inference optimization

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression EMNLP 2025 Not All Layers of LLMs Are Necessary During Inference IJCAI 2025 OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs ICLR 2025 PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint IJCNLP 2025 PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding ACL 2025 PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity ICCV 2025 Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation ACL 2025 Preble: Efficient Distributed Prompt Scheduling for LLM Serving ICLR 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 RefreshKV: Updating Small KV Cache During Long-form Generation ACL 2025 Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? ACL 2025 RTTC: Reward-Guided Collaborative Test-Time Compute EMNLP 2025 SCBench: A KV Cache-Centric Analysis of Long-Context Methods ICLR 2025 SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding COLING 2025 SiLQ: Simple Large Language Model Quantization-Aware Training IJCNLP 2025 SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation ACL 2025 Speculative Sampling via Exponential Races ACL 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025 Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025 SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation EMNLP 2025 TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering ACL 2025 TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization ACL 2025 TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025 The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws ICLR 2025