acceptodds: the papers of ICLR 2027
33,035 results for “keyword:"r"” in ICLR 2027. 8,265 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]HerKry: A Hermite–Gaussian Hierarchy with Recurrent Krylov Trajectory Modeling for Robust Sparse-View CT Reconstruction▼1.2k3.00
[PDF]MAX-Cache: Motion-Aligned Activation Reuse with Mismatch-Guided Selective Recomputation for Efficient Autoregressive Video Diffusion▲3132.67
[PDF]SEGA: Multi-View 3D Instance Segmentation with Geometry-Guided Association for Indoor Environments▲3132.67
[PDF]Who Is the Real Witness? Localizing Attention Heads through Image-Induced Semantic Shifts in LVLMs▼4.3k2.00
[PDF]Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation▲4.7k3.00
[PDF]Beyond Single Roles: Structured Role Discovery for Cooperative Multi-Agent Reinforcement Learning▲5.3k3.00
[PDF]Simple Temperature Scaling of Channel Graphs Is Enough for Multivariate Time Series Forecasting
[PDF]GradTrace: Gradient-Neighborhood Filtering for Backdoor Defense in Multimodal Instruction Tuning▼4.3k2.00
[PDF]When the Gate Does Not Gate: Bounded Memory Injection with Normalized Direction for Vision-Language-Action Models▲2603.67
[PDF]Can Agents Develop Private Shorthand with You? Benchmarking Dyadic Convention Formation in Long-Term Conversations▲5.3k3.00
[PDF]When Does Learning-Rate Retuning Help? Attainable Output Geometry Under a Fixed Update Budget▼5.9k2.33
[PDF]Edit the Model You Deploy: Quantization Weakens Knowledge Edits Through Their Conditioning▼1361.33
[PDF]Joint Contrastive-Adversarial Representation Learning for Unsupervised Domain Adaptation▼1.2k1.67
Withdrawn or desk rejected (8,265)
[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]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67