Efficient Computing

Logic Haystacks: Probing LLMs’ Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding) EACL 2026 LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers AAAI 2026 Logits-Based Block Pruning with Affine Transformations for Large Language Models EACL 2026 LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization WACV 2026 LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning AAAI 2026 LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention AAAI 2026 Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off AAAI 2026 MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding WACV 2026 MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression WACV 2026 Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction AAAI 2026 MemeBQ:Memory Efficient Binary Quantization of LLMs AAAI 2026 Memory-Augmented Representation for Efficient Event-based Visuomotor Policy Learning with Adaptive Perception and Control WACV 2026 MetaLead: A Comprehensive Human-Curated Leaderboard Dataset for Transparent Reporting of Machine Learning Experiments EACL 2026 Mix-QSAM2: Mixed-Precision Quantization for High Fidelity Segmentation in Resource Constrained Scenarios AAAI 2026 Mnemosyne: Accelerating Multi-Hop Question Answering via Cache Hit Order Fitting AAAI 2026 MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation EACL 2026 Model Whisper: Steering Vectors Unlock Large Language Models’ Potential in Test-Time AAAI 2026 MoEG-HOI: Mixture of Expert Groups for One-Stage Hand-Object Interaction Motion Generation with Hand-Finger-Joint Semantic Guidance AAAI 2026 MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training WACV 2026 MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings AAAI 2026 MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models WACV 2026 MRT: Learning Compact Representations with Mixed RWKV-Transformer for Extreme Image Compression AAAI 2026 MSCFL: Model Structure-Aware Clustered Federated Learning for System Heterogeneity and Data Drift AAAI 2026 MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation AAAI 2026 NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages AAAI 2026