← all areas
language, end to end
learn nlp
embeddings, the transformer, pretrained models, and building real apps on top.
curatedmixed~4 weeks, part-time
nlp & the transformer
the modern nlp stack from the ground up: represent text, understand the transformer deeply, then fine-tune and ship.
4 modules · 13 resources · checkpoint per modulestay current
see the full digest →what's new in nlp
- POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shakingthis paper introduces pops, a technique designed to recover multi-modality knowledge that may be 'unlearned' in multi-modal large language models (mllms). for practitioners, this is crucial for ensuring mllms maintain a comprehensive understanding across different data types, thereby improving their overall performance and robustness.
- MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoningthis paper introduces miles, a method for large language models (llms) to improve their reasoning by learning to select and utilize modular instructions. this approach helps practitioners build more robust and adaptable llms, especially for complex tasks that require multi-step reasoning and self-correction capabilities.
- Can Reasoning Models Detect Changes to their Chains of Thought?this paper examines whether reasoning models can detect changes in their chains of thought. this is relevant for practitioners working on explainable ai, as it explores the robustness and manipulability of a model's internal reasoning process.
want something more specific in nlp? generate a fresh path.
generate a path