Foundation Models

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP EMNLP 2025 SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers EMNLP 2025 SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification ACL 2025 SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems ACL 2025 SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications ICCV 2025 ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement AAAI 2025 SCULPT: Systematic Tuning of Long Prompts ACL 2025 SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation ACL 2025 SEARA: An Automated Approach for Obtaining Optimal Retrievers EMNLP 2025 Searching for Structure: Investigating Emergent Communication with Large Language Models COLING 2025 Search-o1: Agentic Search-Enhanced Large Reasoning Models EMNLP 2025 SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities ACL 2025 SecV: LLM-based Secure Verilog Generation with Clue-Guided Exploration on Hardware-CWE Knowledge Graph IJCAI 2025 SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science ACL 2025 Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding CVPR 2025 Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era ACL 2025 See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models ACL 2025 SegBuilder: A Semi-Automatic Annotation Tool for Segmentation WACV 2025 SEK: Self-Explained Keywords Empower Large Language Models for Code Generation ACL 2025 Select-then-Route : Taxonomy guided Routing for LLMs EMNLP 2025 Self-Ensemble: Mitigating Confidence Distortion for Large Language Models EMNLP 2025 Self-Improvement in Multimodal Large Language Models: A Survey EMNLP 2025 Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges ICML 2025 Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs ACL 2025 Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts ICLR 2025