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
4,860 results for “keyword:"lm"” in ICLR 2027. 941 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TRUST: LLM Evaluation with Imperfect Judges via Reliability Transfer under Sparse Target Supervision▲3892.67
[PDF]DelTA: Discriminative Token Credit Assignment for Reinforcement Learning with Verifiable Rewards▲5103.00
[PDF]Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities▲3892.67
[PDF]FinTriad: A Multimodal, Multi-Agent System with Adaptive Memory for Tri-Horizon Portfolio Construction▼1.3k1.75
[PDF]Weak Models or Insensitive Metrics? Auditing and Training Fine-Grained Motion Captioning▲3892.67
[PDF]EvoMedAgent: Auditable Reasoning and Failure-Driven Memory Evolution for Medication Recommendation▲9.2k2.67
[PDF]IMPACT: Measuring Conditional Workflow Responses to Single-Span Model Substitution in Stateful LLM Agents▼1361.33
[PDF]HeteroLoRA-MoE: Heterogeneous Low-Rank Experts with Diverse Projection Patterns and Efficient GPU Kernels▼4.3k2.00
[PDF]All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable … Attacks▲13k2.33
[PDF]Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation▲13k2.33
[PDF]CounterCount: Diagnosing Knowledge Bias in How Vision-Language Models Count Attributes▼4.3k2.00
[PDF]Zero-LLM Trajectory Search over Line-Lifted Knowledge Graphs: Internalizing Query Decomposition for Multi-Hop RAG▲9.2k2.67
[PDF]Protect Before Evicting: Lagrangian-Guided Encoder Caching for Disaggregated Multimodal LLM Serving▼1361.33
[PDF]MetaSkill: Reusable Problem-Solving Methods for Adaptive Skill Orchestration in LLM Agents▼1.2k1.67
Withdrawn or desk rejected (941)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected