8 papers
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Boxiu Li, Zimo Wen, Yijia Fan +24
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a…
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
Junnan Nie, Jiayi Li, Jiachen Zhang +5
Recent vision-language-action and diffusion-based robot policies often use action chunking, where each policy query predicts a sequence of future actions and the robot executes an…
MORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization
Chenghao Liu, Yu Zhang, Zhongtao Jiang +7
Embedding-based retrieval typically returns highest-scoring items, but many production scenarios require items that satisfy a target attribute while preserving a fine-grained patte…
What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
Jiachen Zhang, Junnan Nie, Junyi Lao +4
Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Their frozen representations nev…
VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis
Jiachen Zhang, Junyi Lao, Chenghao Liu +5
Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although r…
DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs
Jiachen Zhang, Chengtai Li, Jianfeng Ren +3
Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermedia…
MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning
Chenghao Liu, Zhimu Zhou, Jiachen Zhang +3
Vision-and-Language Navigation (VLN) requires an agent to interpret natural language instructions and navigate complex environments. Current approaches often adopt a "black-box" pa…
TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models
Chenghao Liu, Jiachen Zhang, Chengxuan Li +4
Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This fram…