[Editor’s Note: This class was a part of the 2019 DFL Jane Street Fellowship.] This guide is thanks to a many different people, all of whom took their time to give feedback, write reviews, and provide their own insights to the curriculum. Special thanks to Cinjon Resnick, who was incredibly helpful throughout the iterations of the class, curriculum, and final notes. A special thanks as well to Professor Qiang Liu, who took the time to help shape the […]

Ver mais

arXiv:2503.15477v4 Announce Type: replace-cross Abstract: The success of Reinforcement Learning from Human Feedback (RLHF) critically depends on the quality of the reward model. However, while this quality is primarily evaluated through accuracy, it remains unclear whether accuracy fully captures what makes a reward model an effective teacher. We address this question from an optimization perspective. First, we prove that regardless of how accurate a reward model is, if it induces low reward variance, then the RLHF objective suffers […]

Ver mais

arXiv:2602.12394v1 Announce Type: new Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users. This gap is primarily due to (i) the absence of high-quality, privacy-sensitive data that capture personalized user-LLM interactions at scale, and (ii) the lack of robust reward signals for individual preferences. To overcome existing data limitations, we introduce […]

Ver mais

Concrete is the most widely used construction material worldwide; however, reliable prediction of compressive strength remains challenging due to material heterogeneity, variable mix proportions, and sensitivity to field and environmental conditions. Recent advances in artificial intelligence enable data-driven modeling frameworks capable of supporting automated decision-making in construction quality control. This study leverages an industry-scale dataset consisting of approximately 70,000 compressive strength test records to evaluate and compare multiple predictive approaches, including linear regression, decision trees, random forests, transformer-based […]

Ver mais

I’m exploring an idea and would love feedback from people who work with ML / agents / RL. Instead of generating synthetic datasets, the idea is to generate synthetic worlds: – populations – economic dynamics – constraints – shocks – time evolution The goal wouldn’t be prediction, but providing controllable environments where AI agents can be trained or stress-tested on long-horizon decisions (policy, planning, resource allocation, etc.). Think more like “SimCity-style environments for AI training” rather than tabular […]

Ver mais

arXiv:2601.10770v1 Announce Type: new Abstract: Traditional speech systems typically rely on separate, task-specific models for text-to-speech (TTS), automatic speech recognition (ASR), and voice conversion (VC), resulting in fragmented pipelines that limit scalability, efficiency, and cross-task generalization. In this paper, we present General-Purpose Audio (GPA), a unified audio foundation model that integrates multiple core speech tasks within a single large language model (LLM) architecture. GPA operates on a shared discrete audio token space and supports instruction-driven task induction, enabling […]

Ver mais

arXiv:2602.11167v1 Announce Type: new Abstract: Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study this phenomenon systematically, we introduce FalseCite, a curated dataset designed to capture and benchmark hallucinated responses induced by misleading or fabricated citations. Running GPT-4o-mini, Falcon-7B, and Mistral 7-B through FalseCite, we observed a noticeable increase in hallucination activity for false claims with deceptive citations, especially in GPT-4o-mini. […]

Ver mais

arXiv:2602.03907v1 Announce Type: new Abstract: While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an open-source ecosystem designed to establish a unified, high-quality foundation for 3D generation. Our contributions are threefold: (1) We curate a library of 250k high-fidelity 3D objects distilled from large-scale repositories, employing a rigorous pipeline to deliver training-ready artifacts, including watertight meshes and multi-view […]

Ver mais

arXiv:2603.12451v1 Announce Type: new Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics […]

Ver mais