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
15,060 results for “keyword:"ode"” in ICLR 2027. 3,645 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Correct Yet Insensitive to Vision: Adaptive Intervention to Improve Visual Reliance in VLMs▲5093.00
[PDF]Retrieval Gains, Similarity Losses: Controllable Specialisation for Entity-Specific Few-Shot Adaptation▲6.1k2.00
[PDF]Beyond Verbs and Trajectories: Physical Action Primitives through Local Interaction Laws▼4.3k2.00
[PDF]Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models▲20k2.67
[PDF]PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation▲3.0k2.50
[PDF]Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition▼4.5k2.67
[PDF]ReWorld: Adaptive Corrective Simulation from World Models for Embodied Policy Learning▼5.9k2.33
[PDF]WaveOperator RNN: Learning Structured World Dynamics with Trainable Local Wave Propagation▼1611.50
[PDF]Beyond Attention Masks: Instruction Anchoring for Efficient In-Context Diffusion Generation▲5093.00
[PDF]Extra Dimensions, Simpler Flows: Accelerating Flow Matching Training with Pretrained Visual Representations▲9.2k2.67
[PDF]Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights▼4.3k2.00
[PDF]Fair Credit Across Correct Modes: Mitigating Correct-Path Coverage Collapse in On-Policy Self-Distillation for Language Models▲9.2k2.67
[PDF]Don't Mind the Gap: Interpretable Vision-Language Models via Independent Sparse Autoencoders▲3.0k2.33
[PDF]Read the Trajectory, Not Just the Endpoint: Calibrated Utility Readout for Transfer Attacks▼4.3k2.00
[PDF]Freeze the Dynamics, Learn the Interface: Modular Recurrent Scaffolds for Compositional World Models▼1361.33
[PDF]IteraFigure: Editable Structured Scientific Diagram Generation with Atomic Local Editing▲9.2k2.67
[PDF]ELiT: An Expressive Lite Transformer for CTR Prediction with Error-Bounded Attention Approximation▲3.0k2.33
[PDF]Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models▼4.3k2.00
[PDF]Fix What's Wrong, Keep What's Right: Hallucination Repair for LLM-Based Optimization Modeling▼5.9k2.33
Withdrawn or desk rejected (3,645)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00