arXiv subjects

Longfei Zhang

Publications and source records attributed to Longfei Zhang.

10 recordsLinked to original sources

arXiv2026

PERO: Efficient Robust Post-Training Foundation Models for Encrypted Traffic Classification

Encrypted traffic classification is vital for network security, yet real-world deployments are inherently sensitive to rare but high-loss errors such as misclassification of malicious traffic. The encrypted traffic foundation model, as a promising general-purpose technique, can achieve impressive overall performance. However, employing standard objectives such as empirical risk minimization often overlooks high-risk tail events, and commonly used performance metrics hardly reflect robustness limitations in risk-sensitive scenarios. Directly applying robust optimization objectives, such as conditional value-at-risk, to post-training is computationally prohibitive for large models, as identifying high-loss samples exhausts substantial computation. To this end, we propose Pre-Evaluation Robust Optimization (PERO), an efficient robust post-training framework for encrypted traffic foundation models. PERO employs a lightweight proxy to estimate sample-wise risk and selects a subset of high-risk samples to update the foundation model, decoupling risk estimation from expensive large-model optimization. Extensive experiments on typical encrypted traffic datasets show that PERO achieves competitive or superior robustness and average performance compared to outstanding robust post-training methods, while significantly reducing computational and memory costs.

cs.LG↗

arXiv2026

Knowledge-guided Disentanglement with Atomic Actions for Action Recognition

Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are insufficient for capturing subtle interactions and fine-grained semantics. While recent prompt-based approaches introduce disentanglement, they lack explicit semantic guidance, and methods based solely on visual or structured cues remain coarse-grained. In this paper, we propose Knowledge-guided Disentanglement with Atomic Actions (KDA), which leverages fine-grained semantic knowledge to enhance action representations and enable more precise disentanglement. Specifically, we use Large Language Models (LLMs) to decompose action labels into atomic actions, providing explicit spatial-temporal semantics. A Knowledge Injection Module (KIM) first integrates atomic action knowledge into video features. Based on this enhanced representation, a Knowledge Disentanglement Module (KDM) further disentangles atomic action knowledge to produce more precise semantic guidance for action disentanglement. A Knowledge Disentanglement Loss (KD Loss) is introduced to encourage clearer disentanglement of knowledge components within KDM. Extensive experiments demonstrate that KDA improves feature discriminability and achieves state-of-the-art performance on multi-label action recognition benchmarks. Moreover, KIM and KDM can be readily integrated into other methods, demonstrating strong generality.

cs.CV↗

arXiv2026

Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization

Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which constrains the policy from capturing multimodal distributions, making it difficult to cover the full range of optimal solutions in multi-solution problems, and the return is reduced to a mean value, losing its multimodal nature and thus providing insufficient guidance for policy updates. In response to these problems, we propose a RL algorithm termed flow-based policy with distributional RL (FP-DRL). This algorithm models the policy using flow matching, which offers both computational efficiency and the capacity to fit complex distributions. Additionally, it employs a distributional RL approach to model and optimize the entire return distribution, thereby more effectively guiding multimodal policy updates and improving agent performance. Experimental trails on MuJoCo benchmarks demonstrate that the FP-DRL algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting superior representation capability of the flow policy.

cs.LG↗

arXiv2026

FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation

Imputing missing node features in graphs is challenging, particularly under high missing rates. Existing methods based on latent representations or global diffusion often fail to produce reliable estimates, and may propagate errors across the graph. We propose FSD-CAP, a two-stage framework designed to improve imputation quality under extreme sparsity. In the first stage, a graph-distance-guided subgraph expansion localizes the diffusion process. A fractional diffusion operator adjusts propagation sharpness based on local structure. In the second stage, imputed features are refined using class-aware propagation, which incorporates pseudo-labels and neighborhood entropy to promote consistency. We evaluated FSD-CAP on multiple datasets. With $99.5\%$ of features missing across five benchmark datasets, FSD-CAP achieves average accuracies of $80.06\%$ (structural) and $81.01\%$ (uniform) in node classification, close to the $81.31\%$ achieved by a standard GCN with full features. For link prediction under the same setting, it reaches AUC scores of $91.65\%$ (structural) and $92.41\%$ (uniform), compared to $95.06\%$ for the fully observed case. Furthermore, FSD-CAP demonstrates superior performance on both large-scale and heterophily datasets when compared to other models.

cs.LG↗

arXiv2026

Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps

We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.

cs.LG↗

arXiv2025

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks in reinforcement learning are based on reward manipulation, which are largely ineffective against the TO model due to its inherent sequence modeling nature. Moreover, the complexities introduced by high-dimensional action spaces further compound the challenge of action manipulation. To address these gaps, we propose TrojanTO, the first action-level backdoor attack against TO models. TrojanTO employs alternating training to enhance the connection between triggers and target actions for attack effectiveness. To improve attack stealth, it utilizes precise poisoning via trajectory filtering for normal performance and batch poisoning for trigger consistency. Extensive evaluations demonstrate that TrojanTO effectively implants backdoor attacks across diverse tasks and attack objectives with a low attack budget (0.3\% of trajectories). Furthermore, TrojanTO exhibits broad applicability to DT, GDT, and DC, underscoring its scalability across diverse TO model architectures.

cs.LG↗

arXiv2024

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is particularly critical in sequential decision-making scenarios where resources are constrained such as in robots and drones with limited computational power. Mamba, a promising new linear-time sequence model, offers performance on par with transformers while delivering substantially fewer parameters on long sequences. As it remains unclear whether Mamba is compatible with trajectory optimization, this work aims to conduct comprehensive experiments to explore the potential of Decision Mamba (dubbed DeMa) in offline RL from the aspect of data structures and essential components with the following insights: (1) Long sequences impose a significant computational burden without contributing to performance improvements since DeMa's focus on sequences diminishes approximately exponentially. Consequently, we introduce a Transformer-like DeMa as opposed to an RNN-like DeMa. (2) For the components of DeMa, we identify the hidden attention mechanism as a critical factor in its success, which can also work well with other residual structures and does not require position embedding. Extensive evaluations demonstrate that our specially designed DeMa is compatible with trajectory optimization and surpasses previous methods, outperforming Decision Transformer (DT) with higher performance while using 30\% fewer parameters in Atari, and exceeding DT with only a quarter of the parameters in MuJoCo.

cs.LG↗

arXiv2022

Reconstructing editable prismatic CAD from rounded voxel models

Reverse Engineering a CAD shape from other representations is an important geometric processing step for many downstream applications. In this work, we introduce a novel neural network architecture to solve this challenging task and approximate a smoothed signed distance function with an editable, constrained, prismatic CAD model. During training, our method reconstructs the input geometry in the voxel space by decomposing the shape into a series of 2D profile images and 1D envelope functions. These can then be recombined in a differentiable way allowing a geometric loss function to be defined. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches to find curves which approximate the profile images, then extrude them and use Boolean operations to build the final CAD model. Our method approximates the target shape more closely than other methods and outputs highly editable constrained parametric sketches which are compatible with existing CAD software.

cs.CV↗

arXiv2021

TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations

Deep reinforcement learning (DRL) has achieved super-human performance on complex video games (e.g., StarCraft II and Dota II). However, current DRL systems still suffer from challenges of multi-agent coordination, sparse rewards, stochastic environments, etc. In seeking to address these challenges, we employ a football video game, e.g., Google Research Football (GRF), as our testbed and develop an end-to-end learning-based AI system (denoted as TiKick) to complete this challenging task. In this work, we first generated a large replay dataset from the self-playing of single-agent experts, which are obtained from league training. We then developed a distributed learning system and new offline algorithms to learn a powerful multi-agent AI from the fixed single-agent dataset. To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios. Extensive experiments further show that our pre-trained model can accelerate the training process of the modern multi-agent algorithm and our method achieves state-of-the-art performances on various academic scenarios.

cs.AI↗

arXiv2021

Inverse design of glass structure with deep graph neural networks

Directly manipulating the atomic structure to achieve a specific property is a long pursuit in the field of materials. However, hindered by the disordered, non-prototypical glass structure and the complex interplay between structure and property, such inverse design is dauntingly hard for glasses. Here, combining two cutting-edge techniques, graph neural networks and swap Monte Carlo, we develop a data-driven, property-oriented inverse design route that managed to improve the plastic resistance of Cu-Zr metallic glasses in a controllable way. Swap Monte Carlo, as "sampler", effectively explores the glass landscape, and graph neural networks, with high regression accuracy in predicting the plastic resistance, serves as "decider" to guide the search in configuration space. Via an unconventional strengthening mechanism, a geometrically ultra-stable yet energetically meta-stable state is unraveled, contrary to the common belief that the higher the energy, the lower the plastic resistance. This demonstrates a vast configuration space that can be easily overlooked by conventional atomistic simulations. The data-driven techniques, structural search methods and optimization algorithms consolidate to form a toolbox, paving a new way to the design of glassy materials.

cond-mat.mtrl-sci↗