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2,183 results for “keyword:"inference"” in ICLR 2027. 455 withdrawn or desk rejected listed apart.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]Built to Read, Not to Recall: Language Skills over World Knowledge in Small Language Models▼1.2k1.67
[PDF]Inference-Time Search in Discrete Diffusion Language Models, Guided by Internal-State Signals▼1.2k1.67
[PDF]LAB-Sparse: Local Accumulative Boost for Adaptive Semantic-Block Retention in KV Cache▼4.3k2.00
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲422.75
[PDF]SPEAR: Privacy- and Executability-Aware Subquery Routing for Edge-Cloud Collaborative RAG▼4.3k2.00
[PDF]What Does a Predictive Gain Certify? Auditing Information Claims under Approximate Inference▼5.8k2.33
[PDF]HAIR: Fine-Strand Hidden-State Anchored Implicit Reasoning with Single-Prefill Inference▲3.0k2.40
[PDF]VeriSeek-VL: Seeking Visual Evidence and Verifying Hypotheses in Multimodal Deep Search▼4.3k2.00
[PDF]Many Caches, Same Reasoning: Rethinking Importance Selection for Reasoning-Time KV Compression▼1.2k1.67
[PDF]When Pairwise Counterfactual Bounds Are Exact: Conflict Certificates and Temporal Compression▼1.2k1.67
[PDF]HELITE-RESNET: A CKKS-FRIENDLY RESIDUAL NETWORK FOR END-TO-END ENCRYPTED FACIAL EXPRESSION RECOGNITION▼5.3k1.33
[PDF]ORBIT: EFFICIENT VERIFICATION OF EDITED LLM OUTPUTS WITH COMPACT ROUTING HINTS AND LOCAL SEMANTIC ASSESSMENT▼1.3k1.75
[PDF]The Blessing of Linear Non-Gaussian Models: Powerful Independent Subspace Inference for Latent-Variable Causal Discovery▲43.67
Withdrawn or desk rejected (455)
[PDF]RetinaPack: Few-Shot Continual Retinal Pre-Screening with Offline Neuromorphic InferenceWithdrawn2.00
[PDF]Reroute, Don’t Remove: Recoverable Visual Token Routing for Vision-Language ModelsWithdrawn2.00
[PDF]CSD: Confidence- and Stability-Guided Speculative Decoding in Large Language ModelsWithdrawn1.33
[PDF]Coverage Is Uniquely Cacheable: Cache-Once Coverage Compression for Multi-Turn Vision-Language ModelsWithdrawn1.67
[PDF]SHIM: Scaling Homomorphic Generative Transformer Inference via Multi-Party CollaborationWithdrawn1.00
[PDF]Janus: Breaking Layer-Bound KV-Cache Layouts to Accelerate Local Agent InferenceDesk rejected2.75