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
1,450 results for “keyword:"efficient"” in ICLR 2027. 350 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Gradient Descent on Tokens Is Sparse: Understanding the Computational Structure of Differentiable Token Optimization▼4.3k2.00
[PDF]Deeper Is Not Always Wiser: Evidential GRPO for Overthinking in Large Vision-Language Models▲3942.67
[PDF]KakeyaShare: Incidence-Structured Query Sharing for Simultaneous Directional Risk Certification▼1.2k1.67
[PDF]Towards Practical FHE-Federated LLMs Training: FHE-Compatible Compression Techniques and Versatile Advanced Aggregation▲13k2.00
[PDF]Adaptive-Depth Layer Grafting: Representation-Level Transfer Across Heterogeneous Tabular Feature Spaces▲3.9k1.67
[PDF]Pay for the Reasoning Once: Compiling Agent-Written Programs for Visual Anomaly Detection▼1.2k3.00
[PDF]Mixture-of-LoRA: Modality-Specialized Low-Rank Adapters for Multimodal Language Models▼1.2k1.67
[PDF]What Does Another Loop Buy? Attention Reallocation Tracks the Marginal Value of Test-Time Compute in Looped Transformers▲3942.67
[PDF]SpecSplice: Dynamic Composition of Parametric and Retrieval-based Drafts for Agentic Speculative Decoding▼1.2k3.00
[PDF]LPA-CACHE: Latency-Plateau Aware KV Cache Reuse for Efficient Vision-Language-Action Model Inference on GPUs▼1.2k1.67
[PDF]When Visual Compression Breaks Control: Efficient Multi-View VLA Inference via Retaining Evidence for Control-Aligned Policy Recovery▼1.2k1.67
[PDF]Lightweight Explainable Physics-Informed Neural Networks by Learnable Activation Function▲6.1k2.00
[PDF]GEAR: Generative Efficient Gap Amplification for Goal-Conditioned Reinforcement Learning▲3942.67
[PDF]HEIR: When the Student Inherits the Teacher's Seat Pareto-Competitive Reference Selection for On-Policy Self-Distillation of Reasoning LLMs▼5.3k1.33
[PDF]MoSPR: Histology-to-Gene Expression Prediction with Morpho-Spatial Macrostates and Low-Rank Molecular Programs▼1.2k1.67
Withdrawn or desk rejected (350)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00