arXiv:2604.07393v1 Announce Type: new Abstract: Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. […]

Ver mais

arXiv:2603.23569v1 Announce Type: new Abstract: Equal-contribution authorship, in which two or more authors are designated as having contributed equally, is increasingly common in scientific publishing. Using approximately 480,000 tagged records from PubMed and PMC (2010-2024), we examine temporal trends, journal-level patterns, geographic distributions, and byline positions of equal-contributing authors. Results show a sharp rise after 2017, with both high-output mega-journals and smaller, discipline-specific journals contributing to the growth. Journal-level analysis indicates a median increase in the share of […]

Ver mais

arXiv:2604.15409v1 Announce Type: new Abstract: KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation. This assumption fails under standard FP16 precision: cache-ON and cache-OFF execution paths employ different floating-point accumulation orderings which, due to FP16 non-associativity, produce a deterministic divergence in decoded token sequences. Across three open-weight models (LLaMA-2-7B, Mistral-7B-v0.3, Gemma-2-2B) evaluated on GSM8K, we observe a 100% token divergence rate across all sampling strategies, including greedy decoding, […]

Ver mais

arXiv:2603.15646v1 Announce Type: new Abstract: Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured, multi-dimensional, contextual rubric-based evaluations. However, existing approaches in RLRR are limited to linearly compressing vector rewards into a scalar reward with a fixed weightings, which is sensitive to artificial score design and fails to capture correlations among reward dimensions. To overcome the limitations of […]

Ver mais

Series Context This is the first part of a 5-part series on agentic AI governance. As organizations deploy AI agents that can act across enterprise systems, traditional approaches to governance are proving insufficient. In this part, we examine why AI agents can no longer be treated as invisible automation and why identity and access management must come before autonomy. Zero Trust cannot govern actors it cannot identify. If an AI agent can read data, call tools, trigger workflows, […]

Ver mais

arXiv:2601.10781v1 Announce Type: new Abstract: Future motion representations, such as optical flow, offer immense value for control and generative tasks. However, forecasting generalizable spatially dense motion representations remains a key challenge, and learning such forecasting from noisy, real-world data remains relatively unexplored. We introduce FOFPred, a novel language-conditioned optical flow forecasting model featuring a unified Vision-Language Model (VLM) and Diffusion architecture. This unique combination enables strong multimodal reasoning with pixel-level generative fidelity for future motion prediction. Our model […]

Ver mais

arXiv:2602.03143v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group frequently receive identical rewards, causing relative advantages to collapse and updates to vanish. We propose self-hint aligned GRPO with privileged supervision (SAGE), an on-policy reinforcement learning framework that injects privileged hints during training to reshape the rollout distribution under the […]

Ver mais

arXiv:2602.10131v1 Announce Type: new Abstract: I present a descriptive analysis of Moltbook, a social platform populated exclusively by AI agents, using data from the platform’s first 3.5 days (6{,}159 agents; 13{,}875 posts; 115{,}031 comments). At the macro level, Moltbook exhibits structural signatures that are familiar from human social networks but not specific to them: heavy-tailed participation (power-law exponent $alpha = 1.70$) and small-world connectivity (average path length $=2.91$). At the micro level, patterns appear distinctly non-human. Conversations are […]

Ver mais

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number of IoT devices. Storing this amount of data centrally is challenging due to issues like limited communication, privacy, and regulations. FL can be Centralized (CFL), Decentralized (DFL), and Semi-decentralized (SDFL). Choosing the right FL architecture depends on […]

Ver mais