2 citations · 2 across the 12 of their papers we have counts for
14 papers
DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement Learning
Ruslan Ageev, Huaze Tang, Runqing Miao +2
Expressive flow policies can represent multiple high-value actions, but sampling them with few integration steps while retaining tractable action densities remains challenging. We…
CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection
Qingyue Zhang, Huaze Tang, Minyu Zhang +3
In-context learning (ICL) allows large language models to use demonstrations without updating their parameters. For interactive agents, demonstrations are trajectories of reasoning…
Revealing Safety-Critical Scenarios for UTM via Transformer
Huaze Tang, Bill Zeng, Chao Wang +3
Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which canno…
Process Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement Learning in LLM Reasoners
Chao Wang, Hongtao Tian, Tao Yang +3
Dense process supervision supplies local feedback but leaves open how that feedback should become a policy advantage. We introduce PASS (Process Advantage Signal Shaping), an advan…
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
Yuhao Wu, Yitian Liu, Weijie Shen +13
Vision-Language-Action (VLA) models have established a powerful paradigm for generalist robotic manipulation by grounding control into the semantic reasoning of VLMs. Prevailing ar…
Lightweight and Generalizable Multi-Sensor Human Activity Recognition via Cascaded Fusion and Style-Augmented Decomposition
Wang Chenglong, Zhuo Yan, Ding Wenbo +1
Wearable Human Activity Recognition (WHAR) is a prominent research area within ubiquitous computing, whose core lies in effectively modeling intra- and inter-sensor spatio-temporal…
RUMAD: Reinforcement-Unifying Multi-Agent Debate
Chao Wang, Han Lin, Huaze Tang +2
Multi-agent debate (MAD) systems leverage collective intelligence to enhance reasoning capabilities, yet existing approaches struggle to simultaneously optimize accuracy, consensus…
ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
Yuanbo Tang, Huaze Tang, Tingyu Cao +6
Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive load and streamli…
Function-Space Empirical Bayes Regularisation with Large Vision-Language Model Priors
Pengcheng Hao, Huaze Tang, Ercan Engin Kuruoglu +1
Bayesian deep learning (BDL) provides a principled framework for reliable uncertainty quantification by combining deep neural networks with Bayesian inference. A central challenge…
E^2-LLM: Bridging Neural Signals and Interpretable Affective Analysis
Fei Ma, Han Lin, Yifan Xie +4
Emotion recognition from electroencephalography (EEG) signals remains challenging due to high inter-subject variability, limited labeled data, and the lack of interpretable reasoni…
Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization
Chao Wang, Tao Yang, Hongtao Tian +5
Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abun…
SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Yixian Zhang, Shu'ang Yu, Tonghe Zhang +6
Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We tra…
Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
Yixian Zhang, Huaze Tang, Changxu Wei +1
The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) diverge…
Policy Newton Algorithm in Reproducing Kernel Hilbert Space
Yixian Zhang, Huaze Tang, Chao Wang +1
Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods l…