model efficiency

Beyond Next Token Prediction: Patch-Level Training for Large Language Models ICLR 2025 Bringing RNNs Back to Efficient Open-Ended Video Understanding ICCV 2025 CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction CVPR 2025 Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency NAACL 2025 Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient CVPR 2025 Consultant Decoding: Yet Another Synergistic Mechanism ACL 2025 CopySpec: Accelerating LLMs with Speculative Copy-and-Paste EMNLP 2025 DAViD: Data-efficient and Accurate Vision Models from Synthetic Data ICCV 2025 Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework CVPR 2025 ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025 Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers EMNLP 2025 Efficient Visual Representation Learning with Heat Conduction Equation IJCAI 2025 EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba AAAI 2025 Enhancing AI-Driven Farming Advisory in Kenya with Efficient RAG Agents via Quantized Fine-Tuned Language Models ACL 2025 Enhancing Large Language Model Performance with Gradient-Based Parameter Selection AAAI 2025 EVEv2: Improved Baselines for Encoder-Free Vision-Language Models ICCV 2025 FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual Compression CVPR 2025 Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups EMNLP 2025 ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025 Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations EMNLP 2025 LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models ICCV 2025 Learning Sparsity for Effective and Efficient Music Performance Question Answering ACL 2025 Low-Bit Quantization Favors Undertrained LLMs ACL 2025 LSNet: See Large, Focus Small CVPR 2025