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416 results for “keyword:"efficient inference"” in ICLR 2027. 79 withdrawn or desk rejected listed apart.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]Shallow Pool, Deep Prune: Accelerating Vision-Language Models via Hybrid Token Reduction▼4.3k2.00
[PDF]HorizonKV: Three-State KV Cache Compression under a Shrinking Generation Horizon for Visual Autoregressive Models▲3972.67
[PDF]Density-Matched Power-of-Two Quantization: Allocating Logarithmic Levels for Multiplier-Free LLM Inference▼1.2k1.67
[PDF]ZipSign: Training-Free Spatio-Temporal Token Compression for Sign Language Translation▼5.8k2.33
[PDF]CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches▲5103.00
[PDF]RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache▼1.2k3.00
[PDF]Not All History Matters: Query-Conditioned Evidence Retrieval for Time Series Forecasting▼4.5k2.25
[PDF]TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval▼4.3k2.00
[PDF]Same Score, Different State: Post-Training Moves Pre-Answer Recoverability under KV Compression▼4.3k2.00
[PDF]Prox: Training-Free FFN Activation Sparsification in LLMs via Approximate Intermediate-State Salience▲3972.67
[PDF]CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search▼4.5k2.67
[PDF]Many Steps, One Pass: Latent Trajectory Simulation for Efficient LiDAR Scene Completion▲3.0k2.33
[PDF]MagicCore-LM: Compact Algebraic Interfaces for Learning Near-Clifford Quantum Circuits▼1.2k1.67
[PDF]Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models▼4.3k2.00
Withdrawn or desk rejected (79)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