arXiv:2601.21892v2 Announce Type: replace-cross Abstract: Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic linear extrapolation that is often sensitive to the guidance scale. In this work, we provide a principled interpretation of CFG through the lens of optimization. […]
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
arXiv:2604.23018v2 Announce Type: replace-cross Abstract: Web-scale 3D asset collections are abundant but rarely deployment-ready, suffering from arbitrary metric scaling, incorrect pivots, brittle geometry, and incomplete textures, defects that limit their use in embodied AI, robotics, and spatial computing. We present AmaraSpatial-10K, a dataset of over 10,000 synthetic 3D assets optimised for zero-shot deployment. Each asset […]
Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle
arXiv:2605.12536v1 Announce Type: new Abstract: The Free Energy Principle (FEP) is a leading framework for mathematically modeling self-organization and learning, while Integrated Information Theory (IIT) is a computational ontology of consciousness oriented around irreducible cause and effect. While conceptual unifications have been proposed and appear to be supported by empirical findings, the absence of a […]
DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
arXiv:2605.12574v1 Announce Type: cross Abstract: Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motivating membership inference as a tool for training-data auditing. This is especially challenging for deployed VLMs, where auditors typically observe only generated textual responses. Existing VLM membership inference attacks either rely on […]
Discovery of Hidden Miscalibration Regimes
arXiv:2605.13484v1 Announce Type: cross Abstract: Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the confidence score alone. However, this view can hide substantial structure: models may be systematically overconfident on some kinds of inputs and underconfident on others, causing global reliability diagnostics to obscure […]
Quantitative Certification of Agentic Tool Selection
arXiv:2510.03992v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access, even without modifying the agent’s underlying model. Existing evaluations measure performance on curated, benign benchmarks. […]
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
arXiv:2507.00990v3 Announce Type: replace-cross Abstract: This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks–such as pouring, wiping, and mixing–purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. Given a language command and an initial scene image, a video diffusion model generates potential […]
Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems
arXiv:2601.15161v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed by generic metrics and LLM judges using general criteria, while expert-authored fine-grained rubrics are expensive […]
Human Ancestries Simulation and Inference: a Review of Ancestral Recombination Graph-Based Approaches
arXiv:2601.09634v3 Announce Type: replace Abstract: There is little debate about the importance of the ancestral recombination graph in population genetics. An important theoretical tool, the main obstacle to its widespread usage is the computational cost required to match the ever-increasing scale of the data being analyzed. Many of these difficulties have been overcome in the […]
SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios
arXiv:2605.07161v2 Announce Type: replace Abstract: AI agents are increasingly used to diagnose and mitigate failures in production systems, known as agentic Site Reliability Engineering (SRE). Current SRE benchmarks are limited to oversimplistic SRE tasks and are unfortunately hard to extend due to bespoke designs. We present SREGym, a high-fidelity benchmark for SRE agents. SREGym exposes […]
Structural identifiability of partially-observed stochastic processes: from single-particle trajectories to total particle density data
arXiv:2605.13504v1 Announce Type: cross Abstract: The increasing availability of experimental data has intensified interest in calibrating stochastic models, raising fundamental questions about parameter identifiability. Structural identifiability determines whether parameters can be uniquely recovered from idealised, noise-free data, a prerequisite to allow for parameter estimation. However, existing methods to assess structural identifiability are not generally applicable […]
The Co-evolution of Costly Signaling and Cooperation in Social Dilemmas
arXiv:2605.13750v1 Announce Type: cross Abstract: Costly cooperation and costly signaling are both difficult to reconcile with simple fitness maximization, yet both are common in biological and social systems. We study a model in which agents emit costly signals and condition their actions on the signals they observe. Across the Prisoner’s Dilemma (PD), Snowdrift (SD), and […]