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
9,448 results for “keyword:"lan"” in ICLR 2027. 2,274 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Visual Thought Matters: Learning to Ground and Refine Continuous Reasoning for Generalizable Deepfake Detection▲3862.67
[PDF]TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training▼5.9k2.33
[PDF]Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning▼5.9k2.33
[PDF]When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition▲5.4k3.00
[PDF]SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision–Language Models▲352.75
[PDF]Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills▲3862.67
[PDF]Understanding Forgetting Dynamics in Full Fine-Tuning of LLMs: A Neural Tangent Kernel Perspective▲3862.67
[PDF]SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning▲6.1k2.00
Withdrawn or desk rejected (2,274)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]NeuroFORM: Neuro-Symbolic Formalization of Legal Rules with Counterexample-Guided RefinementWithdrawn2.00
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected