arXiv:2601.20303v2 Announce Type: replace-cross Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of which is directly observable from RGB appearance. Consequently, mass prediction from pixels is ill-posed and therefore benefits from physically meaningful representations to constrain the space of plausible solutions. We propose […]
From Passive Feeds to Guided Discovery: AI-Initiated Interaction for Vague Intent in Content Exploration
arXiv:2605.02902v1 Announce Type: cross Abstract: Recommendation feeds work well when people are simply browsing, and search works well when they can formulate a query. Between these two cases is a common but poorly supported state: users feel that their feed has become repetitive, yet cannot clearly specify what they want instead. We refer to this […]
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
arXiv:2605.03804v1 Announce Type: new Abstract: Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To address this, we propose ScrapMem, a framework that integrates multimodal data into “Scrapbook Page.” ScrapMem introduces Optical Forgetting, an optical compression mechanism that progressively reduces the resolution of older […]
Robust chemotaxis beyond sensing limits: signal, noise, and strategy
arXiv:2605.03632v1 Announce Type: new Abstract: Bacterial chemotaxis has long been viewed as operating near the physical limits of sensing, as originally articulated by Berg and Purcell. Recent information-theoretic analyses challenge this view, suggesting that Escherichia coli uses only a small fraction of the information available in ligand arrival statistics to bias its motion. How should […]
AgenticPosesRanker: An Agentic AI Framework for Physically Grounded Ranking of Protein-Ligand Docking Poses
arXiv:2605.03707v1 Announce Type: new Abstract: Scoring functions remain the principal bottleneck in molecular docking: they routinely fail to rank near-native poses above decoys, and their composite single-score design obscures the physicochemical basis of each ranking error. We present AgenticPosesRanker, an agentic AI framework that combines six deterministic, physically grounded analysis tools (interaction fingerprinting, solvent-accessible burial, […]
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models
arXiv:2605.03426v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance, yet strict data-sharing constraints render centralized training infeasible. Federated Learning mitigates this issue by enabling decentralized training, but practical deployments face challenges due to client heterogeneity in computational resources, application requirements, and model architectures. Under extreme […]
Expanding functional protein sequence space using high entropy generative models
arXiv:2605.03578v1 Announce Type: new Abstract: Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. However, the relationship between model architecture, specifically parameter density, and experimental performance remains poorly understood. Here, we investigate this relationship using the Chorismate Mutase enzyme family as a model system. […]
Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
arXiv:2605.04019v1 Announce Type: new Abstract: AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows – assembling attacks, transforms, and scorers. When results fall short, workflows must […]
GeoDecider: A Coarse-to-Fine Agentic Workflow for Explainable Lithology Classification
arXiv:2605.03383v1 Announce Type: new Abstract: Lithology classification aims to infer subsurface rock types from well-logging signals, supporting downstream applications like reservoir characterization. Despite substantial progress, most existing methods still treat lithology classification as a single-pass classification task. In contrast, practical experts incorporate geological principles, external knowledge, and tool-use capabilities to perform accurate classification. In this […]
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including scientific assistance, long-horizon agents, high-stakes advice, personalization, and tool use, where the relevant objective is ambiguous, context-dependent, delayed, or […]
Real-Time Evaluation of Autonomous Systems under Adversarial Attacks
arXiv:2605.03491v1 Announce Type: new Abstract: Most evaluations of autonomous driving policies under adversarial conditions are conducted in simulation, due to cost efficiency and the absence of physical risk. However, purely virtual testing fails to capture structural inconsistencies, supervision constraints, and state-representation effects that arise in real-world data and fundamentally shape policy robustness. This work presents […]
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
arXiv:2605.03609v1 Announce Type: new Abstract: Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framework while preserving general competence. We present Convergent-Divergent Routing, which traces and edits minimal branch points inside transformer blocks where ethical-framework-related pathways first converge and then diverge. Gating non-target branches at these […]