1 citations · 3 across the 15 of their papers we have counts for
18 papers
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
Bohan Sun, Zunhai Su, Xialie Zhuang +3
Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden features whose contextual emphasis…
V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents
Yang Zhang, Jiangyuan Zhao, Chenyou Fan +4
World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrained at scale, a prominent line…
WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
Yuehao Huang, Yunzi Wu, Xiaotao Zhang +7
Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observati…
KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding
Zeyu Liu, Zhangzhe Zhu, Yang Zhang +3
Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts offers a more faithful assessme…
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
Yang Zhang, Jiangyuan Zhao, Chenyou Fan +11
Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloni…
ReMoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement
Jiakun Zheng, Ting Xiao, Shiqin Cao +3
Text-to-motion (T2M) generation aims to control the behavior of a target character via textual descriptions. Leveraging text-motion paired datasets, existing T2M models have achiev…
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Siyuan Yang, Yang Zhang, Haoran He +4
Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human tele…
Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering
Zhongjian Qiao, Rui Yang, Jiafei Lyu +4
Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domai…
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
Yang Zhang, Chenwei Wang, Ouyang Lu +7
Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains…
Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Xinran Li, Chenjia Bai, Zijian Li +3
Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environm…
Online Iterative Self-Alignment for Radiology Report Generation
Ting Xiao, Lei Shi, Yang Zhang +3
Radiology Report Generation (RRG) is an important research topic for relieving radiologist' heavy workload. Existing RRG models mainly rely on supervised fine-tuning (SFT) based on…
Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
Yang Zhang, Xinran Li, Jianing Ye +5
World models have recently attracted growing interest in Multi-Agent Reinforcement Learning (MARL) due to their ability to improve sample efficiency for policy learning. However, a…
Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
Xinran Li, Xiaolu Wang, Chenjia Bai +1
In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performanc…
VLP: Vision-Language Preference Learning for Embodied Manipulation
Runze Liu, Chenjia Bai, Jiafei Lyu +3
Reward engineering is one of the key challenges in Reinforcement Learning (RL). Preference-based RL effectively addresses this issue by learning from human feedback. However, it is…
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Jiafei Lyu, Kang Xu, Jiacheng Xu +6
We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-…
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
Yang Zhang, Chenjia Bai, Bin Zhao +3
Learning a world model for model-free Reinforcement Learning (RL) agents can significantly improve the sample efficiency by learning policies in imagination. However, building a wo…
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation
Junjie Zhang, Chenjia Bai, Haoran He +5
Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and…
Cross-Domain Policy Adaptation by Capturing Representation Mismatch
Jiafei Lyu, Chenjia Bai, Jingwen Yang +2
It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics…