arXiv subjects

Fei Miao

Publications and source records attributed to Fei Miao.

At least 19 recordsLinked to original sources

arXiv2026

Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models

Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in scene layout, lighting, or nearby distractors. We trace this brittleness to \textit{shortcut learning}: fine-tuning supervises actions but not the visual evidence the policy uses, so the policy can settle on scene-level correlations that predict the demonstrations without causing success. We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module that takes the same vision and language inputs as existing Vision-Language-Action and World Action Model pipelines and predicts task-conditioned masks over the relevant objects, the robot, and other action-critical regions. During fine-tuning the masks serve as an auxiliary grounding signal that aligns the policy's visual attention with task-relevant regions; the policy architecture is unchanged, and at inference the policy runs on the original observation stream with no AFP call in the control loop. In simulation with four robotic foundation models and on a real robot with $\pi_{0.5}$, AFP improves generalization under environmental perturbations, reduces overfitting, and shortens fine-tuning. Ablations over mask quality and grounding-loss design show that these gains come from directing policy learning toward task-relevant visual evidence. Code, data, and videos are available at https://apollo-lab-yale.github.io/26-CoRL-AFP-website/.

cs.RO↗

arXiv2026

Open-World Video Segmentation

While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support object discovery and identity maintenance in long videos of dynamic ego-motion, and (2) existing evaluation protocols rely on a rigid 1:1 matching that unfairly penalizes semantically valid predictions with mismatched granularity. To address both gaps, we introduce Savvy, a practical and strong system for zero-shot open-world long-horizon video segmentation. Savvy combines hierarchical mask discovery, deferred admission, and track consolidation to support persistent object discovery, safe track promotion, and stable long-range identity maintenance. We further propose OGA, a granularity-aware evaluation suite for open-world video segmentation. Built on a Granularity-Agnostic (GA) matching protocol, OGA relaxes conventional 1:1 matching to an n:1 mapping, but still enforces temporal rigor by detecting support discontinuities through sever points and scoring each reference object through its dominant coherent fragment. This prevents fragmented or flickering support from being over-rewarded while enabling GA-adapted metrics and structural diagnostics: identity persistence (IP), and identity concentration (IC). On VIPSeg, we show that standard 1:1 evaluation substantially underestimates open-world methods, whereas GA evaluation recovers much of their suppressed performance. On the more realistic long-horizon benchmarks: ScanNet and HM3D, Savvy consistently outperforms strong baselines across both classical and proposed metrics, including STQ, VPQ$_\infty$, IP and IC. Together, these results establish a practical benchmark and a strong baseline for open-world long-horizon video segmentation.

cs.CV↗

arXiv2026

SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection

Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside the training environment. Existing evaluations, including the original ACT and SmolVLA benchmarks, demonstrate high success rates under controlled, fixed backgrounds, yet community practitioners report near-zero transfer to new environments. We present SEVO (Semantic-Enhanced Virtual Observation), a data-centric approach that improves cross-environment manipulation robustness without modifying the policy architecture. SEVO transforms the raw RGB camera stream through three mechanisms: (1) body-fixed cameras whose combined fields of view cover the full manipulation workspace, (2) active red-spectrum illumination that physically normalizes object appearance, and (3) real-time YOLO segmentation overlay that provides a background-invariant semantic cue. Critically, we show that a diversified data collection protocol (systematically varying lighting, backgrounds, and distractors during teleoperation) is the single most important factor for generalization. We target transparent water bottles, objects that visually blend with their surroundings, and select a simple pick-and-place task to enable hundreds of controlled real-robot trials across two mobile platforms. The full pipeline achieves 95% grasp success with ACT and 83% with SmolVLA in the training environment, transferring to novel environments at 85% and 75%. Without SEVO, the same policies achieve only 75%/70% in training and collapse to 30-35% in novel environments. Our results demonstrate that principled observation design and environmental diversity during data collection, not model scaling, enable low-cost robots to operate reliably in everyday household environments.

cs.RO↗

arXiv2026

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. We evaluate our method across different off-policy RL algorithms, including SAC and FastTD3 based on different network architectures. Empirically, LoRA efficiently reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

cs.LG↗

arXiv2026

TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs

Multimodal large language models (MLLMs) typically rely on a single late-layer feature from a frozen vision encoder, leaving the encoder's rich hierarchy of visual cues under-utilized. MLLMs still suffer from visually ungrounded hallucinations, often relying on language priors rather than image evidence. While many prior mitigation strategies operate on the text side, they leave the visual representation unchanged and do not exploit the rich hierarchy of features encoded across vision layers. Existing multi-layer fusion methods partially address this limitation but remain static, applying the same layer mixture regardless of the query. In this work, we introduce TGIF (Text-Guided Inter-layer Fusion), a lightweight module that treats encoder layers as depth-wise "experts" and predicts a prompt-dependent fusion of visual features. TGIF follows the principle of direct external fusion, requires no vision-encoder updates, and adds minimal overhead. Integrated into LLaVA-1.5-7B, TGIF provides consistent improvements across hallucination, OCR, and VQA benchmarks, while preserving or improving performance on ScienceQA, GQA, and MMBench. These results suggest that query-conditioned, hierarchy-aware fusion is an effective way to strengthen visual grounding and reduce hallucination in modern MLLMs. Code: https://github.com/Linchenchen/TGIF.

cs.CV↗

arXiv2025

LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.

cs.CL↗

arXiv2025

Robust and Safe Multi-Agent Reinforcement Learning with Communication for Autonomous Vehicles: From Simulation to Hardware

Deep multi-agent reinforcement learning (MARL) has been demonstrated effectively in simulations for multi-robot problems. For autonomous vehicles, the development of vehicle-to-vehicle (V2V) communication technologies provide opportunities to further enhance system safety. However, zero-shot transfer of simulator-trained MARL policies to dynamic hardware systems remains challenging, and how to leverage communication and shared information for MARL has limited demonstrations on hardware. This problem is challenged by discrepancies between simulated and physical states, system state and model uncertainties, practical shared information design, and the need for safety guarantees in both simulation and hardware. This paper designs RSR-RSMARL, a novel Robust and Safe MARL framework that supports Real-Sim-Real (RSR) policy adaptation for multi-agent systems with communication among agents, with both simulation and hardware demonstrations. RSR-RSMARL leverages state (includes shared state information among agents) and action representations considering real system complexities for MARL formulation. The MARL policy is trained with robust MARL algorithm to enable zero-shot transfer to hardware considering the sim-to-real gap. A safety shield module using Control Barrier Functions (CBFs) provides safety guarantee for each individual agent. Experimental results on 1/10th-scale autonomous vehicles with V2V communication demonstrate the ability of RSR-RSMARL framework to enhance driving safety and coordination across multiple configurations. These findings emphasize the importance of jointly designing robust policy representations and modular safety architectures to enable scalable, generalizable RSR transfer in multi-agent autonomy.

cs.RO↗

arXiv2025

CUQDS: Conformal Uncertainty Quantification under Distribution Shift for Trajectory Prediction

Trajectory prediction models that can infer both finite future trajectories and their associated uncertainties of the target vehicles in an online setting (e.g., real-world application scenarios) is crucial for ensuring the safe and robust navigation and path planning of autonomous vehicle motion. However, the majority of existing trajectory prediction models have neither considered reducing the uncertainty as one objective during the training stage nor provided reliable uncertainty quantification during inference stage under potential distribution shift. Therefore, in this paper, we propose the Conformal Uncertainty Quantification under Distribution Shift framework, CUQDS, to quantify the uncertainty of the predicted trajectories of existing trajectory prediction models under potential data distribution shift, while considering improving the prediction accuracy of the models and reducing the estimated uncertainty during the training stage. Specifically, CUQDS includes 1) a learning-based Gaussian process regression module that models the output distribution of the base model (any existing trajectory prediction or time series forecasting neural networks) and reduces the estimated uncertainty by additional loss term, and 2) a statistical-based Conformal P control module to calibrate the estimated uncertainty from the Gaussian process regression module in an online setting under potential distribution shift between training and testing data.

cs.LG↗

arXiv2025

Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks

Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial attacks pose a potential threat to the deep learning COD models, and introduce high output uncertainty. With unknown attack models, it becomes even more challenging to improve COD resiliency and quantify the output uncertainty for highly dynamic perception scenes such as autonomous vehicles. In this study, we propose the Trusted Uncertainty Quantification in Collaborative Perception framework (TUQCP). TUQCP leverages both adversarial training and uncertainty quantification techniques to enhance the adversarial robustness of existing COD models. More specifically, TUQCP first adds perturbations to the shared information of randomly selected agents during object detection collaboration by adversarial training. TUQCP then alleviates the impacts of adversarial attacks by providing output uncertainty estimation through learning-based module and uncertainty calibration through conformal prediction. Our framework works for early and intermediate collaboration COD models and single-agent object detection models. We evaluate TUQCP on V2X-Sim, a comprehensive collaborative perception dataset for autonomous driving, and demonstrate a 80.41% improvement in object detection accuracy compared to the baselines under the same adversarial attacks. TUQCP demonstrates the importance of uncertainty quantification to COD under adversarial attacks.

cs.CV↗

arXiv2025

$α$-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction

In the realm of autonomous vehicle perception, comprehending 3D scenes is paramount for tasks such as planning and mapping. Camera-based 3D Semantic Occupancy Prediction (OCC) aims to infer scene geometry and semantics from limited observations. While it has gained popularity due to affordability and rich visual cues, existing methods often neglect the inherent uncertainty in models. To address this, we propose an uncertainty-aware OCC method ($α$-OCC). We first introduce Depth-UP, an uncertainty propagation framework that improves geometry completion by up to 11.58\% and semantic segmentation by up to 12.95\% across various OCC models. For uncertainty quantification (UQ), we propose the hierarchical conformal prediction (HCP) method, effectively handling the high-level class imbalance in OCC datasets. On the geometry level, the novel KL-based score function significantly improves the occupied recall (45\%) of safety-critical classes with minimal performance overhead (3.4\% reduction). On UQ, our HCP achieves smaller prediction set sizes while maintaining the defined coverage guarantee. Compared with baselines, it reduces up to 92\% set size, with 18\% further reduction when integrated with Depth-UP. Our contributions advance OCC accuracy and robustness, marking a noteworthy step forward in autonomous perception systems.

cs.CV↗

arXiv2025

Solving Constrained Optimization Problems Using Hybrid Qubit-Qumode Quantum Devices

Variational Quantum Algorithms (VQAs) provide a promising framework for tackling complex optimization problems on near-term quantum hardware. Here, we demonstrate that hybrid qubit--qumode quantum devices offer an efficient route to solving Quadratic Unconstrained Binary Optimization (QUBO) problems using the Echoed Conditional Displacement Variational Quantum Eigensolver (ECD-VQE). Leveraging circuit quantum electrodynamics (cQED) architectures, we encode QUBO instances across multiple qumodes weakly coupled to a single qubit and extract binary solutions directly from photon-number measurements. We apply ECD-VQE to the Binary Knapsack Problem and show that it outperforms the Quantum Approximate Optimization Algorithm (QAOA) implemented on conventional qubit circuits, achieving higher-quality solutions with dramatically fewer resources. We also demonstrate that ECD-VQE can be extended to chemically motivated tasks such as active-space selection for multireference electronic structure methods. These results highlight the utility of hybrid qubit-qumode platforms for a broad class of NP-hard and chemistry-related optimization problems, and demonstrate that variational ECD ansatz can realize expressive state preparation with significantly shallower circuits than qubit-only architectures, positioning qubit-qumode gates as compelling candidates for constrained optimization in early fault-tolerant quantum computing.

quant-ph↗

arXiv2024

YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning

Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for some game environments. Recently, large language models (LLMs) have demonstrated emergent reasoning capabilities, making them promising candidates for enhancing coordination among the agents. However, due to the model size of LLMs, it can be expensive to frequently infer LLMs for actions that agents can take. In this work, we propose You Only LLM Once for MARL (YOLO-MARL), a novel framework that leverages the high-level task planning capabilities of LLMs to improve the policy learning process of multi-agents in cooperative games. Notably, for each game environment, YOLO-MARL only requires one time interaction with LLMs in the proposed strategy generation, state interpretation and planning function generation modules, before the MARL policy training process. This avoids the ongoing costs and computational time associated with frequent LLMs API calls during training. Moreover, trained decentralized policies based on normal-sized neural networks operate independently of the LLM. We evaluate our method across two different environments and demonstrate that YOLO-MARL outperforms traditional MARL algorithms.

cs.MA↗

arXiv2024

Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles

We address the problem of coordination and control of Connected and Automated Vehicles (CAVs) in the presence of imperfect observations in mixed traffic environment. A commonly used approach is learning-based decision-making, such as reinforcement learning (RL). However, most existing safe RL methods suffer from two limitations: (i) they assume accurate state information, and (ii) safety is generally defined over the expectation of the trajectories. It remains challenging to design optimal coordination between multi-agents while ensuring hard safety constraints under system state uncertainties (e.g., those that arise from noisy sensor measurements, communication, or state estimation methods) at every time step. We propose a safety guaranteed hierarchical coordination and control scheme called Safe-RMM to address the challenge. Specifically, the high-level coordination policy of CAVs in mixed traffic environment is trained by the Robust Multi-Agent Proximal Policy Optimization (RMAPPO) method. Though trained without uncertainty, our method leverages a worst-case Q network to ensure the model's robust performances when state uncertainties are present during testing. The low-level controller is implemented using model predictive control (MPC) with robust Control Barrier Functions (CBFs) to guarantee safety through their forward invariance property. We compare our method with baselines in different road networks in the CARLA simulator. Results show that our method provides best evaluated safety and efficiency in challenging mixed traffic environments with uncertainties.

cs.RO↗

arXiv2024

Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments

We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or ``similar" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity. Furthermore, by incorporating the benefits of variance-reduction techniques or Hessian approximation, both algorithms achieve state-of-the-art convergence results, characterized by a sample complexity of $\mathcal{O}\left(ε^{-\frac{3}{2}}/N\right)$. Notably, our algorithms enjoy linear convergence speedups with respect to the number of agents, highlighting the benefit of collaboration among agents in finding a common policy.

cs.LG↗

arXiv2024

Constrained Reinforcement Learning Under Model Mismatch

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied during training because there might be model mismatch between the training and real environments. To address the above challenge, we formulate the problem as constrained RL under model uncertainty, where the goal is to learn a good policy that optimizes the reward and at the same time satisfy the constraint under model mismatch. We develop a Robust Constrained Policy Optimization (RCPO) algorithm, which is the first algorithm that applies to large/continuous state space and has theoretical guarantees on worst-case reward improvement and constraint violation at each iteration during the training. We demonstrate the effectiveness of our algorithm on a set of RL tasks with constraints.

cs.LG↗

arXiv2024

What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?

Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are susceptible to adversarial state perturbation attacks. In this work, we propose a State-Adversarial Markov Game (SAMG) and make the first attempt to investigate different solution concepts of MARL under state uncertainties. Our analysis shows that the commonly used solution concepts of optimal agent policy and robust Nash equilibrium do not always exist in SAMGs. To circumvent this difficulty, we consider a new solution concept called robust agent policy, where agents aim to maximize the worst-case expected state value. We prove the existence of robust agent policy for finite state and finite action SAMGs. Additionally, we propose a Robust Multi-Agent Adversarial Actor-Critic (RMA3C) algorithm to learn robust policies for MARL agents under state uncertainties. Our experiments demonstrate that our algorithm outperforms existing methods when faced with state perturbations and greatly improves the robustness of MARL policies. Our code is public on https://songyanghan.github.io/what_is_solution/.

cs.AI↗

arXiv2024

Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation

Object detection and multiple object tracking (MOT) are essential components of self-driving systems. Accurate detection and uncertainty quantification are both critical for onboard modules, such as perception, prediction, and planning, to improve the safety and robustness of autonomous vehicles. Collaborative object detection (COD) has been proposed to improve detection accuracy and reduce uncertainty by leveraging the viewpoints of multiple agents. However, little attention has been paid to how to leverage the uncertainty quantification from COD to enhance MOT performance. In this paper, as the first attempt to address this challenge, we design an uncertainty propagation framework called MOT-CUP. Our framework first quantifies the uncertainty of COD through direct modeling and conformal prediction, and propagates this uncertainty information into the motion prediction and association steps. MOT-CUP is designed to work with different collaborative object detectors and baseline MOT algorithms. We evaluate MOT-CUP on V2X-Sim, a comprehensive collaborative perception dataset, and demonstrate a 2% improvement in accuracy and a 2.67X reduction in uncertainty compared to the baselines, e.g. SORT and ByteTrack. In scenarios characterized by high occlusion levels, our MOT-CUP demonstrates a noteworthy $4.01\%$ improvement in accuracy. MOT-CUP demonstrates the importance of uncertainty quantification in both COD and MOT, and provides the first attempt to improve the accuracy and reduce the uncertainty in MOT based on COD through uncertainty propagation. Our code is public on https://coperception.github.io/MOT-CUP/.

cs.CV↗

arXiv2023

Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications

Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due to their expressiveness and flexibility to define the reward and requirements for different states and actions of the agent. However, how to leverage Signal Temporal Logic (STL) to guide multi-agent reinforcement learning reward design remains unexplored. Complex interactions, heterogeneous goals and critical safety requirements in multi-agent systems make this problem even more challenging. In this paper, we propose a novel STL-guided multi-agent reinforcement learning framework. The STL requirements are designed to include both task specifications according to the objective of each agent and safety specifications, and the robustness values of the STL specifications are leveraged to generate rewards. We validate the advantages of our method through empirical studies. The experimental results demonstrate significant reward performance improvements compared to MARL without STL guidance, along with a remarkable increase in the overall safety rate of the multi-agent systems.

cs.AI↗