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
4,865 results for “keyword:"lm"” in ICLR 2027. 936 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Proxy Calibration Controls the Wrong Risk: Accepted-Set Target Mismatch in Selective LLMs▼4.3k2.00
[PDF]ORBIT: EFFICIENT VERIFICATION OF EDITED LLM OUTPUTS WITH COMPACT ROUTING HINTS AND LOCAL SEMANTIC ASSESSMENT▼1.3k1.75
[PDF]From Sampling to Selection: Grounding LLM Reasoning with Predictive Models of Physical Systems▲3.0k2.33
[PDF]Agents Verify Their Assumptions, Not the Specification: Interpretation Lock-in in Autonomous Coding Agents▼5.3k1.33
[PDF]Doubt Before Acting: Assumption-Level Representation Editing for Safe Embodied LLM Planning▲5.9k1.67
[PDF]OWG: Structuring Agent Evidence as Outcome-Witness Graphs for Efficient Long-Horizon Task Closure▼4.3k2.00
[PDF]Not All Memory Updates Are Equal: A Benchmark for Typed Revision in Long-Term LLM Agents▼4.3k2.00
[PDF]Not All Tokens Should Update the Same Parameters: Prefix-Conditioned Gradient Routing for On-Policy Distillation▼1.2k3.00
[PDF]Learning What vs. Learning How: Decomposing Task and Interface Competence in Agentic Training▲5103.00
[PDF]DriftBench: An Execution-Based Benchmark for LLM SQL Query Repair Under Schema Evolution▲3952.67
[PDF]Don't Miss a Deadline: Online Temporal Planning for Multi-Goal LLM Agents under Partial Observability▼5.8k2.33
[PDF]ActVis: Active Maintenance of Structured Visual Evidence for Efficient Visual Chain-of-Thought Reasoning▼1.2k1.67
[PDF]Recursively Updated Summaries Can Amplify a Remembered Betrayal’s Effect on a Qwen3-8B Agent’s Stated Willingness▼4.3k2.00
[PDF]One Size Fits None: Exercise-Adaptive Cognitive Route Induction for Cognitive Diagnosis with LLM Supervision▼5.8k2.33
[PDF]ONE VOCABULARY PASS, MANY REQUESTS: A STREAM-ONCE OUTPUT-HEAD KERNEL FOR CONCURRENT LLM DECODING▼4.3k2.00
[PDF]FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents▼5.8k2.33
[PDF]RadarVL: From Model-Generated Candidates to Expert-Verified Supervision for Domain-Specialized VLMs▼13k2.00
[PDF]RouteTrace: Membership Inference from Routed Update Traces in Mixture-of-Experts Models▼1.2k1.67
Withdrawn or desk rejected (936)
[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