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416 results for “keyword:"efficient inference"” in ICLR 2027. 79 withdrawn or desk rejected listed apart.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]Decouple to Decode: Parallel Decoding with Deferred Proposal Verification for Diffusion Language Models▼4.3k2.00
[PDF]The Price of a Merge Is Paid in Depth: A Tight, Label-Free Bound on Token Merging in Vision Transformers▼3.7k2.25
[PDF]STFSFormer: Integrating Neuronal Dynamics and Full-Spike Attention for Energy-Efficient EEG Modeling▼4.3k2.00
[PDF]Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models▼1.2k1.67
[PDF]SGPrune: Subspace-Guided Token Pruning for Multi-View Vision-Language Models in Autonomous Driving▲452.75
[PDF]MemCache: Memory-Augmented Adaptive Token Caching for Efficient Vision-Language-Action Inference▲5.4k3.00
[PDF]Prototype-driven Hierarchical Rule Induction and Matching for Efficient Video Anomaly Detection▼1361.33
[PDF]Coverage-Preserving Recasting and Hierarchical Visual Token Pruning for Efficient Multimodel LLMs▼4.3k2.00
[PDF]Pairwise-Safe, Jointly-Unsafe: Higher-Order Residual Risk in Parallel Decoding of Diffusion Language Models▼1361.33
[PDF]Never Evict Always Taper: A Static Logarithmic Bit-Width Schedule for KV Cache Quantization▲11.00
[PDF]BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding▼1.2k3.00
[PDF]EchoSpec: Efficient Target-Integrated Speculative Decoding via Output-Projection Adaptation and Post-Target Refinement▼5.8k2.33
[PDF]Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding▼4.5k2.67
[PDF]LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents▼5.8k2.33
[PDF]Dynamic Audio-Visual Correlation-Aware Token Compression for Omnimodal Large Language Models▼5.8k2.33
[PDF]Attend at the Right Resolution: Head-Adaptive Sparse Attention via Query–Key Interaction Structure▲3.0k2.33
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]ACT-SNN: Activity-Constrained Two-Stage Conversion for Efficient Spiking Large Language Models▲3972.67
Withdrawn or desk rejected (79)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