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
158 results for “keyword:"precision"” in ICLR 2027. 30 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]FROM ATTENTION SENSITIVITY TO LAYER ROLE: REVISITING MIXED-PRECISION QUANTIZATION OF TRANSFORMERS▼1.2k1.67
[PDF]Beyond Accuracy: Prefix-Invariant Realizations of Low-Precision Fast Matrix Multiplication▲8072.80
[PDF]Where Compression Hurts: Function-Space Sensitivity for Mixed-Precision Neural Network Quantization▼4.3k2.00
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
[PDF]Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?▲11k2.00
[PDF]The Evaluator Is a Random Variable: Auditing the Fixed Feature Space Behind Text-to-Motion Benchmarks▼4.3k2.00
[PDF]Post-Calibration Topology Drift Reveals Operator-Dependent Numerical Sensitivity in Quantized Graph Neural Networks▲11.00
[PDF]IncMoE: Active-Path Precision Increment for Calibration-Free Mixture-of-Expert Quantization▼4.3k2.00
[PDF]Precision Inverse Folding: From Low-Order Mutant Measurements to Higher-Order Variant Prioritization▼1.3k1.75
[PDF]QGATE: Counterexample-Guided Precision Patching of Quantized LLMs with Fail-Closed Slice Reporting▲11.00
[PDF]PerturbRx: Learning Treatment-Conditioned Latent Transitions from Single-Cell Perturbations for Patient Drug Response▲3.0k2.33
[PDF]Analysis of MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible error▲3972.67
[PDF]LSMXQ: Layerwise Salience-Aware Mixed-Precision Quantization for Efficient LLM Inference▼1361.33
[PDF]Broken Symmetry in BF16 Attention: Why FlashAttention Gradients Blow Up Late in Training▲153.33
[PDF]Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy▼1.2k1.67
[PDF]The Arithmetic Error Bar: A First-Passage Law for the Numerical Fragility of Language Models▼1361.33
Withdrawn or desk rejected (30)
[PDF]Sharp Root-Exponential Rates for Smooth Convex Optimization in a Serial Finite-Bit ModelDesk rejected2.33
[PDF]HAMoE: Heterogeneity-Aware Mixed-Precision Quantization for Mixture-of-Experts ModelsWithdrawn1.75
[PDF]EdgeEdit: An Edge-Oriented Multimodal Knowledge Editing Framework for On-Device MLLMsWithdrawn1.67
[PDF]Stable Directions, Different Effects: Intervention Fidelity Across Model PrecisionDesk rejected
[PDF]Lossless, Yet Not Identical: Execution-Level Numerical Bifurcations in Speculative DecodingWithdrawn1.33
[PDF]DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision AttentionWithdrawn1.67