Foundation Models

OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints CVPR 2025 Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks CVPR 2025 OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation ICCV 2025 OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking EMNLP 2025 OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities ICLR 2025 Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants CVPR 2025 On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists ICML 2025 ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities ACL 2025 One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit ACL 2025 One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL ACL 2025 One world, one opinion? The superstar effect in LLM responses NAACL 2025 On Large Foundation Models and Alzheimer’s Disease Detection NAACL 2025 ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models ICCV 2025 On Many-Shot In-Context Learning for Long-Context Evaluation ACL 2025 On Memorization of Large Language Models in Logical Reasoning IJCNLP 2025 On Path to Multimodal Generalist: General-Level and General-Bench ICML 2025 On Positional Bias of Faithfulness for Long-form Summarization NAACL 2025 On the Acquisition of Shared Grammatical Representations in Bilingual Language Models ACL 2025 On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages AAAI 2025 On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena NAACL 2025 On the Role of Model Prior in Real-World Inductive Reasoning EMNLP 2025 OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models ACL 2025 OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data ICLR 2025 OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees ICLR 2025 Open-Set Living Need Prediction with Large Language Models ACL 2025