out-of-domain generalization

Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering EACL 2026 Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories ACL 2026 Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization ACL 2026 OccAny: Generalized Unconstrained Urban 3D Occupancy CVPR 2026 Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation CVPR 2026 R1-RE: Cross-Domain Relation Extraction with RLVR ACL 2026 See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning CVPR 2026 Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data ACL 2026 A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs EMNLP 2025 Analyzing Offensive Language Dataset Insights from Training Dynamics and Human Agreement Level COLING 2025 A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy EMNLP 2025 A Variational Approach for Mitigating Entity Bias in Relation Extraction ACL 2025 Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection COLING 2025 Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning EMNLP 2025 D^3: Scaling Up Deepfake Detection by Learning from Discrepancy CVPR 2025 Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentation ICCV 2025 Enhancing Foundation Models with Federated Domain Knowledge Infusion ICML 2025 Explanation Regularisation through the Lens of Attributions COLING 2025 Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation ACL 2025 Generalizable Audio Spoofing Detection using Non-Semantic Representations Interspeech 2025 Knowledge Bridger: Towards Training-Free Missing Modality Completion CVPR 2025 Layered Insights: Generalizable Analysis of Human Authorial Style by Leveraging All Transformer Layers EMNLP 2025 Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs ICLR 2025 Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration NAACL 2025