acceptodds: the papers of ICLR 2027
33,633 results for “keyword:"a"” in ICLR 2027. 8,430 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]From Spectral Responses to Task Effects: Auditing Frequency Dependence in Spiking Neural Networks▼1361.33
[PDF]Improving Entity-Configuration Generalization in Real-Time Strategy Games with Task Hypergraph Representation▲3.1k2.33
[PDF]Rethinking Causal Prior-Fitted Networks under Unobserved Confounding: Identifiability and Randomized Evidence▼1.3k1.75
[PDF]Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space▼1.2k1.67
[PDF]Forgetting is What to learn: Verifier-Grounded Minimal-Core Skills for Self-Evolving Agents▲3.1k2.33
[PDF]Dual-diffusion Spatial Interaction Representation Generalization for 3D Semantic Segmentation▼5.9k2.33
[PDF]CGPRNet: Cross-Scale Graph Prototype Refinement for Robust Few-Shot Semantic Segmentation▼1361.33
[PDF]Subject Identity as a Shortcut: Rethinking Self-Supervised Pretraining for EEG Foundation Models▲6.0k2.00
[PDF]Beyond Predictive Invariance: Causal Mechanism Transport for Generalizable Brain Network Analysis▼5.9k2.33
[PDF]PATHSMOOTHING: Mitigating Semantic Drift and Hub Noise via Path Evidence in KG-based RAG▼4.3k2.00
[PDF]Reproducing, Analyzing, and Detecting Reward Hacking in Rubric‑Based Reinforcement Learning▲3122.67
[PDF]Structure Lives in the Representation: Phase-Field Diffusion for Robust ECG Delineation▼4.3k2.00
[PDF]Improving Safety Alignment and Health Safe Completion via Query-Specific Safety Rubrics in OPSD▲13k2.33
[PDF]Learn Only What Helps : Task-Prioritized Distillation from Heterogeneous Teachers for 2D Molecular Property Prediction▼5.9k2.33
[PDF]Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models▼1361.33
Withdrawn or desk rejected (8,430)
[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