Machine Learning

Space-Efficient Language Generation in the Limit COLT 2026 Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains WACV 2026 SPAR-Det: Segmentation-guided and Prior-Aided Routing for Small Object Detection WACV 2026 SPARD: Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction AAAI 2026 SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling AAAI 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views AAAI 2026 Sparse Action-Dependent Policy Iteration under Coordination Structures: Convergence and Optimality UAI 2026 Sparse Adapter Fusion for Continual Learning in NLP EACL 2026 Sparse Additive Model Pruning for Order-Based Causal Structure Learning AAAI 2026 Sparse Attention Across Multiple-Context KV Cache AAAI 2026 Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs EACL 2026 Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction AAAI 2026 Sparse Nonparametric Contextual Bandits ALT 2026 Sparse Poisson Gamma Belief Networks for High-Dimensional Sparse Count Data AAAI 2026 Sparse recovery of Diffusion Dynamics: Handling High-Dimensionality in Repeated Short Trajectories UAI 2026 Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts ACL 2026 SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder AAAI 2026 Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis CVPR 2026 Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition L4DC 2026 Sparse Topic Modeling via Spectral Decomposition and Thresholding JMLR 2026 Sparse Tuning Enhances Plasticity in PTM-based Continual Learning AAAI 2026 SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space EACL 2026 SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation AAAI 2026 Spatial Graph Attention Network Modeling for Neighborhood-Scale Lead Contamination Risk Prediction Using Publicly Available Data AAAI 2026