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
452 results for “keyword:"efficiency"” in ICLR 2027. 94 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Efficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators▲3972.67
[PDF]Autonomous Federated Learning: Incentive-Aligned, Energy-Aware, and Byzantine-Resilient Coordination▼1361.33
[PDF]Skipping Recomputation During Training: from Recurrent Models to Model Predictive Control and Beyond▼1611.50
[PDF]SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation▲5.7k2.00
[PDF]How Should VLMs Represent Ego-State? A Diagnostic Study on Representation Fidelity and Context Cost▼1.2k1.67
[PDF]Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency▲3972.67
[PDF]Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models▼4.3k2.00
[PDF]Keys Decide Attention, Values Decide Contribution: Value-Gated KV Cache Eviction at 20× Compression▼1361.33
[PDF]No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability▼4.5k2.67
[PDF]Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories▼1.2k1.67
[PDF]Efficient Multi-Agent Reinforcement Learning under Sparse Binary Team Rewards with Few Suboptimal Prior Trajectories▲3.8k2.50
[PDF]Accelerating End-to-End Cryptanalytic Extraction via Geometric Critical Point Screening▼4.3k2.00
Withdrawn or desk rejected (94)
[PDF]Matched Counterfactual Attribution: A Controlled Evaluation of Data Selection for Video Instruction TuningDesk rejected2.00
[PDF]Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction TuningDesk rejected1.67
[PDF]The Normalization Landscape in Continual Learning: Resolving Moving-Average Breakdown and Subspace Interference for Buffer-Free Edge IntelligenceWithdrawn
[PDF]Cross-Model KV Cache Construction in LLM Familiies: Residual-Stream Mapping Without Matched Head GeometryDesk rejected