Large Language Models

Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement EMNLP 2025 OldJoe at AVeriTeC: In-context learning for fact-checking ACL 2025 Olica: Efficient Structured Pruning of Large Language Models without Retraining ICML 2025 OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens ACL 2025 Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos CVPR 2025 OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference ACL 2025 OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction ACL 2025 OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation ACL 2025 OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs ICLR 2025 Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models ICLR 2025 Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks CVPR 2025 On a Connection Between Imitation Learning and RLHF ICLR 2025 On Calibration of LLM-based Guard Models for Reliable Content Moderation ICLR 2025 On choosing the vehicles of metaphors without a body: evidence from Large Language Models ACL 2025 On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation NAACL 2025 On Domain-Adaptive Post-Training for Multimodal Large Language Models EMNLP 2025 One_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based Approach NAACL 2025 One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning EMNLP 2025 One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models AAAI 2025 One Unified Model for Diverse Tasks: Emotion Cause Analysis via Self-Promote Cognitive Structure Modeling NAACL 2025 On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework COLING 2025 On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures ACL 2025 On Integrating LLMs Into an Argument Annotation Workflow ACL 2025 Online Preference Alignment for Language Models via Count-based Exploration ICLR 2025 Online Video Understanding: OVBench and VideoChat-Online CVPR 2025