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
4,877 results for “keyword:"large language models"” in ICLR 2027. 991 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]PEC-Detector: Planning-Execution Coupling Trajectories for Document-Level LLM-Generated Text Detection▲3822.67
[PDF]MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics▲9.2k2.67
[PDF]EMBER: Margin-Targeted Energy Reshaping for Mitigating Exact Memorization in Autoregressive Language Models▼1.2k1.67
[PDF]Harness Meets Diffusion: Single-ReAct-Guided Crystal Generation and Knowledge-Grounded Superconductivity Search▼1611.50
[PDF]Not All Preferences Are Strict: Tie-Aware Preference Optimization for Multi-Image MLLMs▼5.9k2.33
[PDF]Content-Dependent Recovery from Task-Relevant Activation Disruption in Large Language Models▲3822.67
[PDF]Can Correctness Readouts Choose the Right Answer? A Question-Level Audit of Compact KV-Cache Signals▼1361.33
[PDF]ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling▲3.0k2.33
[PDF]MoE-VQ: A Model-Agnostic Gaussian Vector Codebook for 2-Bit Expert Weight Quantization▼4.3k2.00
[PDF]When Is More Reasoning Worth It? Fallback-Aware Reasoning-Strategy Routing Under Hard Token Budgets▼1.2k1.67
[PDF]Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation▲9.2k2.67
[PDF]Beyond Fixed Sampling: Uncertainty-Aware Retrieval and Spatially-Grounded Reasoning for Fine-Grained Visual Recognition▼1.2k1.67
[PDF]LARCH: Latent Attribute Reasoning through Compositional Hierarchies for Generative Recommendation▼4.3k2.00
[PDF]EM-Lens: Towards Observation-Level Electromagnetic Signal Understanding via Agentic Zoom-and-Measure▲3.7k2.50
Withdrawn or desk rejected (991)
[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]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]ReLoC: Recursive Local Causal Modeling for Explaining and Predicting LLM-Based Multi-Agent BehaviorWithdrawn1.33
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected