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
2,183 results for “keyword:"inference"” in ICLR 2027. 455 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Watt Does a Benchmark Point Cost? Measuring the Energy Efficiency of LLM Capability under Production Serving▲3.0k2.33
[PDF]Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference▼4.5k2.67
[PDF]CertifyPAR: Adequacy Certification and Coefficient Inference for Piecewise Affine Regression▼1.2k1.67
[PDF]PRICE: Propagation-Risk-Informed Dynamic Diffusion Caching under Exact Compute Budgets▼5.8k2.33
[PDF]When Mismatch Misleads: Stabilizing Low-Precision Reinforcement Learning via Reliable Correction▼4.5k2.67
[PDF]Beyond the Best Available Cause: Calibrated Verification and Triage under Hypothesis-Space Inadequacy▲3.0k2.33
[PDF]ESFM: Reconstructing Unbalanced Dynamics via Reduction and Extended-Space Flow Matching▼1.2k1.67
[PDF]Calibrated Inference for the Conditional Average Treatment Effect in the Few-Placebo Regime via Gaussian Processes▼1.2k1.67
[PDF]A Wrong Turn in Addition: Generation, Routing, and Correction of Arithmetic Errors in LLMs▲5103.00
[PDF]Speculating on the Past: Lossless Reuse of Stale KV Caches via Self-Speculative Verification▼4.3k2.00
[PDF]Termination Calibration Recovers Answers That Reasoning Models Compute but Never Express▼4.5k2.67
[PDF]GEOEPS: TRAINING-FREE EVIDENCE PRESENTATION AND SELECTION FOR ULTRA-HIGH-RESOLUTION REMOTE SENSING UNDERSTANDING▼4.5k2.67
[PDF]StrideKV: Accelerating Batched Long-Context Decoding via Periodic Reuse of Retrieved KV Cache▲6.1k2.00
Withdrawn or desk rejected (455)
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67
[PDF]TYPED AMPLITUDE COMPOSITION FOR REUSABLE INFERENCE: SEMANTICS, ERROR BOUNDS, AND EXACT CORRECTIONWithdrawn
[PDF]Graphs are Evidence, Not CircuitsDesk rejected