inference efficiency

Parallel Continuous Chain-of-Thought with Jacobi Iteration EMNLP 2025 Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025 PrAd: Prompt Adaptive Tuning for Decoder-only Language Models EMNLP 2025 Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025 Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing ICLR 2025 Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025 Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models ICCV 2025 Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models AAAI 2025 Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling EMNLP 2025 Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game CVPR 2025 Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks CVPR 2025 RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation ACL 2025 RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations IJCAI 2025 Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models EMNLP 2025 SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations ICLR 2025 Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025 SDBench: A Comprehensive Benchmark Suite for Speaker Diarization Interspeech 2025 Selective Attention Improves Transformer ICLR 2025 SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching IJCNLP 2025 ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers ICCV 2025 SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling EMNLP 2025 Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency EMNLP 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding ICML 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025