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4,860 results for “keyword:"lm"” in ICLR 2027. 941 withdrawn or desk rejected listed apart.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]DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability▲3872.67
[PDF]Discover Changes Gradually: LLM-Guided Progressive Network for Remote Sensing Change Detection▼1611.50
[PDF]Learning to Reason Efficiently in Videos: Reinforcement Learning with Short- and Long-Term Rewards▼1.2k1.67
[PDF]PriorBridge: Integrating Language Priors into Prior-Fitted Networks via Rule-Guided Prediction Correction▼4.3k2.00
[PDF]CONSTRUCTING A PROVENANCE-ATTRIBUTION BENCHMARK OVER THE SCIENTIFIC LITERATURE: A SUPPLY CENSUS AND A SHORTCUT GATE▼1611.50
[PDF]SenseMath: Do LLMs Have Number Sense? Evaluating Shortcut Use, Judgment, and Generation▲3872.67
[PDF]AgentFrontier: Stabilizing Learning Frontiers in Reinforcement Learning for Active Reasoning Agents▲3.0k2.33
[PDF]HyperMAS: Evolving Collaboration Primitives for Scalable Multi-Agent LLM Collaboration▲9.2k2.67
[PDF]Which Structures Amplify Attacks? Uncovering Collaboration-Induced Vulnerability in LLM Multi-Agent Systems▼4.5k2.67
[PDF]Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark▼1.2k1.67
[PDF]Human Before the Loop: Constraining the Action Space Improves Security, Reliability, and Capability in AI Agents▼4.3k2.00
[PDF]ACCORDION: Breaking Dependency Barriers in Multi-Agent LLM Workflows via Context Speculation▲3.0k2.50
[PDF]CARVE: Coordinating Imitation and Exploration through Reward Variance for LLM Reasoning Post-Training▼1361.33
Withdrawn or desk rejected (941)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