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452 results for “keyword:"efficiency"” in ICLR 2027. 94 withdrawn or desk rejected listed apart.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]LoadCalib: Cognitive-Load-Calibrated Chain-of-Thought Synthesis for Small Language Models▲11.00
[PDF]Curvature as Decoder State: Exact Cache–Update Frontiers for Strongly Convex Unlearning▲13k2.33
[PDF]Beyond Pairwise Attention: Higher-Order Modular Attention for Efficient Sequence Learning▼4.3k2.00
[PDF]Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification▼1611.50
[PDF]When Richer Preferences Do Not Help: Rubric Redundancy, Pair Selection, and Training Exposure in Scientific QA▼4.3k2.00
[PDF]KVTrans: Towards Seamless Cross-Context KV Cache Reuse for Efficient Agentic Communication▼4.3k2.20
[PDF]Green Quality Distance: Characterizing Energy and Quality Trade-Off in Open Text- to-Image and Text-to-Video Models▼1361.33
[PDF]Measure, Don't Prescribe: Inferring Budget-Dependent Difficulty Preference for Dataset Pruning▲9.2k2.67
Withdrawn or desk rejected (94)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