Research
Research
Research
Research
346,661+ open-access research outputs.
Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak teacher's blind spots. Underst…
Many Multi-Agent Reinforcement Learning (MARL) agents fail to adapt properly to cooperating with agents trained with the same objectives but different seeds, algorithms, or other training differences.…
Deploying machine learning models under production constraints requires joint optimization over model family, quantization scheme, runtime backend, and serving configuration. This induces a hierarchic…
Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these two capabilities ind…
Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks measure broad capability growth, but may not provide …
Cellular differentiation is governed by gene regulatory networks, the high-dimensional stochastic biochemical systems that determine the transcriptional landscape and mediate cellular responses to sig…
Custom policy-learning pipelines in Spark fail for two coupled systems reasons: rowwise Python execution makes inference impractical, and driver-side candidate materialization makes split search fragi…
This study examines the factors that influence the adoption of TikTok as a learning tool for physical education (PE)-related content among tertiary students in the Philippines. The study applies the T…
Our paper studies the setting of players using no-regret algorithms in various two-player games. We address whether having stronger regret guarantees or playing against an opponent with weaker regret …
Tuberculosis (TB) is an airborne disease caused by the pathogen Mycobacterium tuberculosis. In 2023, according to the World Health Organization, it ''probably'' replaced COVID-19 as the leading cause …
Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that, at the one-sided ghost-gap interface actually us…
Measures of disengagement provide insights into unproductive use of learning opportunities. Although measures of active disengagement, such as gaming the system and mind-wandering, are well studied, l…
Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads…
As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction his…
This paper describes the design and implementation of a two-day quantum hackathon for underrepresented high school students in Nova Scotia, Canada. The first day of the hackathon is spent introducing …
Clinical abnormality grounding for rare diseases is often hindered by data scarcity, making supervised fine-tuning impractical and single-pass inference highly unstable. We propose Dynamic Decision Le…
Learning matrix-valued distributions from high-dimensional and possibly incomplete training data is challenging: ambient-space generative modeling is computationally expensive and statistically fragil…
Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforc…
While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conf…
Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resul…
Free open-access publishing with Google Scholar indexing.
Submission Guide →