acceptodds: the papers of ICLR 2027
33,039 results for “keyword:"r"” in ICLR 2027. 8,261 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Wait or Take Over: Forecasting OOD Persistence and Recovery for Efficient Human-in-the-Loop Imitation Learning▲1.7k3.33
[PDF]Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents▲4673.00
[PDF]CoME: Empowering LLMs to Solve Complex Vehicle Routing Problems via Cross-Constraint Modeling Experience▼1.2k1.67
[PDF]Implicit Sparse Regularization in Momentum Gradient Descent: A Shifted Early Stopping Window Induced by Momentum and Depth▼4.3k2.00
[PDF]Token Mass, Not Geometry: A Confound in Embedding-Based Data Selection for Language Model Pretraining▼1.3k1.75
[PDF]A Lightweight Velocity Correction Framework for Improving Instruction Following in Few-Step Text-to-Image Generation▲4.7k3.00
[PDF]JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures▼4.5k2.67
[PDF]CausalSR: Scale-Resolved Causal Discovery from Time Series with Heterogeneous Responses▼1.2k1.67
[PDF]Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection▼13k2.00
[PDF]Forecasting the Forecasters: Training-Free Two-Phase Aggregation of Frozen Time-Series Foundation Models▼5.9k2.33
[PDF]Right, but Can You Show It? Correct Answers from Multimodal LLMs Rarely Come with Faithful Evidence▲5.3k3.00
[PDF]Blind Omnidirectional Video Super-Resolution via Geometry-Conditioned Probabilistic Degradation Modeling▼4.3k2.00
[PDF]CloudFlow: Physical Evolution-Guided Flow Matching for Multispectral Geostationary Meteorological Satellite Data Nowcasting▼4.3k2.00
[PDF]Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation▼4.3k2.00
Withdrawn or desk rejected (8,261)
[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