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
416 results for “keyword:"efficient inference"” in ICLR 2027. 79 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ReVisKV: Converting Dynamic Visual Execution Sparsity into Reversible GPU KV Residency▼4.3k2.00
[PDF]RSI-Router: Cost-Efficient LLM Routing via Evolution of Subtask-Level Model Assignments with Execution Skills▼5.8k2.33
[PDF]Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion▲5103.00
[PDF]WORD-CTR: Write Once, Read Deep for Efficient Long-Sequence Click-Through Rate Prediction▼4.3k2.00
[PDF]RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation▼11k2.33
[PDF]HeteroQuant: Resolving Expert Heterogeneity in MoE Quantization via Targeted Calibration▼1.2k1.67
[PDF]RouteCache: Efficient Long-Context Attention via Learnable Retrieval and Temporal Caching▲3972.67
[PDF]KV Cache Compression as State Substitution: When Does KV Compression Yield a Reliable Replacement for the Full Cache?▼4.3k2.00
[PDF]Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining▼5.8k2.33
[PDF]SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud Streams▲5.4k3.00
[PDF]VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge▼4.3k2.00
[PDF]Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning▼4.3k2.00
[PDF]Visual Tokens Should Not Be Pruned Forever: Budgeted Visual Token Refresh for Multi-Turn LVLMs▼1361.33
[PDF]Less Fusion, Same Action: Revisiting Redundant Connectivity in Mixture-of-Transformer based Robot Policy Models▲5103.00
[PDF]HorizonKV: Future-Aware KVCache Reuse via Lightweight Relevance Estimation for Interleaved Agent Contexts▼1.2k1.67
Withdrawn or desk rejected (79)
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00
[PDF]VOLT: Joint Token Selection and Frame Budget Allocation via Subspace Volume MaximizationDesk rejected2.00
[PDF]ReCo:Training-Free Visual Token Pruning via Relational Transition Coreset in Large Vision-Language ModelsWithdrawn2.00
[PDF]DepthPruner: Visual Token Pruning with Pluggable Depth Guidance for Efficient Vision-Language-Action InferenceWithdrawn2.00