"downstream task performance" Papers

9 papers found

Filters:downstream task performanceClear all

Conference

AAAI 2025 (3,028)COLM 2025 (418)CVPR 2025 (2,873)ICCV 2025 (2,701)ICLR 2025 (3,827)ICML 2025 (3,340)ISMAR 2025 (229)NEURIPS 2025 (5,858)AAAI 2024 (2,289)CVPR 2024 (2,716)ECCV 2024 (2,387)ICLR 2024 (2,297)ICML 2024 (2,635)

Paper Type

poster (24,624)paper (8,558)oral (1,594)spotlight (1,421)highlight (975)

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining

Dylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh et al.

NEURIPS 2025arXiv:2502.02494
1
citations

Group-Level Data Selection for Efficient Pretraining

Zichun Yu, Fei Peng, Jie Lei et al.

NEURIPS 2025arXiv:2502.14709
2
citations

Language models scale reliably with over-training and on downstream tasks

Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar et al.

ICLR 2025arXiv:2403.08540
79
citations

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Philippe Formont, Maxime Darrin, Banafsheh Karimian et al.

NEURIPS 2025arXiv:2510.18680

Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework

Zhenjie Xu, Wenqing Chen, Yi Tang et al.

AAAI 2025paperarXiv:2412.15504
8
citations

Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold

Ido Cohen, Ronen Talmon

NEURIPS 2025

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

Yibo Wang, Ruiyuan Gao, Kai Chen et al.

CVPR 2024arXiv:2403.13304
39
citations

Headless Language Models: Learning without Predicting with Contrastive Weight Tying

Nathan Godey, Éric Clergerie, Benoît Sagot

ICLR 2024arXiv:2309.08351
5
citations

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness

Yahong Zhang, Chenchen Fan, Donghui Chen et al.

ICML 2024