Category
9,568 papers
PalmLeaf-VQA provides a standardized benchmark for advancing culturally grounded and layout-aware multimodal document analysis and reveals substantial limitations in current MLLMs for rare-script, degraded-layout, and preservation-oriented document understanding.
Large language models (LLMs) are increasingly being employed as variation operators in metaheuristics, generating or modifying candidate solutions, heuristics, or programs inside iterative search loops. This shift reframes variation as a model call conditioned on different types of information. We introduce an operator...
CHESTPHENOT is a compact 0.5-3B language model that jointly extracts finding labels, three-class status (present/absent/uncertain), and verbatim supporting evidence spans and demonstrates that locally deployable models can provide competitive and directly auditable radiology-report extraction without relying on externa...
Retrospection-Only Fine-Tuning (ROFT), a minimal online procedure designed to isolate the effect of explanation-only training on subsequent behavior, is studied, showing that learning to explain can also improve learning to do and motivating further study of explanation-to-action transfer.
Reach audiences
Advertise in front of researchers, engineers, and readers.
AI Night-Scientist is introduced, an agentic framework that uses reinforcement learning to teach models when and how to depart from predictable reasoning to suggest creativity is a learnable, multi-level ability that can be shaped to help researchers reach ideas beyond those typically explored by LLMs.
TCSAlgBench provides a refreshable testbed for measuring progress in model reasoning and studying how agent workflows support research-level proof discovery, and evaluates ten model configurations from four families under direct inference and prover-verifier discussion, and compares four agent workflows under matched m...
This work introduces artifact-mediated propagation, where adversarial content introduced through an artifact is stored in an assistant's persistent memory, reproduced in a subsequently created artifact, and acquired by another assistant that later reads it.
While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck. Direct ''SMILES-to-PDDL'' attempts fail because they force models to juggle chemical analysis and planning-language structuring simultaneously. We hypothesize that this failure stems from a lack of intermediate abstractio...
This work introduces SAGE (Self-Adapting Group of Experts), a training-free framework that uses answer agreement, prefix consistency, and reciprocal peer review to select a strategy donor and transfers the selected donor's reasoning strategy to the other agents while preserving their original roles.
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In production environments, where logits may be unavailable, robust black-box uncertainty quantification (UQ) is essential for trustworthiness and safety. Focusing on question-...
EvoIn is an agent fine-tuning framework that bridges evolution and internalization, and consistently enables agents to learn stronger decision-making procedures, raising the pass rate by 10.9 points in-domain and by 9.2 points out-of-domain.
This work proposes 5W1H+Which, a semantic indexing design that separates content extraction from ontology binding, and distinguishes business valid time, system knowledge time, and operational traces, and uses dependency records to support binding revalidation and the maintenance of derived conclusions.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
