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4,865 results for “keyword:"lm"” in ICLR 2027. 936 withdrawn or desk rejected listed apart.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]Watch what LLMs do, not what they say: Preference elicitation of AI agents through game performance▼4.5k2.67
[PDF]The Signal Survives, the Threshold Slips: Small LLM Agents After Quantization and Fine-Tuning▼1.2k1.67
[PDF]Triage Attention: Core-Protected Sparse Attention For Long-Video Vision-Language Models▼4.3k2.00
[PDF]SILICA-BENCH: EVALUATING LONG-HORIZON LLM AGENTS THROUGH VERIFIED RTL-TO-GDS IMPROVEMENT▲2843.00
[PDF]A PAUSE IN TIME SAVES NINE: PUNCTUATION-GUIDED ATTENTION FOR EFFICIENT MULTI-TOKEN REASONING▼4.3k2.00
[PDF]LongRx: Closed-Loop Medication Recommendation with Action-Coverage Reinforcement Learning▼1.2k1.67
[PDF]EAGLE: Grounding Multimodal LLM Judges for AI-Generated Image Assessment via Evidence Anchors▼5.8k2.33
[PDF]SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning▲3.0k2.33
[PDF]Evidence Is Not Authority: A Causal Study of State Arbitration in Long-Horizon Agent Memory▼1.2k1.67
[PDF]AnchorWrite: Detector-Query-Free Rewriting of LLM-Generated Text via Human-Reference Alignment▼12k1.67
[PDF]OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences▼4.3k2.00
[PDF]Mary Had a Little [What?]: Decoding Can Matter More Than the Model Itself in Zero-Shot Detection▼5.8k2.33
[PDF]Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence▼4.3k2.00
[PDF]Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents▼4.3k2.00
[PDF]Small Critics Make Strong Models Count: Learning to Verify Stronger Models for Efficient AutoResearch▼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Withdrawn or desk rejected (936)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