arXiv:2604.01001v1 Announce Type: cross Abstract: We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either lack explicit 3D grounding, causing structural drift under viewpoint changes, or treat the scene as static, failing to update world states […]
Evaluating LLM-Generated ACSL Annotations for Formal Verification
arXiv:2602.13851v2 Announce Type: replace-cross Abstract: Formal specifications are crucial for building verifiable and dependable software systems, yet generating accurate and verifiable specifications for real-world C programs remains challenging. This paper empirically evaluates the extent to which formal-analysis tools can automatically generate and verify ACSL specifications without human or learning-based assistance. We conduct a controlled study […]
Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
arXiv:2604.01039v1 Announce Type: cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and privileged workflow definitions, making system instruction leakage a critical security risk […]
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
arXiv:2604.01128v1 Announce Type: cross Abstract: This paper introduces the first systematic evaluation framework for quantifying the quality and risks of papers written by modern coding agents. While AI-driven paper writing has become a growing concern, rigorous evaluation of the quality and potential risks of AI-written papers remains limited, and a unified understanding of their reliability […]
FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
arXiv:2602.08040v3 Announce Type: replace-cross Abstract: Deep neural networks trained on nonstationary data must balance stability (i.e., retaining prior knowledge) and plasticity (i.e., adapting to new tasks). Standard reinitialization methods, which reinitialize weights toward their original values, are widely used but difficult to tune: conservative reinitializations fail to restore plasticity, while aggressive ones erase useful knowledge. […]
Digital nanophotonic biosensing empowered by silicon Mie voids
arXiv:2604.01182v1 Announce Type: cross Abstract: Optical biosensors are indispensable in medical and environmental diagnostics, yet existing approaches are fundamentally limited in their sensitivity due to ensemble-averaged measurements. Digital biosensing has emerged as a promising solution for resolving individual binding events, thereby providing signals at very low analyte concentrations down to the single-molecule level. Here, we […]
Representation choice shapes the interpretation of protein conformational dynamics
arXiv:2604.00580v1 Announce Type: cross Abstract: Molecular dynamics simulations provide detailed trajectories at the atomic level, but extracting interpretable and robust insights from these high-dimensional data remains challenging. In practice, analyses typically rely on a single representation. Here, we show that representation choice is not neutral: it fundamentally shapes the conformational organization, similarity relationships, and apparent […]
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
arXiv:2501.09136v4 Announce Type: replace Abstract: Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Retrieval-Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by […]
Bypassing Prompt Injection Detectors through Evasive Injections
arXiv:2602.00750v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary prompts force the model to deviate from the user’s instructions to execute a potentially malicious task defined by the adversary. Recent work shows that ML models trained […]
Auto-Formulating Dynamic Programming Problems with Large Language Models
arXiv:2507.11737v2 Announce Type: replace Abstract: Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP techniques. Large Language Models (LLMs) offer the potential to automate this process. However, DP problems pose unique challenges due to their inherently stochastic transitions […]
Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
arXiv:2407.01570v4 Announce Type: replace-cross Abstract: Despite the significant advances in Deep Reinforcement Learning (RL) observed in the last decade, the amount of training experience necessary to learn effective policies remains one of the primary concerns in both simulated and real environments. Looking to solve this issue, previous work has shown that improved efficiency can be […]
DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
arXiv:2601.04823v4 Announce Type: replace Abstract: Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs). Parameter-efficient fine-tuning methods, such as LoRA, are widely adopted to adapt pretrained MoE LLMs to downstream tasks. However, existing approaches typically assign identical LoRA ranks to all expert modules, ignoring the heterogeneous specialization of pretrained experts. This […]