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207 results for “keyword:"model compression"” in ICLR 2027. 46 withdrawn or desk rejected listed apart.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]Spend Bits Where the Renderer Looks: Observability-Guided Rate–Distortion Optimization for Dynamic Gaussian Splatting Compression▲3972.67
[PDF]SparRotQuant: Patterned Sparsity-Aware Rotation-Based Quantization for LLM Compression▼5.9k2.60
[PDF]TRIM: Temporal-subspace Reconstruction Induced by Moments for Post-Training Structured Pruning of Spiking Neural Networks▲5.4k3.00
[PDF]AdaptQuant: Hardware-Aligned Per-Tile MX Format Selection for Post-Training Quantization on NVIDIA Blackwell▲4.6k3.00
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]MBVQ: Multi-Level Block-Wise Vector Quantization for Hardware Friendly Post-Training Quantization of LLMs▼1361.33
[PDF]Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers▲5.4k3.00
[PDF]FoldUMM: Unlocking Efficient Inference in Unified Multimodal Models via Task-Specific Layer Folding▼1.2k3.00
[PDF]Compression-Induced Representational Dissonance: Anticipating and Suppressing Prediction Flips▼4.3k2.00
[PDF]When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization▼5.8k2.33
[PDF]ParetoGS: High-Quality Continuous-Budget 3D Gaussian Splatting with Sparse Adapted Anchors▼4.3k2.00
[PDF]Colinearity Decay: Training Quantization-Friendly Transformers via Decoupled Weight-Space Regularization▼5.8k2.33
[PDF]Hard to Remove, Cheap to Replace: Compact, Transferable Surrogates for Sensitive LLM Layers▲6.1k2.00
Withdrawn or desk rejected (46)
[PDF]When Does the Calibration Source Matter for Low-Bit GPTQ Quantization of LLMs? A Seed-Paired StudyWithdrawn1.33