Deep Learning

BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance CVPR 2025 BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays AAAI 2025 Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs ACL 2025 Beyond Accuracy: On the Effects of Fine-Tuning Towards Vision-Language Model’s Prediction Rationality AAAI 2025 Beyond Accuracy: Revisiting Out-of-Distribution Generalization in NLI Models CoNLL 2025 Beyond A Single AI Cluster: A Survey of Decentralized LLM Training EMNLP 2025 Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling ICML 2025 Beyond Attacks: Advancing Fake Speech Detection with Attack-Agnostic Methods Interspeech 2025 Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning ICLR 2025 Beyond Base Predictors: Using LLMs to Resolve Ambiguities in Akkadian Lemmatization NAACL 2025 Beyond Blur: A Fluid Perspective on Generative Diffusion Models ICCV 2025 Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection WACV 2025 Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing ICLR 2025 Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation ICLR 2025 Beyond Citations: Integrating Finding-Based Relations for Improved Biomedical Article Representations ACL 2025 Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs IJCNLP 2025 Beyond Clean Training Data: A Versatile and Model-Agnostic Framework for Out-of-Distribution Detection with Contaminated Training Data CVPR 2025 Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations ICCV 2025 Beyond Coarse Labels: Fine-Grained Problem Augmentation and Multi-Dimensional Feedback for Emotional Support Conversation EMNLP 2025 Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning ACL 2025 Beyond Constant Parameters: Hyper Prediction Models and HyperMPC CoRL 2025 Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models EMNLP 2025 Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning EMNLP 2025 Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals’ Subjective Text Perceptions ACL 2025 Beyond Demonstrations: Dynamic Vector Construction from Latent Representations EMNLP 2025