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
4,857 results for “keyword:"lm"” in ICLR 2027. 944 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions▲3862.67
[PDF]E-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning▼5.9k2.33
[PDF]Counterfactual Credit Assignment over Execution Graphs of LLM-based Multi-agent Systems▼4.3k2.00
[PDF]Affective Representations of Large Language Models Differ Between AI-Centric and Human-Centric Scenarios▼5.9k2.60
[PDF]Same Verdict, Different Check Values: What Field Order Changes in a Structured LLM Judge▼1.2k1.67
[PDF]HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment▼1361.33
[PDF]Prompt Lottery in LLM-As-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing▼5.9k2.33
[PDF]ACE-Guard: Automated Co-Evolutionary Guardrails for LLM Security via Inference-Time Natural Language Gradients▼1361.33
[PDF]TAPD-SR: Bridging the Detail-Conditioning Gap for Diffusion-Based Faithful Real-World Image Super-Resolution▼4.3k2.00
[PDF]From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks▼1.2k1.67
[PDF]LEAP: LLM-Empowered Adaptive Portfolio Discovery for Instance-Aware MILP Configuration▼1.2k3.00
[PDF]Geometry-Aware Multi-Objective Optimization: Norm-Constrained Oracles with Entropic Weight Updates▲5093.00
[PDF]Two Asymmetries of LLM Self-Review: Family-Dependent Recall Gaps and Same-Model False-Positive Bias▲11.00
[PDF]HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers▲14k3.00
[PDF]Not All Experiences Are Equal: Counterfactual Experience Valuation for Multi-Turn Agent RL▼1.2k1.67
[PDF]IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computing▲3862.67
Withdrawn or desk rejected (944)
[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