: Preserving Decision Structure in Continual Learning▼4.3k2.00
[PDF]NeuroLens: Cross-Modal EEG-to-Text Decoding via Structured State Space Encoding and Contrastive Alignment▼1.2k1.67
[PDF]MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space▼1.2k3.00
[PDF]PRISM: Mitigating Distillation Collapse in Tool-Use LLMs via Position-Level Target Reliability Masking▼1361.33
[PDF]Can Heterogeneous Artifacts Coexist? RGSA: Role-Specialized Global–Selective Adaptation for Mitigating Artifact Feature-Space Collapse in Unified Fake Image Detection▲3972.67
[PDF]Strong-Modality Collapse in Multimodal Fusion: Causal Analysis and Structural Solution▼4.3k2.00
[PDF]What Do Collapse Diagnostics Certify? Testing Alignment Objectives for Orthographic Shortcuts▼4.5k2.67
Withdrawn or desk rejected (29)
[PDF]Federated Shared–Private Basis Reallocation for Multimodal Representation CollapseDesk rejected2.33
[PDF]PrefMoE: Mitigating Preference Collapse in Personalized Multimodal Large Language ModelsWithdrawn1.67
[PDF]Self-Cleaning and Captured Anyway: A Measured Primitive for Error in a Store an Agent Writes to ItselfWithdrawn1.00