Deep Researcher with Test-Time Diffusion
【DL輪読会】”Deep Researcher with Test-Time Diffusion” by @DeepLearning2023
カテゴリー: dls-2025
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
【DL輪読会】 V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and P more
Between Circuits and Chomsky: Pre- pretraining on Formal Languages Imparts Linguistic Bias
【DL輪読会】Between Circuits and Chomsky: Pre- pretraining on Formal Languages Imparts Lin more
Energy-Based Transformers are Scalable Learners and Thinkers
【DL輪読会】Energy-Based Transformers are Scalable Learners and Thinkers by @DeepLearning2 more
“SmolVLA” A vision-language-action model for affordable and efficient robotics
【DL輪読会】“SmolVLA” A vision-language-action model for affordable and efficient robotics more
Instruction Tuning With Loss Over Instructions
【DL輪読会】Instruction Tuning With Loss Over Instructions by @DeepLearning2023
TaskBench: Benchmarking Large Language Models for Task Automation
【DL輪読会】TaskBench: Benchmarking Large Language Models for Task Automation by @DeepLear more
Learning to Reason without External Rewards
【DL輪読会】Learning to Reason without External Rewards by @DeepLearning2023
VisionZip: Longer is Better but Not Necessary in Vision Language Models [S. Yang+CVPR’25]
【DL輪読会】VisionZip: Longer is Better but Not Necessary in Vision Language Models [S. Ya more
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
【DL輪読会】Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked more