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
547 results for “keyword:"quantization"” in ICLR 2027. 100 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Analysis of MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible error▲4002.67
[PDF]LSMXQ: Layerwise Salience-Aware Mixed-Precision Quantization for Efficient LLM Inference▼1351.33
[PDF]One Token Owns the Calibration Hessian: Why Layer-wise Quantization Can Silently Break Instruction Following▼1.2k3.00
[PDF]Unmasking the Hidden Bias, Fairness, and Safety Costs of Compression with Mixture-of-Expert Models▼1.2k3.00
[PDF]From Hidden States to Probability Measures: Measuring Quantization-Induced Deformation in Large Language Models▼1351.33
[PDF]MonoVoc: Efficient Object-Centric Open-Vocabulary 3D Gaussian Mapping from Monocular Video▼4.3k2.00
[PDF]Interventional Commutativity: Effect Preservation and Reference Selection Under Weight-Only Quantisation▼1.2k1.67
[PDF]KLIQ: KL-Informed Low-Bit Quantization via Attention-Distribution-Aware Fisher-Kronecker Curvature▼4.3k2.00
[PDF]QAttrib-MoE: Runtime-Controlled Attribution of Cross-Precision Trajectory Divergence in Mixture-of-Experts Inference▼5.3k1.33
[PDF]ResQAdam: Residual-Preserving Adaptive Optimization for Memory-Efficient Quantization Aware Training▼4.5k2.67
[PDF]QuMix: Query-Guided Mixed-Precision KV-Cache Quantization for Block Diffusion Language Models▲3.0k2.33
[PDF]SP-QAT: Spectral-Preserving Quantization-Aware Training for Extreme Low-Bit Vision-Language-Action Models▲4002.67
[PDF]THE LOW-BIT MEMORY LAW: PRECISION BUYS PROPAGATION, DIMENSION BUYS RETRIEVAL, AND GATING MUST BE STABLE▼1351.33
[PDF]CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering▼5.8k2.33
[PDF]Budgets Transfer, Hardness Labels Do Not: Auditing What Survives Quantization of Reasoning Models▼1.2k1.67
[PDF]DyQ-VLA: Dynamic Quantization and Compensation for VLA models with Runtime Error Awareness▼1.2k3.00
[PDF]BitLadder: Bit-Level Selective Loading of the KV Cache for Efficient Long-Context LLM Inference▼4.3k2.00
Withdrawn or desk rejected (100)
[PDF]DQ-PAD: Discriminative Quantized Prototype Alignment for Adversarial Patch DefenseWithdrawn1.67
[PDF]Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented TuningWithdrawn2.00
[PDF]QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual SidesDesk rejected
[PDF]TASK-SENSITIVE LOW-RANK QUANTIZATION ERROR RECONSTRUCTION WITH PROPAGATION-AWARE COORDINATIONDesk rejected