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
64 results for “keyword:"mixed precision"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DynamicKV: Predictive and Reversible KV-Cache Precision Allocation for Agentic LLM Inference▲2.0k4.00
[PDF]MxQBound: Efficient Mixed-Precision Quantization for MoE-LLMs Guided by Expert Importance and Error Bound Guarantees▲6.1k2.00
[PDF]Bridging Shannon Surprisal and Latent Geometry: A Unified Framework for VLM Storage, Attention Routing, and Data Pruning▼1.2k1.67
[PDF]CostBit: Candidate-Cost-Informed Bit Allocation for Post-Training Quantization of LLMs▼5.8k2.33
[PDF]ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference▲5.4k3.00
Withdrawn or desk rejected (11)
[PDF]Beyond Fixed Precision: Measuring and Tracking Minimum Sufficient Precision in LearningWithdrawn2.00
[PDF]SAGE-VQ: Structure-Adaptive Gating-Aware Expert Vector Quantization with Output Correction for MoE LLMsWithdrawn1.67
[PDF]MARK-VLA: Mixed-Precision Action-Risk-Guided Quantization with Mixed-Weight Kernels for Vision-Language-Action ModelsWithdrawn1.67
[PDF]Adaptive Precision Allocation Can Starve Itself: Consequence-Aware Allocation for Bounded World ModelsWithdrawn2.33
[PDF]HAMoE: Heterogeneity-Aware Mixed-Precision Quantization for Mixture-of-Experts ModelsWithdrawn1.75