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
207 results for “keyword:"model compression"” in ICLR 2027. 46 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LRSR: Hardware-Friendly Approximation of Per-Element Quantization via Low-Rank Scale Reconstruction▲3.9k1.67
[PDF]HeteroQuant: Resolving Expert Heterogeneity in MoE Quantization via Targeted Calibration▼1.2k1.67
[PDF]Representation Matters in 2-Bit QAT: Finite Barnes–Wall Representations for Large Language Models▼5.9k2.50
[PDF]RCDQ: Reference-Guided LLM Quantization with Interleaved Continuous Compensation and Discrete Decisions▼4.3k2.00
[PDF]Teachers Are Not Equal: Task-Flow Conditional Cross-Layer Knowledge Distillation for Efficient Flow-Based VLA Models▲14k3.00
[PDF]ARCH-CPTQ: Replay-Free Continual Post-Training Quantization with Curvature History and Anchoring▲3.8k2.50
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]PGOT: Physically Grounded Optimal Transport for Distilling Vision-Language-Action Models▼5.8k2.33
[PDF]The Compression Square: Weight Quantization and KV-Cache Eviction Do Not Compose at the Operating Point▲153.33
[PDF]SCOPE-Q: ONE-CHECKPOINT QUANTIZATION-AWARE TRAINING FOR CROSS-FRAMEWORK LLM DEPLOYMENT▼4.3k2.00
[PDF]When Weight Fidelity Misleads: Concept-Erasure Safety Edits Under Diffusion-Model Quantization▼1.2k1.67
[PDF]COARSE-GRAINING RECURSIVE COMPUTATION: CONTINUATION-RELATIVE INTERFACES AND FAILURE MODES▼1361.33
[PDF]Compress Locally, Predict Globally: Composable Margin Statistics for Estimating Compressed LLM Accuracy▼1.2k3.00
[PDF]Does Quantization Preserve How Language Models Answer? Causal-Equivariant Quantization for Symbol-Binding Circuits▼4.5k2.25
[PDF]Layer Pruning as a Non-Cooperative Game: Conditional Exchanges for Large Language Models▼1.2k1.67
[PDF]Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models▼12k1.67
[PDF]It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs▼1.3k1.75
[PDF]What Survives Extreme Compression? Vision-Language Embedding Alignment at Microcontroller Scale▼1.2k1.67
[PDF]Configuration-Valued Expert Importance for Mixed-Precision Quantization of Multimodal Mixture-of-Experts▼5.9k2.50
[PDF]ESPTQ: Post-Training Ternarization of Weights and KV Cache for Eliminating Per-Element Multiplications▼4.3k2.00
[PDF]GapSQ: Closing the Pruning-Induced Gap for Joint Sparsification and Quantization of LLMs▼5.8k2.33
Withdrawn or desk rejected (46)
[PDF]When Does the Calibration Source Matter for Low-Bit GPTQ Quantization of LLMs? A Seed-Paired StudyWithdrawn1.33