3 citations · 6 across the 14 of their papers we have counts for
8 papers · 1 filter
CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds
Ang Li, Haofei Yu, Zhengwei Tao +7
The growing use of language models for forecasting motivates a broader evaluation of their world-model capabilities. Such evaluation must go beyond predictive accuracy to assess hi…
Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution
Hyewon Suh, Thanh Minh Nguyen, Chih-Lun Lee +5
Many computer tasks recur: the same workflow runs many times, with new inputs and from different starting states. Current computer-use agents re-plan every step of every run, which…
Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
Guoheng Sun, Chen Chen, Jin Wang +2
World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction adds further inference overhead to…
World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation
Ang Li, Xin Xu, Bin Liang +4
Reinforcement learning for user-centric agents is limited by the cost, latency, and risk of collecting online feedback, as well as by the lack of counterfactual comparisons under t…
RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills
Runyi Zhao, Ruixin Wu, Chengkun Li +15
Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress i…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
Guoheng Sun, Tingting Du, Kaixi Feng +6
Vision-Language-Action (VLA) models enable instruction-following robotic manipulation, but they are typically pretrained on 2D data and lack 3D spatial understanding. An effective…
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
Yuan Cao, Dezhi Ran, Mengzhou Wu +9
Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications…