profile-image

Deep Learning JP

@DeepLearning2023

deep learning @deep learning jp dee

DL輪読会資料

このユーザのスライド一覧

slide-thumbnail

【DL輪読会】Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
user-img Deep Learning JP 424
slide-thumbnail

【DL輪読会】 Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
user-img Deep Learning JP 1.6K
slide-thumbnail

【DL輪読会】Gradient Estimation with Discrete Stein Operators
user-img Deep Learning JP >100
slide-thumbnail

【DL輪読会】TARAD: Task-Aware Robot Affordance-Centric Diffusion Policy Learned From LLM-Generated Demonstrations
user-img Deep Learning JP 173
slide-thumbnail

【DL輪読会】Subtask-Aware Visual Reward Learning from Segmented Demonstrations
user-img Deep Learning JP 310
slide-thumbnail

【Diffusion勉強会】Diffusion for World Modeling: Visual Details Matter in Atari
user-img Deep Learning JP 0.9K
slide-thumbnail

【DL輪読会】Large Language Models With Contrastive Decoding
user-img Deep Learning JP 231
slide-thumbnail

【DL輪読会】TaskBench: Benchmarking Large Language Models for Task Automation
user-img Deep Learning JP 189
slide-thumbnail

【DL輪読会】Robust Function-Calling for On-Device Language Model via Function Masking
user-img Deep Learning JP 146
slide-thumbnail

【DL輪読会】”Deep Researcher with Test-Time Diffusion”
user-img Deep Learning JP 509
slide-thumbnail

【DL輪読会】 V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
user-img Deep Learning JP 2.7K
slide-thumbnail

【DL輪読会】Between Circuits and Chomsky: Pre- pretraining on Formal Languages Imparts Linguistic Biases
user-img Deep Learning JP 505
slide-thumbnail

【DL輪読会】Energy-Based Transformers are Scalable Learners and Thinkers
user-img Deep Learning JP 798
slide-thumbnail

【DL輪読会】“SmolVLA” A vision-language-action model for affordable and efficient robotics
user-img Deep Learning JP 3.7K
slide-thumbnail

【DL輪読会】Instruction Tuning With Loss Over Instructions
user-img Deep Learning JP 554
slide-thumbnail

【DL輪読会】TaskBench: Benchmarking Large Language Models for Task Automation
user-img Deep Learning JP 151
slide-thumbnail

【DL輪読会】Robust Function-Calling for On-Device Language Model via Function Masking
user-img Deep Learning JP 510
slide-thumbnail

【DL輪読会】VisionZip: Longer is Better but Not Necessary in Vision Language Models [S. Yang+CVPR'25]
user-img Deep Learning JP 1.3K
slide-thumbnail

【DL輪読会】Learning to Reason without External Rewards
user-img Deep Learning JP 887
slide-thumbnail

【DL輪読会】Novelty Detection in Reinforcement Learning with World Models
user-img Deep Learning JP 1.5K
slide-thumbnail

【DL輪読会】Programmatic Video Prediction Using Large Language Models
user-img Deep Learning JP 594
slide-thumbnail

【DL輪読会】Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
user-img Deep Learning JP 1.4K
slide-thumbnail

【DL輪読会】 WoMAP: World Models For Embodied Open-Vocabulary Object Localization
user-img Deep Learning JP 484
slide-thumbnail

【DL輪読会】Unified Vision-Language-Action Models (arXiv, 2025)
user-img Deep Learning JP 618

このユーザの動画一覧

条件に一致するスライドが見つかりませんでした。