downstream task

From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions NAACL 2025 Great Memory, Shallow Reasoning: Limits of kNN-LMs NAACL 2025 GSID: Generative Semantic Indexing for E-Commerce Product Understanding EMNLP 2025 Image Quality Assessment: From Human to Machine Preference CVPR 2025 Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework NAACL 2025 Language models scale reliably with over-training and on downstream tasks ICLR 2025 LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models ICML 2025 Less Mature is More Adaptable for Sentence-level Language Modeling ACL 2025 MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba ICLR 2025 Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks ACL 2025 MissScore: High-Order Score Estimation in the Presence of Missing Data ICML 2025 MTQ-Eval: Multilingual Text Quality Evaluation for Language Models IJCNLP 2025 Omni-scene Perception-oriented Point Cloud Geometry Enhancement for Coordinate Quantization ICCV 2025 One for all and all for one: Efficient computation of partial Wasserstein distances on the line ICLR 2025 Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models ICLR 2025 Plug-and-Play Versatile Compressed Video Enhancement CVPR 2025 PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation ICCV 2025 Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks AAAI 2025 RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs AAAI 2025 Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check EMNLP 2025 Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement ICLR 2025 Simplifying DINO via Coding Rate Regularization ICML 2025 Studying the Effect of Hindi Tokenizer Performance on Downstream Tasks COLING 2025 Task-Driven Discrete Representation Learning AISTATS 2025 Task-driven Image Fusion with Learnable Fusion Loss CVPR 2025