Theory

Difference-of-submodular Bregman Divergence ICLR 2025 Differential Privacy Mechanisms in Neural Tangent Kernel Regression WACV 2025 Diffusion Models for Robotics AAAI 2025 Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data ICLR 2025 Disagreements in analyses of rhetorical text structure: A new dataset and first analyses ACL 2025 Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators ICLR 2025 Discursive Circuits: How Do Language Models Understand Discourse Relations? EMNLP 2025 Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality CVPR 2025 Divergence of Neural Tangent Kernel in Classification Problems ICLR 2025 DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation EMNLP 2025 Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis ICML 2025 Do Influence Functions Work on Large Language Models? EMNLP 2025 Do LLMs estimate uncertainty well in instruction-following? ICLR 2025 Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs NAACL 2025 DRM Revisited: A Complete Error Analysis JMLR 2025 DROWN: Towards Tighter LiRPA-based Robustness Certification COLING 2025 DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation ACL 2025 Dynamic Epistemic Friction in Dialogue CoNLL 2025 Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration CVPR 2025 Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs ICLR 2025 Early Concept Drift Detection via Prediction Uncertainty AAAI 2025 EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models AAAI 2025 Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly COLING 2025 Efficient Visual Representation Learning with Heat Conduction Equation IJCAI 2025 EFX Feasible Scheduling for Time-dependent Resources IJCAI 2025