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
【DL輪読会】 SAFECHAIN: Safety of Language Models with Long Chain-of-Thought Reasoning Cap more
【DL輪読会】Prompt-to-SQL Injections in LLM-Integrated Web Applications: Risks and Defense more
【DL輪読会】Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs b more
【DL輪読会】Open-World Reinforcement Learning over Long Short-Term Imagination by @DeepLea more
【DL輪読会】Learning Transformer-based World Models with Contrastive Predictive Coding by more
【DL輪読会】 Titans: Learning to Memorize at Test Time by @DeepLearning2023
【DL輪読会】Towards Understanding How Knowledge Evolves in Large Vision-Language Models by more
【DL輪読会】 Language Models Are Capable of Metacognitive Monitoring and Control of Their more
【Diffusion勉強会】A continuous time framework for discrete denoising models by @DeepLearn more
【DL輪読会】From task structures to world models: what do LLMs know? by @DeepLearning2023