Do Vision-Language Models Respect Contextual Integrity in Location Disclosure? Paper • 2602.05023 • Published Feb 4 • 2
COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs Paper • 2502.17410 • Published Feb 24, 2025
LLMs Can Generate a Better Answer by Aggregating Their Own Responses Paper • 2503.04104 • Published Mar 6, 2025 • 1
SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation Paper • 2506.18349 • Published Jun 23, 2025 • 13
KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation Paper • 2407.00548 • Published Jun 29, 2024
Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation Paper • 2305.03907 • Published May 6, 2023 • 1
Ego4D: Around the World in 3,000 Hours of Egocentric Video Paper • 2110.07058 • Published Oct 13, 2021
Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation Paper • 2305.03907 • Published May 6, 2023 • 1
Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders Paper • 2412.09586 • Published Dec 12, 2024 • 6
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_3 Text Generation • 8B • Updated May 13, 2024
GeorgiaTech/0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3 Text Generation • 7B • Updated May 12, 2024 • 2