QvQ-72B-Previewπ an open weight model for visual reasoning just released by Alibaba_Qwen team Qwen/qvq-676448c820912236342b9888 β¨ Combines visual understanding & language reasoning. β¨ Scores 70.3 on MMMU β¨ Outperforms Qwen2-VL-72B-Instruct in complex problem-solving
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute π₯
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
π Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
π Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
π§ Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
Megrez-3B-Omni π₯ an on-device multimodal LLM by Infinigence AI, another startup emerging from the Tsinghua University ecosystem. Model: Infinigence/Megrez-3B-Omni Demo: Infinigence/Megrez-3B-Omni β¨Supports analysis of image, text, and audio modalities β¨Leads in bilingual speech ( English & Chinese ) input, multi-turn conversations, and voice-based queries β¨Outperforms in scene understanding and OCR across major benchmarks