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
カテゴリー: seminar
WoMAP: World Models For Embodied Open-Vocabulary Object Localization
【DL輪読会】 WoMAP: World Models For Embodied Open-Vocabulary Object Localization by @Deep more
Unified Vision-Language-Action Models (arXiv, 2025)
【DL輪読会】Unified Vision-Language-Action Models (arXiv, 2025) by @DeepLearning2023
From Foresight to Forethought: VLM-In-The-Loop Policy Steering via Latent Alignment
【DL輪読会】From Foresight to Forethought: VLM-In-The-Loop Policy Steering via Latent Alig more
SAFECHAIN: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
【DL輪読会】 SAFECHAIN: Safety of Language Models with Long Chain-of-Thought Reasoning Cap more
Prompt-to-SQL Injections in LLM-Integrated Web Applications: Risks and Defenses
【DL輪読会】Prompt-to-SQL Injections in LLM-Integrated Web Applications: Risks and Defense more
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
【DL輪読会】Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs b more
Open-World Reinforcement Learning over Long Short-Term Imagination
【DL輪読会】Open-World Reinforcement Learning over Long Short-Term Imagination by @DeepLea more
Learning Transformer-based World Models with Contrastive Predictive Coding
【DL輪読会】Learning Transformer-based World Models with Contrastive Predictive Coding by more
Titans: Learning to Memorize at Test Time
【DL輪読会】 Titans: Learning to Memorize at Test Time by @DeepLearning2023