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
9,443 results for “keyword:"lan"” in ICLR 2027. 2,279 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SocialBench : Evaluating Multimodal Perception, Understanding and Reasoning in Social Settings▲3772.67
[PDF]Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models▼4.5k2.67
[PDF]Reality Flow Integrity: Defending VLM-Enabled Wearable Assistants against Physical Prompt Injection▲9.2k2.67
[PDF]MaLoRA: Mitigating Text-Centric Bias in Multimodal Large Language Models through Key-Space Alignment▲3772.67
[PDF]Structural Gaming in Financial Safety Alignment: A Dynamic Strategic Evasion Framework via Tabular Representations▼1.2k1.67
[PDF]Revealing the Emergent Learning Mechanisms of Critic Models in PPO for LLM Reinforcement Learning▲3772.67
[PDF]SGPrune: Subspace-Guided Token Pruning for Multi-View Vision-Language Models in Autonomous Driving▲262.75
[PDF]Rethinking Code Localization through Repair-Context Completeness: From Structural and Code Coverage Analysis to Context Augmentation▼1351.33
[PDF]AlphaOpsBench: Benchmarking End-to-End Alpha Strategy Operationalization in Prediction Markets▼1.2k1.67
[PDF]PUSH: Sparse Representation Dynamics Enable Cost-Efficient Reinforcement Learning in LLMs▼1.2k3.00
[PDF]TheraWorld: A Medical World Model in Hyperbolic Space for Treatment-Driven Disease Trajectory Simulation▲5.4k3.00
[PDF]MemCache: Memory-Augmented Adaptive Token Caching for Efficient Vision-Language-Action Inference▲5.4k3.00
[PDF]Coach-Guided Autonomous Reflection Improves Deception and Detection in Multi‑Agent Werewolf Games▼4.3k2.00
[PDF]Beyond Problem-Solving: A Multi-Agent Framework and Pedagogically-Aligned Benchmark for Evaluating LLMs’ Educational Question Generation▼1351.33
[PDF]Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models▼1611.50
[PDF]Risk Concealment Across Modalities: Structural Obfuscation Attacks on Multimodal LLMs in Finance▼1.2k1.67
Withdrawn or desk rejected (2,279)
[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