Optimization

Verti-Bench: A General and Scalable Off-Road Mobility Benchmark for Vertically Challenging Terrain RSS 2025 Vertical Federated Learning with Missing Features During Training and Inference ICLR 2025 VFOSA: Variance-Reduced Fast Operator Splitting Algorithms for Generalized Equations JMLR 2025 Vicomtech@WMT 2025: Evolutionary Model Compression for Machine Translation EMNLP 2025 VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning AAAI 2025 Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models CVPR 2025 Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning EMNLP 2025 Video-T1: Test-time Scaling for Video Generation ICCV 2025 VinePPO: Refining Credit Assignment in RL Training of LLMs ICML 2025 Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks CVPR 2025 Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models ACL 2025 Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models ACL 2025 Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models ICLR 2025 Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves ICCV 2025 VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search ACL 2025 Vocabulary-level Memory Efficiency for Language Model Fine-tuning NAACL 2025 VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation EMNLP 2025 Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning ICML 2025 VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field WACV 2025 VProChart: Answering Chart Question Through Visual Perception Alignment Agent and Programmatic Solution Reasoning AAAI 2025 VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints AAAI 2025 Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning ICML 2025 Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach ACL 2025 Wait-Less Offline Tuning and Re-solving for Online Decision Making ICML 2025 Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation ACL 2025