Efficient Computing

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning ACL 2026 Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics ACL 2026 BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers CVPR 2026 Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers CVPR 2026 Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing CVPR 2026 BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs ACL 2026 Can We Predict Before Executing Machine Learning Agents? ACL 2026 CARES: Context-Aware Resolution Selector for VLMs ACL 2026 CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models ACL 2026 CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models CVPR 2026 Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG ACL 2026 Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing CVPR 2026 Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers CVPR 2026 CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling ACL 2026 Conformal LLM Routing with Distribution-Free Safety Guarantees ACL 2026 ContrastKV: Robust KV Cache Eviction via Contrastive Signal Fusion for Multi-Query Generalization ACL 2026 Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge CVPR 2026 CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels ACL 2026 Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning ACL 2026 DeDelayed: Deleting Remote Inference Delay via On-Device Correction CVPR 2026 Deep Kernel Fusion for Transformers ACL 2026 DeNC++: Efficient Diffusion-Enhanced Neural Codec for End-to-end Semantic Streaming at the Edge AAAI 2026 Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding CVPR 2026 DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning CVPR 2026 Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking ACL 2026