arXiv:2604.00248v1 Announce Type: cross Abstract: Most automated peer review systems rely on textual manuscript content alone, leaving visual elements such as figures and external scholarly signals underutilized. We introduce REM-CTX, a reinforcement-learning system that incorporates auxiliary context into the review generation process via correspondence-aware reward functions. REM-CTX trains an 8B-parameter language model with Group Relative […]
Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation
arXiv:2604.00265v1 Announce Type: cross Abstract: We propose Question-Asking Navigation (QAsk-Nav), the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN) that enables an explicit, separate assessment of embodied navigation and collaborative question asking. CoIN tasks an embodied agent with reaching a target specified in free-form natural language under partial observability, using only egocentric visual observations […]
SANA I2I: A Text Free Flow Matching Framework for Paired Image to Image Translation with a Case Study in Fetal MRI Artifact Reduction
arXiv:2604.00298v1 Announce Type: cross Abstract: We propose SANA-I2I, a text-free high-resolution image-to-image generation framework that extends the SANA family by removing textual conditioning entirely. In contrast to SanaControlNet, which combines text and image-based control, SANA-I2I relies exclusively on paired source-target images to learn a conditional flow-matching model in latent space. The model learns a conditional […]
The Persistent Vulnerability of Aligned AI Systems
arXiv:2604.00324v1 Announce Type: cross Abstract: Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors once embedded, testing for vulnerabilities before deployment, and predicting when models will act against deployers. ACDC automates circuit discovery […]
Deep Networks Favor Simple Data
arXiv:2604.00394v1 Announce Type: cross Abstract: Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign emphhigher density to simpler out-of-distribution (OOD) data than to in-distribution test data. We refer to this behavior as the OOD anomaly. Prior work typically studies this […]
G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs
arXiv:2604.00419v1 Announce Type: cross Abstract: Large language models (LLMs) are trained on massive web-scale corpora, raising growing concerns about privacy and copyright. Membership inference attacks (MIAs) aim to determine whether a given example was used during training. Existing LLM MIAs largely rely on output probabilities or loss values and often perform only marginally better than […]
Contact-Dependent Ion Gating Explains Directional Asymmetry in the Bacterial Flagellar Motor
arXiv:2604.00470v1 Announce Type: cross Abstract: The bacterial flagellar motor (BFM) is a rotary molecular machine driven by the ion electrochemical potential across the cell membrane. Recent cryo-EM structures reveal a cogwheel-like architecture in which multiple stators engage a large rotor. A longstanding puzzle is the directional asymmetry of its torque-speed relation: concave in counterclockwise (CCW) […]
Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
arXiv:2604.00770v1 Announce Type: cross Abstract: A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally new attack surface. ThoughtSteer perturbs a single embedding vector at the input layer; the model’s own multi-pass reasoning amplifies this perturbation into […]
OrgAgent: Organize Your Multi-Agent System like a Company
arXiv:2604.01020v1 Announce Type: cross Abstract: While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical multi-agent framework that separates collaboration into governance, execution, and compliance layers. OrgAgent decomposes multi-agent reasoning into three layers: […]
MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning
arXiv:2604.00514v1 Announce Type: cross Abstract: Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a significant domain shift, limiting performance. Self-Supervised Learning (SSL) on unlabeled medical data has emerged as a […]
BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance
arXiv:2510.16082v5 Announce Type: replace Abstract: Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework […]
Dual Optimal: Make Your LLM Peer-like with Dignity
arXiv:2604.00979v2 Announce Type: cross Abstract: Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. We propose the Dignified Peer framework, which counters servility with anti-sycophancy and trustworthiness, and mitigates evasiveness through empathy and creativity. Realizing this agent requires […]