Foundation Models

SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts AAAI 2026 SLANG-GraphRAG: Multi-Layered Retrieval with Domain-Specific Knowledge for Low Resource Social Media Conversations EACL 2026 Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA Benchmarks AAAI 2026 SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse AAAI 2026 SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models CVPR 2026 SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization AAAI 2026 SPAN: Benchmarking and Improving Cross-Calendar Temporal Reasoning of Large Language Models AAAI 2026 Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views AAAI 2026 Sparse Attention Across Multiple-Context KV Cache AAAI 2026 SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding CVPR 2026 Spikingformer: A Key Foundation Model for Spiking Neural Networks AAAI 2026 Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering EACL 2026 SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation AAAI 2026 Steve: Your Personal AI Career Coach AAAI 2026 ST-LLM: Spatial Transcriptomics Embedding with Large Language Models AAAI 2026 Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models EACL 2026 Stratos: An End-to-End Distillation Pipeline for Customized LLMs Under Distributed Cloud Environments AAAI 2026 Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs EACL 2026 ST-SAM: Multimodal Scene Text Segmentation with Dense Visual and Sparse Textual Prompts via SAM AAAI 2026 ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos WACV 2026 ST-VLM: A Spatial-to-Image Multimodal Spatial-Temporal Prediction Framework with Vision-Language Model AAAI 2026 SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation EACL 2026 Synthetic Data Generation Pipeline for Low-Resource Swahili Sentiment Analysis: Multi-LLM Judging with Human Validation EACL 2026 T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation EACL 2026 T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation WACV 2026