Papers

  • Hilbert States for Decision-Making under Partial Observability

    Decision-making under partial observability can be fundamentally limited by information, even with known dynamics: distinct physical states can induce the same observation history while favoring different actions. We study three questions: when is full-state optimality unattainable, what information exactly preserves the best observation-based decision, and how does finite-data learning affect …

  • AutoDiDact: Input Reduction over Inferred Structure

    Delta debugging reduces a failing input by deleting chunks of it, keeping a deletion only if an oracle confirms the failure persists. It chunks the input based only on its length, so its deletions cut through units such as identifiers and delimited groups, wasting calls and leaving outputs large. Current …

  • From Vision to Interaction: Evaluating Dynamic Social Intelligence of VLM Agents in ALIVE-World

    As AI agents are increasingly deployed in real-world applications and take on social roles, dynamic social intelligence, the ability to continuously perceive multimodal cues, infer latent cognitive states, intervene through embodied actions, and ultimately achieve social goals, has become essential. However, existing evaluations largely fragment social intelligence into text-based abstractions, …

  • Jev-as-a-Reward: Validating Probabilistic Safety Judges for Reinforcement Learning

    Probabilistic safety judges return the probability of a safety label and cheaply score reinforcement learning rollouts. A confidence gate sends only uncertain verdicts to a stronger LLM judge, which leaves confidently passed harm in a blind spot. Policies can exploit this blind spot, and commercial judges release new versions. We …

  • A Convergence Analysis of the Random Feature Method for Linear PDEs

    The Random Feature Method (RFM) distinguishes itself among machine learning approaches to partial differential equations (PDEs) through its superior accuracy and computational efficiency. Nevertheless, the theoretical underpinnings of RFM remain incompletely elucidated. This paper provides a comprehensive analysis of RFM within the framework of kernel methods, focusing on two principal …

  • ROSE: A Shared Cross-Embodiment Facial-Motion Latent Space for Humanoid Robot Expression

    Natural, coherent full-face dynamic expressions are central to making humanoid robots socially approachable, yet existing systems commonly realize only limited lip motion or scripted expressions. The limitation is both physical and algorithmic. A compact head leaves little room for densely packed, independently controllable actuation; meanwhile, learned systems often generate an …

  • One Code per Material: Neural Representation and Generation of Measured BTFs

    Measured bidirectional texture functions (BTFs) capture the full appearance of real materials--including parallax, self-shadowing and inter-reflections that analytic SVBRDFs cannot express--but each measurement is billions of values, and every new material requires a new capture. Existing neural BTF representations encode each material as large per-texel latent maps rather than as …

  • From Strong Normalization to WhatsApp: the Journey of an Axiom

    Twenty years ago, Mariangiola Dezani-Ciancaglini, Daniele Varacca and I showed that Milner's classic encoding of functions into processes does not respect one of the laws of intersection types, the one stating that $(\sigma\to\tau)\land(\sigma\to\rho)$ is a subtype of $\sigma\to(\tau\land\rho)$, which Barendregt, Coppo and Dezani-Ciancaglini had stated in 1983 for their filter …

  • vividRGB: Various visual cue detection in RGB photographs with forced focused attention

    Natural photographs contain dense, overlapping structures that can be weakly expressed in feature maps from whole-image vision encoders. We introduce forced focused attention (FFA) and its Python implementation, vividRGB. FFA is an encoder-agnostic inference-time procedure that applies a frozen encoder to enlarged, overlapping local crops, averages inverse-aligned reflections, and reconstructs …