inference efficiency

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models ACL 2026 CacheNotes: Task-Aware Key-Value Cache Compression for Reasoning-Intensive Knowledge Tasks EACL 2026 CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models ACL 2026 CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning AAAI 2026 CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models CVPR 2026 Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models WACV 2026 DualRes: Production-ready Dynamic Object Detection WACV 2026 Efficient Model Specialization via Training-time and Test-time Adaptation AAAI 2026 EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling CVPR 2026 FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training AAAI 2026 HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding ACL 2026 HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract) AAAI 2026 LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention AAAI 2026 NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers CVPR 2026 OctoT2I: A Self-Evolving Agentic Text-to-Image Router CVPR 2026 PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference EACL 2026 PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference CVPR 2026 Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment AAAI 2026 SABER: Switchable and Balanced Training for Efficient LLM Reasoning AAAI 2026 SEAP: Sparse Expert Activation Pruning Unlocks the Brainpower of Large Language Models AAAI 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model AAAI 2026 TIV: Thought Injection via Vectors for Efficient Reasoning in Large Reasoning Models AAAI 2026 TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstruction CVPR 2026 TokenPowerBench: Benchmarking the Power Consumption of LLM Inference AAAI 2026