Foundation Models

RobSense: A Robust Multi-modal Foundation Model for Remote Sensing with Static, Temporal, and Incomplete Data Adaptability CVPR 2025 Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech NAACL 2025 Robust Function-Calling for On-Device Language Model via Function Masking ICLR 2025 Robust Multi-Objective Preference Alignment with Online DPO AAAI 2025 Robustness of LLMs to Transliteration Perturbations in Bangla AACL 2025 ROGRAG: A Robustly Optimized GraphRAG Framework ACL 2025 RoMath: A Mathematical Reasoning Benchmark in Romanian EMNLP 2025 Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning NAACL 2025 RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation ACL 2025 RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model ICCV 2025 R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning CVPR 2025 RTTC: Reward-Guided Collaborative Test-Time Compute EMNLP 2025 Rule-Guided Extraction: A Hierarchical Rule Optimization Framework for Document-Level Event Argument Extraction EMNLP 2025 s1: Simple test-time scaling EMNLP 2025 S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning ACL 2025 SAEs Are Good for Steering – If You Select the Right Features EMNLP 2025 SAE-V: Interpreting Multimodal Models for Enhanced Alignment ICML 2025 SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models ICML 2025 Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning AAAI 2025 SAFIRE: Segment Any Forged Image Region AAAI 2025 SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation EMNLP 2025 SAKE: Steering Activations for Knowledge Editing ACL 2025 SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation ICML 2025 SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model’s Parameter-Efficient Fine-Tuning ICML 2025 SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models’ Knowledge of Indian Culture ACL 2025