Speaking News You Can USE!
Seeking Speed without Loss in Large Language Models? Meet EAGLE: A Machine Learning Framework Setting New Standards for Lossless Acceleration
For LLMs, auto-regressive decoding is now considered the gold standard. Because LLMs generate output tokens individually, the procedure is time-consuming and expensive. Methods based on speculative sampling provide an answer to this problem. In the first, called the...
Meet CMMMU: A New Chinese Massive Multi-Discipline Multimodal Understanding Benchmark Designed to Evaluate Large Multimodal Models LMMs
In the realm of artificial intelligence, Large Multimodal Models (LMMs) have exhibited remarkable problem-solving capabilities across diverse tasks, such as zero-shot image/video classification, zero-shot image/video-text retrieval, and multimodal question answering...
DeepSeek-AI Introduce the DeepSeek-Coder Series: A Range of Open-Source Code Models from 1.3B to 33B and Trained from Scratch on 2T Tokens
In the dynamic field of software development, integrating large language models (LLMs) has initiated a new chapter, especially in code intelligence. These sophisticated models have been pivotal in automating various aspects of programming, from identifying bugs to...
This AI Paper from China Introduces ‘AGENTBOARD’: An Open-Source Evaluation Framework Tailored to Analytical Evaluation of Multi-Turn LLM Agents
Evaluating LLMs as versatile agents is crucial for their integration into practical applications. However, existing evaluation frameworks face challenges in benchmarking diverse scenarios, maintaining partially observable environments, and capturing multi-round...
Researchers from the Chinese University of Hong Kong and Tencent AI Lab Propose a Multimodal Pathway to Improve Transformers with Irrelevant Data from Other Modalities
Transformers have found widespread application in diverse tasks spanning text classification, map construction, object detection, point cloud analysis, and audio spectrogram recognition. Their versatility extends to multimodal tasks, exemplified by CLIP’s use of...
Meet BiTA: An Innovative AI Method Expediting LLMs via Streamlined Semi-Autoregressive Generation and Draft Verification
Large language models (LLMs) based on transformer architectures have emerged in recent years. Models such as Chat-GPT and LLaMA-2 demonstrate how the parameters of LLMs have rapidly increased, ranging from several billion to tens of trillions. Although LLMs are very...
