Wu Zhang

Jinpeng Chen, Cheng Gong, Hanbo Li et al.

Developing multi-turn interactive tool-use agents is challenging because real-world user needs are often complex and ambiguous, yet agents must execute deterministic actions to satisfy them. To address this gap, we introduce \textbf{CoVe} (\textbf{Co}nstraint-\textbf{Ve}rification), a post-training data synthesis framework designed for training interactive tool-use agents while ensuring both data complexity and correctness. CoVe begins by defining explicit task constraints, which serve a dual role: they guide the generation of complex trajectories and act as deterministic verifiers for assessing trajectory quality. This enables the creation of high-quality training trajectories for supervised fine-tuning (SFT) and the derivation of accurate reward signals for reinforcement learning (RL). Our evaluation on the challenging $τ^2$-bench benchmark demonstrates the effectiveness of the framework. Notably, our compact \textbf{CoVe-4B} model achieves success rates of 43.0\% and 59.4\% in the Airline and Retail domains, respectively; its overall performance significantly outperforms strong baselines of similar scale and remains competitive with models up to $17\times$ its size. These results indicate that CoVe provides an effective and efficient pathway for synthesizing training data for state-of-the-art interactive tool-use agents. To support future research, we open-source our code, trained model, and the full set of 12K high-quality trajectories used for training.

Xifeng Yao, Dongyu Lang, Wu Zhang et al.

Significant advancements have been made in the capabilities of code large language models, leading to their rapid adoption and application across a wide range of domains. However, their further advancements are often constrained by the scarcity of real-world coding problems. To bridge this gap, we propose a novel framework for synthesizing code problems that emulate authentic real-world scenarios. This framework systematically integrates domain knowledge, domain skills, and coding skills, all of which are meticulously extracted from real-world programming-related datasets, including Stack Overflow and Kaggle. The extracted elements serve as the foundational building blocks for constructing code problems. To align the generated problems with practical applications, application scenarios are also mined from the aforementioned datasets. These scenarios are then utilized to construct a scenario-centric graph that interconnects domain knowledge, domain skills, and coding skills. Based on this structured representation, a sampling strategy on the graph is designed, which effectively controls the generation of a code problem with complexity and diversity, reflects real-world challenges. Experimental results demonstrate that the proposed method consistently achieves superior performance over state-of-the-art open-source large language models of varying sizes and functionalities, including both coders and general-purpose models, across a diverse set of real-world benchmarks.

Wu Zhang

In this paper, we introduce a divide-and-conquer algorithm to improve sentence alignment speed. We utilize external bilingual sentence embeddings to find accurate hard delimiters for the parallel texts to be aligned. We use Monte Carlo simulation to show experimentally that using this divide-and-conquer algorithm, we can turn any quadratic time complexity sentence alignment algorithm into an algorithm with average time complexity of O(NlogN). On a standard OCR-generated dataset, our method improves the Bleualign baseline by 3 F1 points. Besides, when computational resources are restricted, our algorithm is faster than Vecalign in practice.

Yexin Duan, Junhua Zou, Xingyu Zhou et al.

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable adversarial examples under the black-box setting. To this end, this paper proposes to improve the transferability of adversarial examples, and applies dual-stage feature-level perturbations to an existing model to implicitly create a set of diverse models. Then these models are fused by the longitudinal ensemble during the iterations. The proposed method is termed Dual-Stage Network Erosion (DSNE). We conduct comprehensive experiments both on non-residual and residual networks, and obtain more transferable adversarial examples with the computational cost similar to the state-of-the-art method. In particular, for the residual networks, the transferability of the adversarial examples can be significantly improved by biasing the residual block information to the skip connections. Our work provides new insights into the architectural vulnerability of neural networks and presents new challenges to the robustness of neural networks.

Yexin Duan, Jialin Chen, Xingyu Zhou et al.

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object tends to suffer from an inevitable reduction in attack performance as the viewpoint changes. To remedy this issue, this work proposes the Coated Adversarial Camouflage (CAC) to attack the detectors in arbitrary viewpoints. Unlike the patch trained in the 2D space, our camouflage generated by a conceptually different training framework consists of 3D rendering and dense proposals attack. Specifically, we make the camouflage perform 3D spatial transformations according to the pose changes of the object. Based on the multi-view rendering results, the top-n proposals of the region proposal network are fixed, and all the classifications in the fixed dense proposals are attacked simultaneously to output errors. In addition, we build a virtual 3D scene to fairly and reproducibly evaluate different attacks. Extensive experiments demonstrate the superiority of CAC over the existing attacks, and it shows impressive performance both in the virtual scene and the real world. This poses a potential threat to the security-critical computer vision systems.

Guannan Hu, Wu Zhang, Hu Ding et al.

Catastrophic forgetting in continual learning is a common destructive phenomenon in gradient-based neural networks that learn sequential tasks, and it is much different from forgetting in humans, who can learn and accumulate knowledge throughout their whole lives. Catastrophic forgetting is the fatal shortcoming of a large decrease in performance on previous tasks when the model is learning a novel task. To alleviate this problem, the model should have the capacity to learn new knowledge and preserve learned knowledge. We propose an average gradient episodic memory (A-GEM) with a soft constraint $ε\in [0, 1]$, which is a balance factor between learning new knowledge and preserving learned knowledge; our method is called gradient episodic memory with a soft constraint $ε$ ($ε$-SOFT-GEM). $ε$-SOFT-GEM outperforms A-GEM and several continual learning benchmarks in a single training epoch; additionally, it has state-of-the-art average accuracy and efficiency for computation and memory, like A-GEM, and provides a better trade-off between the stability of preserving learned knowledge and the plasticity of learning new knowledge.

Junhua Zou, Yexin Duan, Boyu Li et al.

Fast gradient sign attack series are popular methods that are used to generate adversarial examples. However, most of the approaches based on fast gradient sign attack series cannot balance the indistinguishability and transferability due to the limitations of the basic sign structure. To address this problem, we propose a method, called Adam Iterative Fast Gradient Tanh Method (AI-FGTM), to generate indistinguishable adversarial examples with high transferability. Besides, smaller kernels and dynamic step size are also applied to generate adversarial examples for further increasing the attack success rates. Extensive experiments on an ImageNet-compatible dataset show that our method generates more indistinguishable adversarial examples and achieves higher attack success rates without extra running time and resource. Our best transfer-based attack NI-TI-DI-AITM can fool six classic defense models with an average success rate of 89.3% and three advanced defense models with an average success rate of 82.7%, which are higher than the state-of-the-art gradient-based attacks. Additionally, our method can also reduce nearly 20% mean perturbation. We expect that our method will serve as a new baseline for generating adversarial examples with better transferability and indistinguishability.