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4,865 results for “keyword:"lm"” in ICLR 2027. 936 withdrawn or desk rejected listed apart.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]Gradient Subspace Dynamics During Supervised Fine-Tuning of LLMs: Input–Output Asymmetry▼4.3k2.00
[PDF]LLMs for Binary Decompilation: Can Large Language Models Reconstruct Source Code from Compiled Binaries?▼1.2k1.67
[PDF]One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness▲3.0k2.33
[PDF]Finale: Reconstructing Local Supervision with Terminal-Anchored Replay for End-to-End Web Agents▲5.4k3.00
[PDF]HackBench: A Benchmarking Suite for Evaluating Naturally-Emerging Reward Hacking in LLMs▼4.3k2.00
[PDF]ADE: Accurate, Inference-efficient, and Tunable Delta Compression for Task-specific Fine-tuned Foundation Models▼5.8k2.33
[PDF]Discover-Many-Worlds: Reinforcement Learning for Scientific Discovery in Automatically Generated Physics▼4.5k2.67
[PDF]Anchored but Not Protected: When Refusal Erodes During Fine-Tuning, and Whether Holding One Direction Stops It▲13k2.33
[PDF]When Agents Should Not Remember: Habitual Execution for Retrieval-Efficient Long-Running LLM Agents▼1361.33
[PDF]NicheLedger: Replacing References and Graders on Fixed Answers of Spatial Transcriptomics Agents▲3.0k2.33
[PDF]Rethinking Program Search for AutoML: A Reachability Analysis of LLM-Edited Training Programs▲13k2.33
[PDF]AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic Reinforcement Learning▼4.3k2.00
Withdrawn or desk rejected (936)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