arXiv:2601.19934v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always produce identical outputs, even when temperature and other decoding parameters are fixed. In this work, we conduct repeated-run experiments to empirically quantify baseline behavioural drift, defined as output variability observed when the same prompt is issued multiple times under operator-free conditions. We evaluate two publicly accessible models, gpt-4o-mini and llama3.1-8b, across […]

Ver mais

Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided […]

Ver mais

arXiv:2601.00189v1 Announce Type: new Abstract: Mosquitos are the main transmissive agents of arboviral diseases. Manual classification of their neuronal spike patterns is very labor-intensive and expensive. Most available deep learning solutions require fully labeled spike datasets and highly preprocessed neuronal signals. This reduces the feasibility of mass adoption in actual field scenarios. To address the scarcity of labeled data problems, we propose a new Generative Adversarial Network (GAN) architecture that we call the Semi-supervised Swin-Inspired GAN (SSI-GAN). The […]

Ver mais

arXiv:2602.23371v1 Announce Type: new Abstract: Legal research in India involves navigating long and heterogeneous documents spanning statutes, constitutional provisions, penal codes, and judicial precedents, where purely keyword-based or embedding-only retrieval systems often fail to support structured legal reasoning. Recent retrieval augmented generation (RAG) approaches improve grounding but struggle with multi-hop reasoning, citation chaining, and cross-domain dependencies inherent to legal texts. We propose a domain partitioned hybrid RAG and Knowledge Graph architecture designed specifically for Indian legal research. The […]

Ver mais

What are the numbers made of? More precisely, what are prime numbers made of? I posed this question to myself on the evening of August 19, 2025, which prompted prolonged introspection and profound contemplation. Then, I began constructing a numerical pyramid with prime numbers. The number one took the place of the central axis. Therefore, it is possible that large prime numbers could be surrounded by prime numbers on either side of one. However, this property extends to […]

Ver mais

There are many ways to read, organize your favorite books, and share your opinions about them. Numerous developers in the open-source world know this, and they’ve been creating a wide set of free tools we can use to expand our reading experience. From personal libraries to social reading, these software pieces are available for everyone. Here, we’ll explore five tools that will make our stories even more interesting. If you find them useful, donating cryptocurrency to their teams […]

Ver mais

In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect the imbalance problem of relational data in RDBs and risk under-representing the minority entities, leading to an unusable model in practice. In this work, we investigate, for the first time, class imbalance problem […]

Ver mais

arXiv:2602.09081v1 Announce Type: new Abstract: State Space Models (SSMs), particularly Mamba, have shown potential in long-term time series forecasting. However, existing Mamba-based architectures often struggle with datasets characterized by non-stationary patterns. A key observation from time series theory is that the statistical nature of inter-variable relationships differs fundamentally between the trend and seasonal components of a decomposed series. Trend relationships are often driven by a few common stochastic factors or long-run equilibria, suggesting that they reside on a […]

Ver mais

arXiv:2601.08050v1 Announce Type: new Abstract: We unify Hamilton-Jacobi (HJ) reachability and Reinforcement Learning (RL) through a proposed running cost formulation. We prove that the resultant travel-cost value function is the unique bounded viscosity solution of a time-dependent Hamilton-Jacobi Bellman (HJB) Partial Differential Equation (PDE) with zero terminal data, whose negative sublevel set equals the strict backward-reachable tube. Using a forward reparameterization and a contraction inducing Bellman update, we show that fixed points of small-step RL value iteration converge […]

Ver mais

Enterprise mobile apps are no longer optional in 2026. This list highlights 11 top US-based mobile app development companies trusted by enterprises for scalable, secure, and future-ready apps. From AI-driven innovation to deep backend integration, these firms help businesses modernize operations, improve UX, and stay competitive.

Ver mais