High-Capacity Generalized Hopfield Networks
arXiv:2608.08226v1 Announce Type: cross Abstract: Generalized Hopfield networks are introduced where memories and neurons are continuous variables that lie on a Riemannian manifold. We explicitly focus…
Papers 5171 stories
An invertible generative model for forward and inverse problems
arXiv:2509.03910v2 Announce Type: replace Abstract: We formulate inverse problems in a Bayesian framework and aim to train an invertible generative model that is capable of simulation…
Optimal Transport for Machine Learners
arXiv:2505.06589v3 Announce Type: replace Abstract: Modern machine learning repeatedly manipulates probability measures: empirical datasets, generated samples, latent distributions, class-conditional laws, particle systems, weights of wide networks…
Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems
arXiv:2608.07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance…
The Field Knows: Cross-Dimensional Geometry from Navigation to Black Holes
arXiv:2608.07566v1 Announce Type: new Abstract: We introduce a continuous metric field framework trained by a single causal contrastive loss. The framework encodes a scene into coefficients…
WuYuEval: A Multi-Level Benchmark for Large Language Models in Solid Waste Management
arXiv:2608.07529v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as technical assistants, but their competence in solid waste management (SWM) remains difficult to…
Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation
arXiv:2607.10744v4 Announce Type: replace Abstract: Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models (LLMs) have…
Latent-Frequency Validity: Fast Spectral Editing with Screened Video-VAE Transfer Operators
arXiv:2608.07569v1 Announce Type: new Abstract: Direct spectral editing in video-VAE latents can control noise, flicker, smoothness, and frequency content without a decode--filter--reencode pass. However, video VAEs…
SIP: Site in Pieces- A Dataset of Disaggregated Construction-Phase 3D Scans for Semantic Segmentation and Scene Understanding
arXiv:2512.09062v2 Announce Type: replace-cross Abstract: Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development. LiDAR is…
Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids
arXiv:2603.28385v2 Announce Type: replace-cross Abstract: Maritime surveillance missions, such as search and rescue and environmental monitoring, rely on the efficient allocation of sensing assets over vast…
Communication-efficient distributed hazard difference estimation for heterogeneous multi-site survival data
arXiv:2601.14609v2 Announce Type: replace Abstract: Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block…
Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes
arXiv:2608.09074v1 Announce Type: new Abstract: We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB). Leveraging the asymptotic normality…
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two…
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny:…
Motif 3: Technical Report
We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each sparse MoE layer contains 384…
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four…
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an…
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations. Teacher entropy alone does…
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware post-training methods encourage image use…
Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
World generative models are typically used through what they produce: a rendered future, a video-conditioned action, or latent context computed by a costly generative branch. We…
CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions. We introduce CLIP-CC-Bench,…
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues
Turn-taking is a central component of full-duplex interaction. Which turn-taking behaviors are appropriate varies with the scenario, yet current models apply a single norm regardless of…
Forking-Sequences — Part II: Multi-Horizon Forecast Ensembling with Reduced Volatility
Based on: Potosnak, W., Wolff, M., Cao, M., Ma, R., Konstantinova, T., Efimov, D., Mahoney, M.W., Oreshkin, B., & Olivares, K.G. "Forking-Sequences: Statistically and Computationally Efficient…
Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting
Sequence models must decide what to write into memory and what to retain. In quantum and quantum-inspired sequence learning, nonlinear recurrent updates often require repeated circuit…