Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…The agent first pulls potentially relevant documents into its workspace, then performs local DCI operations — search, filter, compare, inspect, and verify — within that evolving workspace. 💡 Why it works: DR-DCI combines the…
…an expert-locality-aware decode router for prefill-decode disaggregated Mixture-of-Experts serving that improves performance by predicting expert activations and routing requests accordingly. Generated by Qwen/Qwen2.5-Coder-32B…
…introduced to transfer visual localization capabilities into textual reasoning, improving fine-grained perception in multimodal language models without requiring explicit visual grounding during inference. Generated by Qwen/Qwen2.5-Coder-32B-Instruct…
…rescaling factors and utilizing a bifocal attention mechanism that maintains high performance across varying sequence lengths. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Modern LLMs are increasingly deployed in long-context…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language…
…video generation in world action models for robot control, achieving better performance with reduced computational costs. Generated by Qwen/Qwen2.5-Coder-32B-Instruct World Action Models (WAMs) commonly rely on video…
…gradient conflicts and merges results via weighted averaging, achieving performance comparable to centralized methods with reduced communication overhead. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Instruction tuning aligns large language models…
…training data poisoning while maintaining performance, with the backdoor activating at token feature level and being detectable through behavioral and weight-level statistics. Generated by Qwen/Qwen2.5-Coder-32B-Instruct We…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their…
…Fine-tuning VITA-1.5 , Qwen2.5-Omni-7B and Qwen3-Omni-30B on OmniVideo-100K yields performance gains of up to 20.59% on OmniVideo-Test , demonstrating strong generalization (up to…