arXiv:2511.16541v2 Announce Type: replace-cross Abstract: The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem is compounded by the accelerated release cycle of novel generative models, which renders traditional detection approaches (reliant on periodic retraining) […]
The Coding Limits of Robust Watermarking for Generative Models
arXiv:2509.10577v2 Announce Type: replace-cross Abstract: We ask a basic question about cryptographic watermarking for generative models: to what extent can a watermark remain reliable when an adversary is allowed to corrupt the encoded signal? To study this question, we introduce a minimal coding abstraction that we call a zero-bit tamper-detection code. This is a secret-key […]
InTAct: Interval-based Task Activation Consolidation for Continual Learning
arXiv:2511.17439v1 Announce Type: cross Abstract: Continual learning aims to enable neural networks to acquire new knowledge without forgetting previously learned information. While recent prompt-based methods perform strongly in class-incremental settings, they remain vulnerable under domain shifts, where the input distribution changes but the label space remains fixed. This exposes a persistent problem known as representation […]
Value of Information-Enhanced Exploration in Bootstrapped DQN
arXiv:2511.02969v2 Announce Type: replace-cross Abstract: Efficient exploration in deep reinforcement learning remains a fundamental challenge, especially in environments characterized by high-dimensional states and sparse rewards. Traditional exploration strategies that rely on random local policy noise, such as $epsilon$-greedy and Boltzmann exploration methods, often struggle to efficiently balance exploration and exploitation. In this paper, we integrate […]
From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
arXiv:2509.06938v2 Announce Type: replace-cross Abstract: As generative AI systems become competent and democratized in science, business, and government, deeper insight into their failure modes now poses an acute need. The occasional volatility in their behavior, such as the propensity of transformer models to hallucinate, impedes trust and adoption of emerging AI solutions in high-stakes areas. […]
Generative AI and Power Imbalances in Global Education: Frameworks for Bias Mitigation
arXiv:2406.02966v4 Announce Type: replace-cross Abstract: This study examines how Generative Artificial Intelligence reproduces global power hierarchies in education and proposes a framework to address resulting inequities. Using a critical qualitative design, the study conducted zero-shot prompt testing with two leading systems, ChatGPT-4 Turbo and Gemini 1.5, and collected real-time outputs from Global North and South […]
Lost in Translation and Noise: A Deep Dive into the Failure Modes of VLMs on Real-World Tables
arXiv:2511.17238v1 Announce Type: cross Abstract: The impressive performance of VLMs is largely measured on benchmarks that fail to capture the complexities of real-world scenarios. Existing datasets for tabular QA, such as WikiTableQuestions and FinQA, are overwhelmingly monolingual (English) and present tables in a digitally perfect, clean format. This creates a significant gap between research and […]
Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
arXiv:2505.10297v2 Announce Type: replace-cross Abstract: Federated learning (FL) remains highly vulnerable to adaptive backdoor attacks that preserve stealth by closely imitating benign update statistics. Existing defenses predominantly rely on anomaly detection in parameter or gradient space, overlooking behavioral constraints that backdoor attacks must satisfy to ensure reliable trigger activation. These anomaly-centric methods fail against adaptive […]
Approximating a gene regulatory network from non-sequential data
arXiv:2401.11858v3 Announce Type: replace Abstract: Given non-sequential snapshots from instances of a dynamical system, we design a compressed sensing based algorithm that reconstructs the dynamical system. On the theoretical side, we show that: (1) successful reconstruction is possible under the assumption that we can construct an approximate clock from a subset of the coordinates of […]
How LLMs Learn to Reason: A Complex Network Perspective
arXiv:2509.23629v2 Announce Type: replace Abstract: Training large language models with Reinforcement Learning with Verifiable Rewards (RLVR) exhibits a set of distinctive and puzzling behaviors that remain poorly understood, including a two-stage learning curve, a V-shaped response-length trajectory, and a pronounced vulnerability to catastrophic forgetting. In this work, we propose that these behaviors are emergent collective […]
A Reinforcement Learning-Based Telematic Routing Protocol for the Internet of Underwater Things
arXiv:2506.00133v2 Announce Type: replace-cross Abstract: The Internet of Underwater Things (IoUT) has a lot of problems, like low bandwidth, high latency, mobility, and not enough energy. Routing protocols that were made for land-based networks, like RPL, don’t work well in these underwater settings. This paper talks about RL-RPL-UA, a new routing protocol that uses reinforcement […]
Model Inversion Attack Against Deep Hashing
arXiv:2511.12233v2 Announce Type: replace-cross Abstract: Deep hashing improves retrieval efficiency through compact binary codes, yet it introduces severe and often overlooked privacy risks. The ability to reconstruct original training data from hash codes could lead to serious threats such as biometric forgery and privacy breaches. However, model inversion attacks specifically targeting deep hashing models remain […]