Foundation Models

Unveiling and Addressing Pseudo Forgetting in Large Language Models ACL 2025 Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing ACL 2025 Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis COLING 2025 Unveiling Internal Reasoning Modes in LLMs: A Deep Dive into Latent Reasoning vs. Factual Shortcuts with Attribute Rate Ratio EMNLP 2025 Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models COLING 2025 Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging ACL 2025 Update Your Transformer to the Latest Release: Re-Basin of Task Vectors ICML 2025 UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation EMNLP 2025 UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence ICCV 2025 UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction AAAI 2025 UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios AAAI 2025 User-side Model Consistency Monitoring for Open Source Large Language Models Inference Services ACL 2025 U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models ICLR 2025 Using Next Sentence Prediction to Test ChatGPT’s Text Comprehension (Student Abstract) AAAI 2025 UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench ACL 2025 Value Profiles for Encoding Human Variation EMNLP 2025 VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting ICCV 2025 Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025 VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions EMNLP 2025 VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios EMNLP 2025 Verifying the Steps of Deductive Reasoning Chains ACL 2025 VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM EMNLP 2025 VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs EMNLP 2025 vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation CVPR 2025 VGGSounder: Audio-Visual Evaluations for Foundation Models ICCV 2025