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416 results for “keyword:"efficient inference"” in ICLR 2027. 79 withdrawn or desk rejected listed apart.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]Built to Read, Not to Recall: Language Skills over World Knowledge in Small Language Models▼1.2k1.67
[PDF]LAB-Sparse: Local Accumulative Boost for Adaptive Semantic-Block Retention in KV Cache▼4.3k2.00
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲502.75
[PDF]ORBIT: EFFICIENT VERIFICATION OF EDITED LLM OUTPUTS WITH COMPACT ROUTING HINTS AND LOCAL SEMANTIC ASSESSMENT▼1.3k1.75
[PDF]Lifetime: KV Cache Eviction from Attention Trajectories for Long-Context Language Models▼4.3k2.00
[PDF]Beyond Berry–Esseen: Loss-Aware Distortion Transfer for Randomized Hadamard Quantization▼1.2k1.67
[PDF]What Survives Token Merging? Merge-Invariant Low-Rank Attention for Vision Transformers▼4.3k2.00
[PDF]One Step Is Often Enough: Accelerating VLA Action Heads with Training-Free Marginal-Aligned Warm Starts▲4012.67
[PDF]ConGRets: Low-Resource, Low-Latency Co-Speech Gesture Synthesis via Contrastive Latent Prediction▼1351.33
[PDF]OmniCens: Self-Improving Distillation for Multimodal Classification of Millions of Profiles▲11.00
[PDF]Chain2Parallel: Post-Hoc Parallelization of T5 Classifier Chains for Few-Shot Multi-Label Classification▼5.8k2.33
[PDF]Listen First, Look as Needed: Uncertainty-Aware Asymmetric Routing for Audio-Visual Recognition▼1351.33
[PDF]Pinning Visual Paths:Preserving Visual Structure for Ultra-Low-Bit Vision Encoders with Task-Informed Reconstruction▼4.3k2.00
[PDF]DART-VLA: Dynamic Action-Relevance Token Pruning for Efficient Vision-Language-Action Models▲3.0k2.33
[PDF]ARCS: APPROXIMATION-RISK-AWARE COMPUTATION SCHEDULING FOR FEATURE FORECASTING IN DIFFUSION TRANSFORMERS▲4012.67
[PDF]IncMoE: Active-Path Precision Increment for Calibration-Free Mixture-of-Expert Quantization▼4.3k2.00
[PDF]GB-LSR: Local Spectral Decoding with a Learned Global Bandwidth for Arbitrary-Scale Super-Resolution▼4.3k2.00
[PDF]LLM-SemanticLAN: Anchored Public Latent Communication via KV Caches across Heterogeneous Large Language Models▲3.0k2.33
Withdrawn or desk rejected (79)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