Model Compression

Beyond Real Weights: Hypercomplex Representations for Stable Quantization WACV 2026 DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation AAAI 2026 Efficient Text-Guided Convolutional Adapter for the Diffusion Model WACV 2026 Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization ACL 2026 FIRM-MoE:Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference AAAI 2026 GFT: Graph Feature Tuning for Efficient Point Cloud Analysis WACV 2026 HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference ACL 2026 Motivating Next-Gen Accelerators with Flexible N:M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches ACL 2026 One-Cycle Structured Pruning via Stability-Driven Subnetwork Search WACV 2026 OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMs AAAI 2026 Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation AAAI 2026 Single-step Diffusion for Image Compression at Ultra-Low Bitrates WACV 2026 Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport CVPR 2026 TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression WACV 2026 Theoretical Compression Bounds for Wide Multilayer Perceptrons COLT 2026 3D-GSW: 3D Gaussian Splatting for Robust Watermarking CVPR 2025 500xCompressor: Generalized Prompt Compression for Large Language Models ACL 2025 AAIG at GenAI Detection Task 1: Exploring Syntactically-Aware, Resource-Efficient Small Autoregressive Decoders for AI Content Detection COLING 2025 ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models AAAI 2025 Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning ICCV 2025 Accelerating Cross-Encoders in Biomedical Entity Linking ACL 2025 Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025 ACECODER: Acing Coder RL via Automated Test-Case Synthesis ACL 2025 Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning ICCV 2025 Active Data Curation Effectively Distills Large-Scale Multimodal Models CVPR 2025