Model Compression

TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning AAAI 2025 TinySAM: Pushing the Envelope for Efficient Segment Anything Model AAAI 2025 Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025 TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration WACV 2025 Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment AAAI 2025 Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism AAAI 2025 Towards compact and efficient Slovak summarization models ACL 2025 Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMs ACL 2025 Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product ICCV 2025 Towards Lossless Implicit Neural Representation via Bit Plane Decomposition CVPR 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 Training-free LLM Merging for Multi-task Learning ACL 2025 Training LLMs with MXFP4 AISTATS 2025 Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models EMNLP 2025 Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models ICCV 2025 Treasures in Discarded Weights for LLM Quantization AAAI 2025 TreeKV: Smooth Key-Value Cache Compression with Tree Structures IJCAI 2025 TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs ACL 2025 TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025 TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning ICCV 2025 TTE: Two Tokens Are Enough to Improve Parameter-Efficient Tuning AAAI 2025 TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models ACL 2025 UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models AAAI 2025 Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models ACL 2025 UNLEARN Efficient Removal of Knowledge in Large Language Models NAACL 2025