Related papers: Auto-ART: Structured Literature Synthesis and Auto…

Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt…

When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks…

Recently, adversarial training has been incorporated in self-supervised contrastive pre-training to augment label efficiency with exciting adversarial robustness. However, the robustness came at a cost of expensive adversarial training. In…

Evaluating statement autoformalization, translating natural language mathematics into formal languages like Lean 4, remains a significant challenge, with few metrics, datasets, and standards to robustly measure progress. In this work, we…

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…

Vision--Language Models (VLMs) show significant promise for Medical Visual Question Answering (VQA), yet their deployment in clinical settings is hindered by severe vulnerability to adversarial attacks. Standard adversarial training, while…

Challenges have become the state-of-the-art approach to benchmark image analysis algorithms in a comparative manner. While the validation on identical data sets was a great step forward, results analysis is often restricted to pure ranking…

Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model…

In this work, we propose a robust framework that employs adversarially robust training to safeguard the ML models against perturbed testing data. Our contributions can be seen from both computational and statistical perspectives. Firstly,…

Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchmark of…

A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open problem. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and…

Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution,…

Automated essay scoring (AES) research often relies on rank-based correlation metrics to validate analytic assessment. However, such metrics obscure both intrinsic intercorrelations among analytic dimensions that arise from the structure of…

The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluations are susceptible to stylistic biases, and…

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

The recent surge of building software systems powered by Large Language Models (LLMs) has led to the development of various testing frameworks, primarily focused on treating prompt templates as the unit of testing. Despite the significant…

A small but growing body of work has shown that machine learning models which better align with human vision have also exhibited higher robustness to adversarial examples, raising the question: can human-like perception make models more…

The exponential growth of scientific literature poses unprecedented challenges for researchers attempting to synthesize knowledge across rapidly evolving fields. We present \textbf{Agentic AutoSurvey}, a multi-agent framework for automated…

Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models. However, there are two issues for the existing methods. First, instances from the…