Optimization

Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS ICCV 2025 Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion ICML 2025 BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving ACL 2025 BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution CVPR 2025 BiasFilter: An Inference-Time Debiasing Framework for Large Language Models EMNLP 2025 Bias Mitigation in Graph Diffusion Models ICLR 2025 Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models ICLR 2025 BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data ACL 2025 BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference AAAI 2025 Bilevel Learning for Bilevel Planning RSS 2025 Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling AAAI 2025 Bilevel Reinforcement Learning via the Development of Hyper-gradient without Lower-Level Convexity AISTATS 2025 BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning CVPR 2025 BinarySelect to Improve Accessibility of Black-Box Attack Research COLING 2025 Black-Box Optimization with Implicit Constraints for Public Policy AAAI 2025 Black-Box Test-Time Prompt Tuning for Vision-Language Models AAAI 2025 Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization AISTATS 2025 Blind Image Deblurring with FFT-ReLU Sparsity Prior WACV 2025 BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host Caching OSDI 2025 Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models ICLR 2025 BlockPruner: Fine-grained Pruning for Large Language Models ACL 2025 Block Verification Accelerates Speculative Decoding ICLR 2025 BoA: Attention-aware Post-training Quantization without Backpropagation ICML 2025 BodyGen: Advancing Towards Efficient Embodiment Co-Design ICLR 2025 BoFire: Bayesian Optimization Framework Intended for Real Experiments JMLR 2025