Efficient Computing

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models ACL 2026 BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook ACL 2026 Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference ACL 2026 CaT-GS: Efficient 3DGS Rendering for Large-Scale Scenes with Inter-frame Caching and Tile Scheduling CVPR 2026 Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths ACL 2026 Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models CVPR 2026 Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring ACL 2026 Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing CVPR 2026 Content-Aware Dynamic Patchification for Efficient Video Diffusion CVPR 2026 Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning ACL 2026 D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration CVPR 2026 DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers CVPR 2026 Decoding Text Spans for Efficient and Accurate Named-Entity Recognition ACL 2026 Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache CVPR 2026 Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation CVPR 2026 DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching CVPR 2026 Don’t Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models ACL 2026 Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism ACL 2026 DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation ACL 2026 DTC-WSI: Dynamic Token Compression for Whole-Slide Images MIDL 2026 EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving ACL 2026 EdgeFormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks ACL 2026 Edge-RecViT: Efficient Vision Transformer via Semantic-Refined Dynamic Recursion CVPR 2026 Efficiency Follows Global-Local Decoupling CVPR 2026 Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation CVPR 2026