32 papers
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
Yan Wang, Xiulong Yuan, Kaiming Yang +16
Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost ope…
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Lianghua Huang, Zhi-Fan Wu, Wei Wang +22
We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. W…
Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
Jiazhao Zhang, Gengze Zhou, Hale Yin +32
Agentic navigation systems require a base navigation model whose observation strategy can be externally reconfigured at inference time, because instruction following, object search…
Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention
Xiao Li, Chengruidong Zhang, Hao Luo +15
Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active corr…
Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
Yangjun Wu, Keyu Yan, Yu Liu +5
The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realis…
Qwen-AgentWorld: Language World Models for General Agents
Yuxin Zuo, Zikai Xiao, Li Sheng +30
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigat…