Microsoft has released HARC-Qwen2.5-7B-Instruct, a fine-tuned version of Qwen2.5-7B-Instruct optimized for safety and alignment in conversational AI. The model is a transformer-based text-generation model, available on Hugging Face under the Apache 2.0 license. It is distributed in safetensors format and is compatible with text-generation-inference and Hugging Face endpoints. The release is associated with the paper arXiv:2607.00572.
Microsoft released HARC-Llama-3.1-8B-Instruct on Hugging Face. It is a text-generation model built on Meta's Llama 3.1 8B Instruct. Repository tags indicate a focus on safety, alignment, and conversational use. The model card provides no benchmarks, training details, or specific capability claims. It is distributed under the Llama 3.1 license.
VideoSearch-R1 is an agentic framework that performs iterative video retrieval and reasoning by interacting with a search engine in multiple turns. It introduces Soft Query Refinement (SQR), which refines search query tokens in a continuous latent space rather than rewriting discrete text, enabling more efficient adjustments. The framework is trained with Group Relative Policy Optimization (GRPO) using task-level rewards from retrieval and downstream tasks like temporal grounding. VideoSearch-R1 achieves state-of-the-art results on three datasets for Video Corpus Moment Retrieval (VCMR), iteratively retrieving videos from large-scale corpora and then performing precise query-conditioned temporal grounding within the retrieved content. Analysis shows SQR effectively refines queries while requiring significantly fewer generated tokens than explicit text-level refinement. Code and model checkpoints are publicly available.
Nvidia has published a quantized variant of the Mistral-Medium-3.5-128B large language model on Hugging Face. The model employs NVFP4, a 4-bit floating point precision format, to reduce memory footprint and potentially accelerate inference. It is labeled as conversational and text-generation compatible, using the safetensors format. The repository indicates the model is based on the original Mistral-Medium-3.5-128B from Mistral AI and is shared under a custom license.
Microsoft has released GELab-Zero-4B-preview-Sico-Evolution, a 4-billion-parameter vision-language model specialized for GUI agent tasks. The model is built on Qwen3-VL using LoRA fine-tuning and targets mobile and general GUI agent use cases. It supports English and Chinese text inputs, and processes image-text-to-text pipelines. The release is open-source under the Apache 2.0 license and is noted as an early preview version.
A Hugging Face repository for the LongCat-2.0 model by meituan-longcat was created on June 30, 2026. The repository metadata contains no description of the model's architecture, capabilities, or usage. As of the creation timestamp, the repository has 51 likes and 0 downloads.