Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…across multiple input modalities, revealing significant gaps in model performance and demonstrating superior error detection compared to traditional methods. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Existing benchmarks for MLLM-generated…
…Across three 7-8B instruction-tuned models (Qwen2.5, Qwen3, OLMo-3), SCOPE improves open-ended performance by up to +10.4 points on eight benchmarks and matches or exceeds GRPO_data…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models…
…dual-action semantics and RL to recover reasoning performance under the new format. Across two Qwen3 architectures/scales ( MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain ( AIME25 ) and out…
…the head level, achieving superior long-context performance with reduced training overhead through interpretability-driven selection and scale-normalized fusion. Generated by Qwen/Qwen2.5-Coder-32B-Instruct The quadratic complexity of…
…reasoning by addressing cascading errors through step-wise process rewards, demonstrating superior performance over existing methods. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Recent multimodal large language models have shown great…
Papers arxiv:2606.18249 Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification Published on Jun 16 Submitted by taesiri on Jun 17 Qwen Authors: Wujian Peng , , , , , , , , , Abstract…
…RL post-training with METHOD consistently improves performance on ten external multimodal reasoning benchmarks across Qwen3-VL-4B, Qwen2.5-VL-7B, and MiMo-VL-7B-SFT. View arXiv page View PDF…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model…
…6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6. Generated by Qwen/Qwen2.5-Coder-32B-Instruct…