January 2026

arXiv:2601.16988v1 Announce Type: new Abstract: The rapid expansion of scholarly publications across diverse disciplines has made it increasingly difficult to systematically evaluate how research contributes to the United Nations Sustainable Development Goals (SDGs). Domain classification of research articles done manually through research experts is extremely impractical because of the number of publications, expensive in time and may not be consistent when done by human beings. This paper proposes an automated and rule-based computational model of classifying research papers […]

Ver mais

arXiv:2601.16987v1 Announce Type: new Abstract: Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most existing RM evaluations rely on static, pre-annotated preference datasets, which provide limited coverage and often fail to faithfully assess generalization in open-world settings. We introduce Pairwise Maximum Discrepancy Competition (PMDC), a dynamic and annotation-efficient framework for evaluating RM generalization using a large, unlabeled, open-domain prompt pool. PMDC actively selects […]

Ver mais

arXiv:2601.16986v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike traditional generation tasks where all tokens are uniformly important, CoT emphasizes the final answer, rendering conventional KV compression strategies ineffective. In this paper, we present Crystal-KV, an efficient KV cache management framework tailored for CoT reasoning. Our key insight is the […]

Ver mais

arXiv:2601.16985v1 Announce Type: new Abstract: Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow adaptation, and catastrophic forgetting. We present a neuro-symbolic framework integrating hierarchical abstractions, task and motion planning (TAMP), and reinforcement learning to enable rapid adaptation in robotics. Our architecture combines symbolic goal-oriented learning and world model-based exploration to facilitate rapid adaptation to environmental […]

Ver mais

arXiv:2601.16984v1 Announce Type: new Abstract: The 3rd Generation Partnership Project (3GPP) produces complex technical specifications essential to global telecommunications, yet their hierarchical structure, dense formatting, and multi-modal content make them difficult to process. While Large Language Models (LLMs) show promise, existing approaches fall short in handling complex queries, visual information, and document interdependencies. We present TelcoAI, an agentic, multi-modal Retrieval-Augmented Generation (RAG) system tailored for 3GPP documentation. TelcoAI introduces section-aware chunking, structured query planning, metadata-guided retrieval, and multi-modal […]

Ver mais

Risk disclosures in SEC filings describe potential adverse events but rarely quantify their likelihood, limiting their usefulness for probabilistic analysis. A central obstacle is the absence of large-scale, risk-level supervision linking disclosed risks to realized outcomes. We introduce a fully automated data generation pipeline that converts qualitative SEC risk disclosures into temporally grounded supervision using only public data. For each filing, the pipeline generates firm-specific, time-bounded risk queries from the Risk Factors section and labels them by automatically […]

Ver mais

Fairness is a central pillar of trustworthy machine learning, especially in domains where accuracy- or profit-driven optimization is insufficient. While most fairness research focuses on supervised learning, fairness in policy learning remains less explored. Because policy learning is interventional, it induces two distinct fairness targets: action fairness (equitable action assignments) and outcome fairness (equitable downstream consequences). Crucially, equalizing actions does not generally equalize outcomes when groups face different constraints or respond differently to the same action. We propose […]

Ver mais

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by incorporating non-uniform $ell_2$ regularization or by adjusting the loss function. However, these approaches become insufficient in the nonlinear setting, as the remaining variance cannot be properly captured independently of the nonlinear mapping. In this work, we propose a novel autoencoder framework that integrates non-uniform variance regularization with […]

Ver mais

The chart looked convincing. A clear, upward slope, a quick shift right after a new feature rollout, and a healthy percentage increase in bold. Heads nodded in the meeting room. There was a remark: “This clearly worked.” Then the discomforting follow-up: “But how do we know this happened because of the feature?” That question too often asked too late, or not at all — is where econometric statistics intervenes, quietly, to affect the outcome of real-world decisions. The […]

Ver mais

Market Prediction Despite the recent backlash around WLFI, political memecoins connected to the Trump family are likely to be among the most impactful assets in the next 2-3 years. After years in the crypto industry, you start recognizing patterns not just in the token charts, but also in the behavior of traders and a broader global economy. Watching the current crypto market patterns, we can expect an interesting paradox emerging soon – crypto startups with no real utility […]

Ver mais