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
245 results for “keyword:"acceleration"” in ICLR 2027. 54 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KalmanCache+: Uncertainty-Aware Closed-Loop Diffusion Caching via Predict–Trust–Correct Residual Estimation▲8.9k2.75
[PDF]CRAFT: Coupled Rotation-Aware Action-Field Caching and Two-Bit Quantization for Vision-Language-Action Models▲9.2k2.67
[PDF]UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation▼4.5k2.67
[PDF]When Exact Loops Beat Shortcuts: Deep-Target Approximation Is Not Recurrent-Depth Acceleration▲6.1k2.00
[PDF]MAX-Cache: Motion-Aligned Activation Reuse with Mismatch-Guided Selective Recomputation for Efficient Autoregressive Video Diffusion▲3972.67
[PDF]ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement▼4.5k2.25
[PDF]BATON: Passing Denoising Trajectories Across Replans for Parallel Sampling of Robot Policies▼4.3k2.00
[PDF]Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding▲153.33
[PDF]CAVC: Convergence-Adaptive Audio-Visual Cache for Modality-Asymmetric Diffusion Generation▼4.3k2.00
[PDF]SparRotQuant: Patterned Sparsity-Aware Rotation-Based Quantization for LLM Compression▼5.9k2.60
[PDF]Beyond the History Span: State-Guided Span Expansion for Efficient Diffusion Inference▼5.8k2.33
[PDF]Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection▼13k2.00
[PDF]TaylorGAP: Progressive Anchor Scheduling and Geometry-Aware Taylor Forecasting for Training-Free Diffusion Acceleration▼1361.33
[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]AdaptQuant: Hardware-Aligned Per-Tile MX Format Selection for Post-Training Quantization on NVIDIA Blackwell▲4.6k3.00
[PDF]EvoComp-2: Learning to Compress Audio-Video Tokens for Omnimodal Large Language Models via Topic-Guided Evolutionary Labeling▼4.3k2.00
[PDF]QuadVGGT: Quotient Attention for Accelerating Dense-Token Inference in Visual Geometry Grounded Transformers▲5103.00
Withdrawn or desk rejected (54)
[PDF]ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution ShapingWithdrawn1.67
[PDF]VeloCache: Frequency-Decoupled Velocity Caching for Training-Free Video Diffusion AccelerationWithdrawn2.00
[PDF]Speed on Demand: Faster-than-Demonstration Imitation via a Neural Robot Dynamics ModelWithdrawn1.67
[PDF]Learning When to Commit: Token Scores, Stopping Rules, and Stability in Diffusion Language ModelsWithdrawn1.67
[PDF]RAJNI: Importance-Aware, Dispersion-Scheduled Training-Free Token Pruning for Vision TransformersWithdrawn1.67