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
106 results for “keyword:"inference acceleration"” in ICLR 2027. 12 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CAVC: Convergence-Adaptive Audio-Visual Cache for Modality-Asymmetric Diffusion Generation▼4.3k2.00
[PDF]Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection▼13k2.00
[PDF]CSRe: Training-Free Diffusion Transformer Acceleration via Component-Wise Selective Refresh▲3972.67
[PDF]From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative Decoding▼4.3k2.00
[PDF]From Position Risks to Block Survival: Faster Generation for Diffusion Language Models▼4.5k2.67
[PDF]WHEN TO SYNCHRONIZE, HOW MUCH TO REPAIR: CACHE CONTROL FOR AUTOREGRESSIVE VIDEO DIFFUSION▲5.4k3.00
[PDF]Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration▼5.8k2.33
[PDF]EvoComp-2: Learning to Compress Audio-Video Tokens for Omnimodal Large Language Models via Topic-Guided Evolutionary Labeling▼4.3k2.00
[PDF]SpecKV: Lossless Speculative Decoding via Dynamic KV Selection for Efficient Inference of Large Vision-Language Models
[PDF]SpecSplice: Dynamic Composition of Parametric and Retrieval-based Drafts for Agentic Speculative Decoding▼1.2k3.00
[PDF]No Man Is an Island: Overlapping Pruning for Near-Unstructured Quality at 2:4 Efficiency▲2623.67
[PDF]MMoE: Multi-Level Routing Capacity Allocation for Extremely Sparse Multimodal MoE Inference▲3972.67
[PDF]RETIRE3D — WHERE RESOLUTION LIVES: LOCAL SCALE COMPLETION FOR COARSE-TO-FINE 3D GENERATION▼4.3k2.00
[PDF]TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation▲3972.67
[PDF]TORE: Token-Wise Taylor Order Selection via Decomposed Residual Error Estimation for Diffusion Acceleration▼13k2.00
[PDF]SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation▼5.8k2.33
[PDF]Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion–AR Self-Speculation Frontier▼5.8k2.33
[PDF]A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models▲3972.67
[PDF]DSpark-OPD: Acceptance-Aligned On-Policy Distillation for Semi-Autoregressive Speculative Drafting▼1.2k1.67
[PDF]The World Does Not Pause: Real-Time Benchmarks and Training-Free Acceleration for Dynamic Manipulation▼5.8k2.33
[PDF]AdaptSpec: Input- and Step-Adaptive Tree-Based Speculative Decoding to Accelerate LLM Inference▼1.2k1.67
[PDF]SparEdge: Redundancy-Aware Dynamic Sparse Inference with Edge-Cloud Collaboration for Multimodal LLMs▼4.3k2.00
Withdrawn or desk rejected (12)
[PDF]ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution ShapingWithdrawn1.67
[PDF]RAJNI: Importance-Aware, Dispersion-Scheduled Training-Free Token Pruning for Vision TransformersWithdrawn1.67
[PDF]AdaVTP: Prediction Guided Adaptive Visual Token Pruning for Efficient Diffusion MLLM InferenceWithdrawn1.67
[PDF]Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video GenerationDesk rejected
[PDF]AsymRefresh: Modality-Asymmetric Refresh for Efficient Joint Audio-Video GenerationWithdrawn1.67
[PDF]Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation ModelsDesk rejected