arXiv:2603.10935v2 Announce Type: replace-cross Abstract: Variational autoencoders (VAEs) frequently suffer from posterior collapse, where latent variables become uninformative and the approximate posterior degenerates to the prior. Recent work has characterized this phenomenon as a phase transition governed by the spectral properties of the data covariance matrix. In this paper, we propose a fundamentally different approach: […]
Value Under Ignorance in Universal Artificial Intelligence
arXiv:2512.17086v2 Announce Type: replace Abstract: We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent’s belief distribution only predict a finite prefix of the history, which is sometimes interpreted as […]
The Epistemic Support-Point Filter: Jaynesian Maximum Entropy Meets Popperian Falsification
arXiv:2603.10065v2 Announce Type: replace-cross Abstract: This paper proves that the Epistemic Support-Point Filter (ESPF) is the unique optimal recursive estimator within the class of epistemically admissible evidence-only filters. Where Bayesian filters minimize mean squared error and are driven toward an assumed truth, the ESPF minimizes maximum entropy and surfaces what has not been proven impossible […]
Logics-Parsing-Omni Technical Report
arXiv:2603.09677v2 Announce Type: replace Abstract: Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the Omni Parsing framework. This framework establishes a Unified Taxonomy covering documents, images, and audio-visual streams, introducing a progressive parsing paradigm that bridges perception and cognition. Specifically, the framework integrates three […]
Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach
arXiv:2603.11757v1 Announce Type: cross Abstract: Personalized AI-based services involve a population of individual reinforcement learning agents. However, most reinforcement learning algorithms focus on harnessing individual learning and fail to leverage the social learning capabilities commonly exhibited by humans and animals. Social learning integrates individual experience with observing others’ behavior, presenting opportunities for improved learning outcomes. […]
Once4All: Skeleton-Guided SMT Solver Fuzzing with LLM-Synthesized Generators
arXiv:2508.20340v3 Announce Type: replace-cross Abstract: Satisfiability Modulo Theory (SMT) solvers are foundational to modern systems and programming languages research, providing the foundation for tasks like symbolic execution and automated verification. Because these solvers sit on the critical path, their correctness is essential, and high-quality test formulas are key to uncovering bugs. However, while prior testing […]
Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation
arXiv:2509.20681v3 Announce Type: replace-cross Abstract: Implicit representations have been widely applied in robotics for obstacle avoidance and path planning. In this paper, we explore the problem of constructing an implicit distance representation from a single image. Past methods for implicit surface reconstruction, such as NeuS and its variants generally require a large set of multi-view […]
BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft
arXiv:2603.03964v2 Announce Type: replace-cross Abstract: We present textbfBLOCK, an open-source bi-stage character-to-skin pipeline that generates pixel-perfect Minecraft skins from arbitrary character concepts. BLOCK decomposes the problem into (i) a textbf3D preview synthesis stage driven by a large multimodal model (MLLM) with a carefully designed prompt-and-reference template, producing a consistent dual-panel (front/back) oblique-view Minecraft-style preview; and […]
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
arXiv:2603.09731v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint. We study this gap through a new task, Egocentric Scene Prediction with LOng-horizon REasoning: given an […]
Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
arXiv:2603.11896v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video streams difficult. Existing streaming methods typically use an interleaved perception-generation paradigm, which prevents concurrent perception and generation and […]
Scaling Laws and Paradoxical Metastable States in Nanofilament Entropic Separation
arXiv:2603.11732v1 Announce Type: cross Abstract: Entropic forces play a fundamental role in nanoscale phenomena, from colloidal self-assembly to biomolecular disaggregation. Here, we develop an exact analytical theory and find general scaling laws for the entropic separation of tether-mediated nanofilament bundles, revealing that a single dimensionless parameter–the ratio of the excluded-volume radius to the tether length–dictates […]
LLMTrack: Semantic Multi-Object Tracking with Multi-modal Large Language Models
arXiv:2601.06550v2 Announce Type: replace-cross Abstract: Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures and Multi-modal Large Language Models (MLLMs). To address this, we introduce Grand-SMOT, a large-scale, open-world benchmark providing high-density, […]