technocracy

arXiv:2602.04941v1 Announce Type: new Abstract: Sets represent a fundamental abstraction across many types of data. To handle the unordered nature of set-structured data, models such as DeepSets and PointNet rely on fixed, non-learnable pooling operations (e.g., sum or max) — a design choice that can hinder the transferability of learned embeddings and limits model expressivity. More recently, learnable aggregation functions have been proposed as more expressive alternatives. In this work, we advance this line of research by introducing […]

Ver mais

arXiv:2601.22285v1 Announce Type: new Abstract: Model merging combines knowledge from separately fine-tuned models, yet success factors remain poorly understood. While recent work treats mergeability as an intrinsic property, we show with an architecture-agnostic framework that it fundamentally depends on both the merging method and the partner tasks. Using linear optimization over a set of interpretable pairwise metrics (e.g., gradient L2 distance), we uncover properties correlating with post-merge performance across four merging methods. We find substantial variation in success […]

Ver mais

Gozzip turns your social graph into your storage network. Instead of relying on servers that decide what gets stored and served, the protocol creates bilateral storage pacts between peers within your Web of Trust. Data lives on your device and your trusted contacts’ devices, verified by cryptographic challenge-response. The architecture formalizes how human communities have always preserved information: reciprocal obligation along trust edges, bounded by Dunbar layers, propagated through gossip. Built on Nostr primitives, bridges to ActivityPub and […]

Ver mais

Modal methods are a long-standing approach to physical modelling synthesis. Extensions to nonlinear problems are possible, including the case of a high-amplitude vibration of a string. A modal decomposition leads to a densely coupled nonlinear system of ordinary differential equations. Recent work in scalar auxiliary variable techniques has enabled construction of explicit and stable numerical solvers for such classes of nonlinear systems. On the other hand, machine learning approaches (in particular neural ordinary differential equations) have been successful […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work Preliminaries and Notations Differentiable Structural Information 4.1. A New Formulation 4.2. Properties 4.3. Differentiability & Deep Graph Clustering LSEnet 5.1. Embedding Leaf Nodes 5.2. Learning Parent Nodes 5.3. Hyperbolic Partitioning Tree Experiments 6.1. Graph Clustering 6.2. Discussion on Structural Entropy Conclusion, Broader Impact, and References Appendix A. Proofs B. Hyperbolic Space C. Technical Details D. Additional Results B. Hyperbolic Space B.1. Riemannian Manifold B.2. Models of Hyperbolic Space B.3. […]

Ver mais

arXiv:2602.11235v1 Announce Type: new Abstract: Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We propose MTFM (Meituan Foundation Model for Recommendation), a transformer-based framework that addresses these challenges. Instead of pre-aligning inputs, MTFM transforms cross-domain data into heterogeneous tokens, capturing multi-scenario knowledge in an alignment-free manner. To enhance efficiency, we first introduce a multi-scenario user-level sample aggregation that significantly enhances […]

Ver mais

Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to alter the dynamics of their released simulators for malicious purposes. Therefore, in this work we highlight a novel threat, demonstrating how simulator dynamics can be exploited to stealthily implant action-level backdoors into RL agents. The backdoor then allows […]

Ver mais

arXiv:2602.21435v1 Announce Type: new Abstract: Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking the need for explicit interaction between the two capabilities during task solving. As a result, current models treat understanding and generation as parallel skills rather than synergistic processes. To achieve real synergy, we introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm […]

Ver mais