15 papers
Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives
Hua, Xu, Dongxin Li +4
Discrete diffusion models generate sequences by iteratively resolving multiple tokens in parallel, offering a flexible alternative to left-to-right generation. However, guiding thi…
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
Zeyu Zhang, Jinyuan Mao, Dakai An +6
Leveraging the paradigm of autoregressive diffusion, text-conditioned interactive video world models aim to simulate temporally coherent environments guided by textual instructions…
Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs
Haiji Liang, Pengfei Zhou, Zhenglin Wan +3
Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing vision token pruning method…
ReWorld: An Interactive World Model with Long-Horizon Memory
Zhifei Chen, Luozhou Wang, Guibao Shen +8
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memo…
Video = World + Event Stream
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +24
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persis…
Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +23
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises…
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…
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
Shikai Qiu, Xiaowen Xu, Benlei Cui +55
General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI s…
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Pengfei Zhou, Zhiwei Tang, Yixing Ma +8
Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Con…
Discovering Millions of Interpretable Features with Sparse Autoencoders
XinYang He, Wei Wang, Bing Zhao +5
Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features. However, training SAEs…
WorldOlympiad: Can Your World Model Survive a Triathlon?
Yuke Zhao, Wangbo Zhao, Weijie Wang +8
We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchm…
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era
Masao Someki, Alexander Polok, Carlos Carvalho +14
Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort…
MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model
Lichen Bai, Tianhao Zhang, Shitong Shao +14
As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but…
From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
Yiqing Zhou, Yu Lei, Shuzheng Si +7
Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents…
RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
Yu Lei, Shuzheng Si, Wei Wang +4
Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt…