Jiajun Deng

WAM-OPD: Sharpening World Action Models via On-Policy Distillation

Panjun Liu, Xiaohan Lei, Shiqi Zhang +8

Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without de…

DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting

Yuxuan Gao, Shiqi Zhang, Yedong Shen +6

Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasi…

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Guangting Zheng, Yiyuan Zhang, Tao Yang +4

Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then a generative model on the frozen latent space. Since…

RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation

Shaoxuan Wang, Guangting Zheng, Rui Huang +4

Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusion- and flow-matching robot p…

LabDex: A Hierarchical Benchmark for Dexterous Manipulation in Laboratories

Zhipeng Tang, Sihang Chen, Sha Zhang +11

Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instrume…

ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction

Shiqi Zhang, Xin Zhang, Yedong Shen +9

Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing physical interactions. Yet effec…

ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes

Xinrui Lin, Sha Zhang, Shumin Wang +3

Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-language instruction. Existing meth…

ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models

Haojie Ren, Songrui Luo, Lingfeng Wang +6

LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV represe…

GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation

Yuan Zhang, Shiqi Zhang, Yedong Shen +11

Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot emb…

GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

Yedong Shen, Shiqi Zhang, Sha Zhang +6

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches t…

Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Control

Yuxuan Gao, Yedong Shen, Shiqi Zhang +6

Diffusion policies effectively model multimodal action distributions for robotic manipulation, but their iterative denoising requires tens to hundreds of network function evaluatio…

Learning Surgical Robotic Manipulation with 3D Spatial Priors

Yu Sheng, Lidian Wang, Xiaomeng Chu +6

Achieving 3D spatial awareness is crucial for surgical robotic manipulation, where precise and delicate operations are required. Existing methods either explicitly reconstruct the…

cs.AI2026

Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models

Yuting Huang, Leilei Ding, Zhipeng Tang +7

While Vision-Language-Action (VLA) models hold promise in embodied intelligence, their large parameter counts lead to substantial inference latency that hinders real-time manipulat…

FARMER: Flow AutoRegressive Transformer over Pixels

Guangting Zheng, Qinyu Zhao, Tao Yang +6

Directly modeling the explicit likelihood of the raw data distribution is key topic in the machine learning area, which achieves the scaling successes in Large Language Models by a…

cs.AI2025

VLMPlanner: Integrating Visual Language Models with Motion Planning

Zhipeng Tang, Sha Zhang, Jiajun Deng +5

Integrating large language models (LLMs) into autonomous driving motion planning has recently emerged as a promising direction, offering enhanced interpretability, better controlla…

PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum

Shiqi Zhang, Sha Zhang, Jiajun Deng +3

Existing open-vocabulary 3D semantic segmentation methods typically supervise 3D segmentation models by merging text-aligned features (e.g., CLIP) extracted from multi-view images…

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

Guangting Zheng, Yehao Li, Yingwei Pan +4

Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-s…

SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images

Yu Sheng, Jiajun Deng, Xinran Zhang +4

A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate se…