Can large language models collaborate without sending a single token of text? a team of researchers from Tsinghua University, Infinigence AI, The Chinese University of Hong Kong, Shanghai AI ...

Optical character recognition has moved from plain text extraction to document intelligence. Modern systems must read scanned and digital PDFs in one pass, preserve layout, detect tables, extract key ...

The landscape of AI is expanding. Today, many of the most powerful LLMs (large language models) reside primarily in the cloud, offering incredible capabilities but also concerns about privacy and ...

Shobha is a data analyst with a proven track record of developing innovative machine-learning solutions that drive business value.

Canary-1b-v2: Multilingual ASR + Translation (En ↔ 24 Languages) Canary-1b-v2 is a billion-parameter Encoder-Decoder model trained on Granary, delivering high-quality transcription and translation ...

Orchestration Host routes across many servers/tools App-local chaining Agent/toolkit routes intents → operations ...

The Mixture-of-Agents (MoA) architecture is a transformative approach for enhancing large language model (LLM) performance, especially on complex, open-ended tasks where a single model can struggle ...

Meta has introduced KernelLLM, an 8-billion-parameter language model fine-tuned from Llama 3.1 Instruct, aimed at automating the translation of PyTorch modules into efficient Triton GPU kernels. This ...

Meta has released MobileLLM-R1, a family of lightweight edge reasoning models now available on Hugging Face. The release includes models ranging from 140M to 950M parameters, with a focus on efficient ...

In this article we will analyze how Google, OpenAI, and Anthropic are productizing ‘agentic’ capabilities across computer-use control, tool/function calling, orchestration, governance, and enterprise ...

The research introduced a two-phase training process. First, they used supervised fine-tuning (SFT) on high-quality trajectories sampled from Claude-4 Sonnet using rejection sampling, effectively ...

Vibe Coding is redefining the software landscape by harnessing artificial intelligence to make code creation faster, more intuitive, and accessible to virtually anyone. In 2025, this trend has moved ...