conftrace_

efficient inference

233 papers

Explore in graph

Also known as

EI

Co-occurring keywords

model compression (3302) efficient computing (781) large language model (13587) knowledge distillation (3725) vision transformer (1106) model quantization (281) convolutional neural network (4226) inference optimization (219) inference efficiency (248) inference acceleration (244)

Papers

Rethinking Large Language Model Architectures for Sequential Recommendations IJCNLP 2025
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers CVPR 2025
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025
MobileMamba: Lightweight Multi-Receptive Visual Mamba Network CVPR 2025
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory EMNLP 2025
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference IJCNLP 2025
Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025
ReMamba: Equip Mamba with Effective Long-Sequence Modeling EMNLP 2025
Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation EMNLP 2025
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025
Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention ACL 2025
Harnessing Input-Adaptive Inference for Efficient VLN ICCV 2025
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing WACV 2025
Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025
Q-Mamba: Towards more efficient Mamba models via post-training quantization ACL 2025
LightThinker: Thinking Step-by-Step Compression EMNLP 2025
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables CVPR 2025
QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge CVPR 2025
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient CVPR 2025
Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales CVPR 2025
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping ICCV 2025
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025