arXiv:2501.02378v2 Announce Type: replace-cross Abstract: Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop transient slow regions in state space that extend the effective timescales of computation. However, the mechanisms driving sudden performance improvements and their causal role remain unclear. To address this gap, we introduce the ghost mechanism, a process by which dynamical systems exhibit transient slowdown near the remnant of a saddle-node bifurcation. […]

Ver mais

arXiv:2604.13244v1 Announce Type: new Abstract: The 4th Workshop on Maritime Computer Vision (MaCVi) is organized as part of CVPR 2026. This edition features five benchmark challenges with emphasis on both predictive accuracy and embedded real-time feasibility. This report summarizes the MaCVi 2026 challenge setup, evaluation protocols, datasets, and benchmark tracks, and presents quantitative results, qualitative comparisons, and cross-challenge analyses of emerging method trends. We also include technical reports from top-performing teams to highlight practical design choices and lessons […]

Ver mais

The ultimate deep-dive into memory systems, web search, skills, multi-agent architecture, and cloud deployment I’ve been following OpenClaw’s evolution for a while now. Every few weeks, there’s another update, another feature, another reason to reconsider how I work with AI agents. The beginner tutorials are everywhere now, but what about the stuff that actually makes you productive? The features that transform OpenClaw from a cool demo into a serious productivity engine? That’s exactly what this guide is about. […]

Ver mais

arXiv:2604.16919v1 Announce Type: new Abstract: Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but they are susceptible to local minima and noise overfitting. Although DMs can provide strong priors for Bayesian approaches, enforcing measurement consistency during the denoising process leads to manifold infeasibility issues. We propose Noise-space Hamiltonian Monte Carlo (N-HMC), a posterior sampling method that treats reverse diffusion as a deterministic mapping […]

Ver mais

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is fundamentally governed by reward design. Despite its importance, the relationship between reward modeling and core LLM challenges–such as evaluation bias, hallucination, distribution shift, and efficient learning–remains poorly understood. This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment, shaping what models […]

Ver mais

I’m planning to fine-tune OSS-120B (or Qwen3-30B-A3B-Thinking-2507) on a mixed corpus: ~10k human-written Q&A pairs plus ~80k carefully curated synthetic Q&A pairs that we spent a few months generating and validating. The goal is to publish an open-weight model on Hugging Face and submit the work to an upcoming surgical conference in my country. The model is intended to help junior surgeons with clinical reasoning/support and board-style exam prep. I’m very comfortable with RAG + inference/deployment, but this […]

Ver mais

arXiv:2604.05080v1 Announce Type: new Abstract: We present Nidus, a governance runtime that mechanizes the V-model for AI-assisted software delivery. In the self-hosting deployment, three LLM families (Claude, Gemini, Codex) delivered a 100,000-line system under proof obligations verified against the current obligation set on every commit. The system governed its own construction. Engineering invariants – traced requirements, justified architecture, evidenced deliveries – cannot be reliably maintained as learned behavior; assurance requires enforcement by a mechanism external to the proposer. […]

Ver mais

arXiv:2510.09676v2 Announce Type: replace-cross Abstract: Inverse problems, where the goal is to recover an unknown signal from noisy or incomplete measurements, are central to applications in medical imaging, remote sensing, and computational biology. Diffusion models have recently emerged as powerful priors for solving such problems. However, existing methods either rely on projection-based techniques that enforce measurement consistency through heuristic updates, or they approximate the likelihood $p(boldsymbol{y} mid boldsymbol{x})$, often resulting in artifacts and instability under complex or high-noise […]

Ver mais

arXiv:2602.13242v1 Announce Type: new Abstract: As artificial intelligence (AI) becomes increasingly integrated into daily life, higher education must move beyond code-centric instruction to foster holistic AI literacy. We present a novel pedagogical approach that integrates embodied, unplugged activities into a university-level Introduction to AI course. Inspired by the effectiveness of CS Unplugged in K-12 education, our physical, collaborative activities gave students a first-person perspective on AI decision-making. Through interactive games modeling Search Algorithms, Markov Decision Processes, Q-learning, and […]

Ver mais