Machine Learning

GPU-Disaggregated Serving for Deep Learning Recommendation Models at Scale NSDI 2025 GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference IJCNLP 2025 GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision ICLR 2025 GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration ACL 2025 Graceful Forgetting in Generative Language Models EMNLP 2025 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining COLING 2025 GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models COLING 2025 GRADA: Graph-based Reranking against Adversarial Documents Attack EMNLP 2025 GraDaSE: Graph-Based Dataset Search with Examples EMNLP 2025 GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation EMNLP 2025 Graders Should Cheat: Privileged Information Enables Expert-Level Automated Evaluations EMNLP 2025 GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer EMNLP 2025 GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning EMNLP 2025 Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models ACL 2025 Gradient Aligned Regression via Pairwise Losses ICML 2025 Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation AAAI 2025 Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval EMNLP 2025 Gradient-based Explanations for Deep Learning Survival Models ICML 2025 Gradient-Based Nonlinear Rehearsal Learning with Multivariate Alterations AAAI 2025 Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation AAAI 2025 Gradient Boosting Reinforcement Learning ICML 2025 Gradient correlation is a key ingredient to accelerate SGD with momentum ICLR 2025 Gradient Decomposition and Alignment for Incremental Object Detection ICCV 2025 Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes ICML 2025 Gradient descent with generalized Newton’s method ICLR 2025