arXiv:2604.26328v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches struggle with robustness against adversarial perturbation, paraphrasing attacks, and domain shifts, often requiring restrictive access to model parameters or large labeled datasets. […]
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
arXiv:2604.26419v1 Announce Type: cross Abstract: Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current models exhibit a weak capacity to refuse queries that exceed their parametric knowledge. In this paper, we propose a systematic framework to enhance the refusal capability of […]
Lifting Embodied World Models for Planning and Control
arXiv:2604.26182v1 Announce Type: cross Abstract: World models of embodied agents predict future observations conditioned on an action taken by the agent. For complex embodiments, action spaces are high-dimensional and difficult to specify: for example, precisely controlling a human agent requires specifying the motion of each joint. This makes the world model hard to control and […]
MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution
arXiv:2604.26244v1 Announce Type: cross Abstract: We study generative super-resolution (SR) in real-world scenarios where content and degradations vary across domains, genres, and segments. For example, images and videos may alternate between text overlays, fast motion, smooth cartoons, and low-light faces, each benefiting from different forms of side information. Existing metadata-guided SR methods typically use a […]
ImproBR: Bug Report Improver Using LLMs
arXiv:2604.26142v1 Announce Type: cross Abstract: Bug tracking systems play a crucial role in software maintenance, yet developers frequently struggle with low-quality user-submitted reports that omit essential details such as Steps to Reproduce (S2R), Observed Behavior (OB), and Expected Behavior (EB). We propose ImproBR, an LLM-based pipeline that automatically detects and improves bug reports by addressing […]
Test-Time Safety Alignment
arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model’s input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. However, this has only been demonstrated for pretrained text-completion models on the relatively simple objective of reducing surface-level profanity in short continuations. A natural […]
Seeking Consensus: Geometric-Semantic On-the-Fly Recalibration for Open-Vocabulary Remote Sensing Semantic Segmentation
arXiv:2604.26221v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) in remote sensing images is a promising task that employs textual descriptions for identifying undefined land cover categories. Despite notable advances, existing methods typically employ a static inference paradigm, overlooking the distinct distribution of each scene, resulting in semantic ambiguity in diverse land covers and incomplete […]
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
arXiv:2604.26274v1 Announce Type: cross Abstract: Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion detection, codename compiles verified benign tool-call telemetry into a parameterized deterministic finite automaton (pDFA). The model defines permitted tool sequences, sequential contexts, and […]
SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection
arXiv:2604.26375v1 Announce Type: cross Abstract: We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way). Since responses frequently exceed the 512-token limit of standard Transformer encoders, we apply an overlapping sliding-window chunking strategy with element-wise Max-Pooling aggregation […]
Culturally Aware GenAI Risks for Youth: Perspectives from Youth, Parents, and Teachers in a Non-Western Context
arXiv:2604.26494v1 Announce Type: cross Abstract: Generative AI tools are widely used by youth and have introduced new privacy and safety challenges. While prior research has explored youth’s safety in GenAI within western context, it often overlooks the cultural, religious, and social dimensions of technology use that strongly shape youths digital experiences in countries like Saudi […]
Fundamental Physics, Existential Risks and Human Futures
arXiv:2604.26530v1 Announce Type: cross Abstract: Over the past 25 years, I have been involved in some intriguing developments in the foundations of physics, exploring the quantum reality problem, the relationship between quantum theory and gravity and the interplay between consciousness and physical laws. These investigations make it plausible that we will find physics beyond quantum […]
TDD Governance for Multi-Agent Code Generation via Prompt Engineering
arXiv:2604.26615v1 Announce Type: cross Abstract: Large language models (LLMs) accelerate software development but often exhibit instability, non-determinism, and weak adherence to development discipline in unconstrained workflows. While test-driven development (TDD) provides a structured Red-Green-Refactor process, existing LLM-based approaches typically use tests as auxiliary inputs rather than enforceable process constraints. We present an AI-native TDD framework […]