Category: AI News

  • AI Research Highlights | Week 38, 2023

    1. Large Language Models as Optimizers Source: https://arxiv.org/abs/2309.03409 LLMs can serve as optimizers in the OPRO (Optimization by PROmpting) framework, which DeepMind Scientists just unveiled. Under OPRO, prompts can be best optimized by LLMs, exceeding human-designed prompts by up to 8% on GSM8K tests and by up to 50% on…

  • Top 10 Most Influential Projects on AI in 2022

    The year 2022 saw significant advancements in the realm of Artificial Intelligence(AI). Natural Language Processing, Image Generation, Machine Learning, and other related fields have all made remarkable strides, making AI tools widely used across various domains. In the first half of 2022, a large number of generative AI models emerged,…

  • AI Research Highlights | Week 46, 2023

    1. MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning Source: https://arxiv.org/abs/2311.02303 Researchers from the Ant group proposed MFTCoder, an open-source project of CodeFuse for multitasking Code-LLMs, which includes models, datasets, training codebases, and inference guides. The focus is on addressing the issues of data balance and convergence speed that commonly arise…

  • ADI: How MindOS Developed an Adaptive AI to Surpass AGI

    Research reveals a curious trend: Large language models (LLMs) are closer to the habits and likes of a specific group of people. We call this group the WEIRD population. WEIRD stands for Western, Educated, Industrialized, Rich, and Democratic. So, how can we ensure AI serves not just a select few…

  • AI Research Highlights | Week 49, 2023

    1. FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models Source: https://arxiv.org/abs/2311.15614 In this paper, the authors proposed a novel collaborative learning framework called FreeAL to employ the LLMs as active annotators and the SLMs as weak filters to interactively distill the taskrelated knowledge from the LLMs.…

  • AI Research Highlights | Week 51, 2023

    1. Intelligent Virtual Assistants with LLM-based Process Automation Source: https://arxiv.org/abs/2312.06677 This paper proposed LLM-Based Process Automation (LLMPA), containing modules for decomposing instructions, generating natural language descriptions, detecting interface elements, predicting next actions, and checking for errors. The system is demonstrated using the Alipay mobile payments app as a target environment.…

  • AI Research Highlights | Week 52, 2023

    1. LLM in a flash: Efficient Large Language Model Inference with Limited Memory Source: https://browse.arxiv.org/html/2312.11514v1 This paper discusses the challenges of efficiently running large language models (LLMs) that exceed the available DRAM capacity by storing the model parameters on flash memory but bringing them on demand to DRAM. It introduces…

  • AI Research Highlights | Week 1, 2024

    1. WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation Source: https://arxiv.org/abs/2312.14187v2 In this paper, researchers proposed a method that could make full use of source code and explicitly control the quality of generated data. Owing to the fact that instruction tuning is to align the pre-training model…

  • AI Research Highlights | Week 2, 2024

    Contents 1. LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning 2. Soaring from 4K to 400K: Extending LLM’s Context with Activation Beacon 3. Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models 4. LLM Augmented LLMs: Expanding Capabilities through Composition 5. Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives…

  • AI Research Highlights | Week 3, 2024

    Contents 1. Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security 2. The Impact of Reasoning Step Length on Large Language Models 3. User Embedding Model for Personalized Language Prompting 4. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training 5. TrustLLM: Trustworthiness in Large Language…