arXiv:2605.00829v1 Announce Type: new Abstract: Social media has become a critical source of situational awareness during disasters, providing real-time insights into evolving impacts and emerging needs. To support crisis response at scale, recent work has increasingly leveraged large language models (LLMs) to automatically classify and summarize situational information from social media streams. However, existing approaches implicitly assume that extracted situational claims are equally plausible, despite information quality varying substantially as a crisis unfolds. In this work, we propose […]

Ver mais

Large language models are stateless by default. Each API call starts fresh. The model forgets your last message once the response returns. That is fine for a single question. It breaks the moment you build an agent. Agents plan, call tools, and run across many steps. They need to remember. Memory is the infrastructure that fixes this. It turns a stateless model into a system that retains context. That system can learn from experience and act over time. […]

Ver mais

:::info Authors: Liang Wang (Microsoft Corporation) Nan Yang (Microsoft Corporation) Xiaolong Huang (Microsoft Corporation) Binxing Jiao (Microsoft Corporation) Linjun Yang (Microsoft Corporation) Daxin Jiang (Microsoft Corporation) Rangan Majumder (Microsoft Corporation) Furu Wei (Microsoft Corporation) ::: Abstract This paper presents E5 1, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset (called CCPairs). E5 […]

Ver mais

arXiv:2604.08619v1 Announce Type: new Abstract: This paper presents a comprehensive dataset of doctoral theses defended in France between 1985 and 2025, constructed from multiple national academic metadata sources. The dataset is primarily based on data from the French national thesis platform and is enriched using additional authority and bibliographic databases to improve data quality, completeness, and interoperability. The data production pipeline includes the aggregation of heterogeneous sources, the correction of inconsistent identifiers, the enrichment of person and institution […]

Ver mais

arXiv:2602.21297v1 Announce Type: new Abstract: The standard way to evaluate language models on subjective tasks is through pairwise comparisons: an annotator chooses the “better” of two responses to a prompt. Leaderboards aggregate these comparisons into a single Bradley-Terry (BT) ranking, forcing heterogeneous preferences into a total order and violating basic social-choice desiderata. In contrast, social choice theory provides an alternative approach called maximal lotteries, which aggregates pairwise preferences without imposing any assumptions on their structure. However, we show […]

Ver mais

arXiv:2603.08899v1 Announce Type: new Abstract: Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that are subsequently verified by the target model. The effectiveness of this paradigm critically depends on the quality of the draft model. While recent advances such as the EAGLE series achieve state-of-the-art speedup, existing draft models remain limited by error accumulation: they condition only on the current prefix, causing […]

Ver mais

arXiv:2602.05946v1 Announce Type: cross Abstract: Recent research shows that Preference Alignment (PA) objectives act as divergence estimators between aligned (chosen) and unaligned (rejected) response distributions. In this work, we extend this divergence-based perspective to general alignment settings, such as reinforcement learning with verifiable rewards (RLVR), where only environmental rewards are available. Within this unified framework, we propose $f$-Group Relative Policy Optimization ($f$-GRPO), a class of on-policy reinforcement learning, and $f$-Hybrid Alignment Loss ($f$-HAL), a hybrid on/off policy objectives, […]

Ver mais

I’ve been building data sync workflows for B2B companies for the better part of three years. The stack I keep coming back to is n8n piping data into PostgreSQL. Not because it’s trendy. Because it works at 50 records and at 500,000 records, and because when it breaks at 3 AM, I can actually debug it. But here’s what bothers me: almost every tutorial I find online about n8n + Postgres covers the happy path. Connect the nodes, […]

Ver mais

arXiv:2405.19206v2 Announce Type: replace Abstract: Deep neural networks (DNNs) on Riemannian manifolds have garnered increasing interest in various applied areas. For instance, DNNs on spherical and hyperbolic manifolds have been designed to solve a wide range of computer vision and nature language processing tasks. One of the key factors that contribute to the success of these networks is that spherical and hyperbolic manifolds have the rich algebraic structures of gyrogroups and gyrovector spaces. This enables principled and effective […]

Ver mais