Efficient Computing

KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation ACL 2025 KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference ICML 2025 L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression AAAI 2025 L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models ACL 2025 LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models ICML 2025 LaCoOT: Layer Collapse through Optimal Transport ICCV 2025 Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping ICML 2025 LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025 LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents EMNLP 2025 LaMPlace: Learning to Optimize Cross-Stage Metrics in Macro Placement ICLR 2025 Language-Agnostic Speech Tokenizer for Spoken Term Detection with Efficient Retrieval Interspeech 2025 Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing EMNLP 2025 Language-Models-as-a-Service: Overview of a New Paradigm and its Challenges AAAI 2025 Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations EMNLP 2025 Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models EMNLP 2025 Laplace Sample Information: Data Informativeness Through a Bayesian Lens ICLR 2025 Large Convolutional Model Tuning via Filter Subspace ICLR 2025 Large Language Models as Realistic Microservice Trace Generators EMNLP 2025 Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility ICCV 2025 La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation ICML 2025 Latent Distribution Decouple for Uncertain-Aware Multimodal Multi-label Emotion Recognition ACL 2025 LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation EMNLP 2025 Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers CVPR 2025 Layer-wise Quantization for Quantized Optimistic Dual Averaging ICML 2025 Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs ICCV 2025