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
4,861 results for “keyword:"lm"” in ICLR 2027. 940 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation Algorithms▲3.9k1.67
[PDF]LLM Benchmark Compression via Maximum Independent Set Prompt Selection on Proximity Graphs▼4.3k2.00
[PDF]OracleResolve: Hypothesis-Guided Evidence Reasoning for Oracle Bone Script Decipherment▲6.1k2.00
[PDF]Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers▲11.00
[PDF]MAPF-Evo: LLM-Driven Evolution of Heuristics for Conflict Elimination in Multi-Agent Path Finding▼4.5k2.67
[PDF]MedGuideEvolve: Evolving Transferable Clinical Experience Cards from Cases under Established Guidelines▼4.3k2.00
[PDF]UnCurl: Reliability-Conditioned Partial Sharing for Joint Curriculum and Exploration Control▼5.8k2.33
[PDF]Pareto Frontier of LLM Test-Time Compute: Adaptive Rollouts and Voting Under Token Budgets▲3.0k2.33
[PDF]Hallucination-Corrected Action Compression via LLM-RL Coordination for Task-Oriented Dialogue policy optimization▼1361.33
[PDF]InteractShift: Diagnosing Doctor LLM Consultation Degradation under Difficult Interactions via Fact-Anchored Paired Stress Testing▼12k1.67
[PDF]LatentGym: A Testbed for Cross-task Experiential Learning with Contollable Latent Structure▼1.2k3.00
[PDF]ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs▼4.3k2.00
[PDF]Does Chain-of-Thought Follow the Computation? A Graph-Based Study of Reasoning Faithfulness▼1.2k1.67
[PDF]Attribution Is a Propagation Problem: End-to-End Causal Evidence Attribution in Multi-Agent Systems▲11.00
[PDF]Where to Speculate: Cross-Request Survival-Value Allocation for Batched Speculative Decoding▼1.2k1.67
Withdrawn or desk rejected (940)
[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