22 citations · 79 across the 123 of their papers we have counts for
131 papers
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Jie Wu, Zhenru Zhang, Beichen Zhang +11
As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what…
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Jiani Guo, Junjie Wang, Jie Wu +5
Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them through multi-step deduction. Existing free-form traces obscure the decisions that…
Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA
Tianhang Yang, Yanze Zheng, Junjie Wang +3
While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across manipulation tasks and, even…
Simple-OPD: Demystifying Warm-up for On-policy Distillation
Tao Liu, Taiqiang Wu, Mao Zheng +5
On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage b…
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes…
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Yan Wang, Qifan Zhang, Jiachen Yu +12
Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…
AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence
Wei-Bin Kou, Jingreng Lei, Guangxu Zhu +1
Mixture of Experts (MoE) are increasingly deployed over wireless cloud-edge networks, as a single edge device lacks sufficient resources to host large-scale models locally. In this…
AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation
Zeyue Tian, Lei Ke, Zhaoyang Liu +8
Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework,…
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Haoling Li, Kai Zheng, Jie Wu +4
Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reli…
Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos
Bo Gou, Jicheng Zhang, Jianlong Xiong +9
Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges. First, publicly available datasets are scar…
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Yu Li, Menghan Xia, Gongye Liu +8
Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we…
WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts
Yuxin Meng, Yuhan Suo, Junjie Wang +9
Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page…
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
Yusong Zhao, Yuejin Xie, Youliang Yuan +4
Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable multimodal large language mod…
Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
Xuewei Yang, Jiachen Yu, Jie Wu +3
Reinforcement learning from verifiable rewards improves the reasoning ability of large language models, but often suffers from entropy collapse, in which increasingly concentrated…
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu +7
Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In t…
VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding
Yinghao Wu, Zhuoyan Luo, Yiyao Yu +3
Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emph…
OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization
Wei-Bin Kou, Guangxu Zhu, Ming Tang +4
The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud data aggregation, others en…
Video-Zero: Self-Evolution Video Understanding
Ruixu Zhang, Deyi Ji, Lanyun Zhu +4
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains…
IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
Yifan Chen, Fei Yin, Chunle Guo +2
In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms…
MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence
Yifan Chen, Fei Yin, Qingyan Bai +2
We introduce MMCL-Bench, a benchmark for multimodal context learning: learning task-local rules, procedures, and empirical patterns from visual or mixed-modality teaching context a…
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
Jiachen Yu, Zhihao Xu, Junjie Wang +1
Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for reinforcement learning. Howeve…
Velocity-Space 3D Asset Editing
Hao Liu, Yuxuan Lin, Jingfeng Guo +4
Editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing. Existing methods enforce locality through mechan…
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiran Xu, Yiming Ren, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
Yuqing Chen, Lin Liu, Haisu Wu +4
Video object removal frequently struggles to eliminate target objects and their associated complex physical effects (e.g., smoke and light) in real-world scenes. We attribute this…