8 papers
What Should Robot Policies Learn to Predict? Rethinking Supervision Targets in Vision-Language-Action Learning
Haitao Shen, Hanyu Liu, Yihan Lin +7
Vision-language-action (VLA) policies are typically trained with action prediction as the primary supervision signal, since robots ultimately execute actions. Auxiliary objectives…
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
Cheng Yin, Wang Xu, Junpeng Yang +8
Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in observations from minutes earlier. Existing memory mechanisms…
Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics
Bozhou Chen, Yongyi Wang, Hanyu Liu +2
Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable. Existing studies often attribute i…
HFORD: Hybrid Forward Optimization and Reverse Design Method and Its Applications to On-Chip Millimeter-Wave Inductive Elements
Yuzhen Song, Yifan Wang, Guqiao Chen +5
On-chip inductive elements are pivotal in determining both the silicon footprint and performance of millimeter-wave (mmWave) integrated circuits. However, the layout-level synthesi…
Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
Yongyi Wang, Hanyu Liu, Lingfeng Li +6
Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return…
Liberating LLM Capabilities in Full-Duplex Speech Models
Luoyuan Zhang, Bokai Xu, Junbo Cui +4
Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabili…
Decoupling Return-to-Go for Efficient Decision Transformer
Yongyi Wang, Hanyu Liu, Lingfeng Li +5
The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), u…
Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling
Yongyi Wang, Lingfeng Li, Bozhou Chen +5
Recent benchmarks for memory-augmented reinforcement learning (RL) have introduced partially observable Markov decision process (POMDP) environments in which agents must use histor…