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2,183 results for “keyword:"inference"” in ICLR 2027. 455 withdrawn or desk rejected listed apart.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]Beyond Token Pruning: Prompt Compression via Minimum Description Length and Semantic Message Anchors▼1.3k1.75
[PDF]Cache Homeostasis: Diagnosing and Controlling Feature Drift in Autoregressive Video Diffusion▼4.3k2.00
[PDF]PluralGen: Efficient Test-Time Scaling by Decoupling Particle Search from Model Execution▼1.2k3.00
[PDF]REPRISE: Efficient Long-Context Diffusion Inference via Distillation through Reused KV Caches▲5.4k3.00
[PDF]CandiKV: Preserving Candidate KV State Across Selection and Continuation in LLM Workflows▲3942.67
[PDF]Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers▲5.4k3.00
[PDF]Fund Regions, Not Tokens: Query-Conditioned Budget Allocation for Extreme KV-Cache Eviction in Vision-Language Models▲5103.00
[PDF]AVSG: Accelerated Vectorized Sparse Gather for Efficient KV Cache Offload in Sparse-Attention LLM Serving▲9.2k2.67
[PDF]Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection▼1.2k1.67
[PDF]READ: Query-Relevant Evidence Retrieval for Visual Token Compression in Edge–Cloud VLM Inference▲5103.00
[PDF]Prune Less, Pay More: Imperceptible Budget Inflation Attacks on Token Pruning in Vision-Language Models▼1.2k1.67
[PDF]FoldUMM: Unlocking Efficient Inference in Unified Multimodal Models via Task-Specific Layer Folding▼1.2k3.00
[PDF]You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model▲5.4k3.00
[PDF]What Does Full Attention Add? State-Complementary Visual KV Compression for Hybrid Vision-Language Models▼5.8k2.33
[PDF]No Man Is an Island: Overlapping Pruning for Near-Unstructured Quality at 2:4 Efficiency▲2623.67
Withdrawn or desk rejected (455)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