Sign in
1.

OpenThoughts-Agent: Receitas de Dados para Modelos Agênticos

OpenThoughts-Agent: Data Recipes for Agentic Models

UC Berkeley; Stanford University; JSC; LAION; Open-Ψ(Open-Sci) Collective; University of Texas at Austin; Bespoke Labs; Laude Institute; UCLA; Harvard University & Harvard Medical School; TU Munich & Munich Center for Machine Learning; New York University; Medical University of South Carolina; The LLM Data Company; Oumi.AI; BenchFlow; Independent Researcher; Northeastern University; University of Wisconsin–Madison; University of Washington; TU Darmstadt; University of Southern California; UC San Diego; Amazon; Microsoft; Korea University; Cornell Tech; University of Michigan
Abstract
2.

Modelos Mundiais em Pedaços: Certificação Estrutural para Agentes Gerais

World Models in Pieces: Structural Certification for General Agents

School of Data Science, The Chinese University of Hong Kong, Shenzhen
Abstract
3.

Alinhando Tarefas a Objetivos: Estratégias de Ajuste Fino e Ajuste de Prompt para Modelos de Linguagem Pré-treinados Codificador-Decodificador

Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

University of Tehran
Abstract
4.

Avaliando o Avaliador: Lições da Avaliação de um Sistema de Análise de Dados Agentivo

Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System

Columbia University
Abstract
5.

Precisão e Satisfação em Diálogos de Múltiplas Interações com LLM para Avaliação de NFR

Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment

University of Maine; University of Notre Dame
Abstract
6.

Fazer diferença sem fazer diferença

Difference-Making without Making a Difference

University College London
Abstract
7.

Resolvendo Problemas Inversos de Sistemas Caóticos com Matching de Fluxo Condicional Bidirecional

Solving Inverse Problems of Chaotic Systems with Bidirectional Conditional Flow Matching

Westlake University; Georgia Institute of Technology; Chinese Academy of Sciences; Max-Planck-Institut für Astronomie; The Ohio State University
Abstract
8.

Avaliando Mudança de Distribuição no Reconhecimento de Atividades Humanas para Generalização de Domínio

Assessing Distribution Shift in Human Activity Recognition for Domain Generalization

The University of Texas at Austin
Abstract
9.

BluTrain: Um framework C++/CUDA para sistemas de IA

BluTrain: A C++/CUDA Framework for AI Systems

BluBridge Research
Abstract
10.

A Escala Pode Nos Salvar da Perda de Plasticidade em Grandes Modelos de Linguagem?

Can Scale Save Us From Plasticity Loss in Large Language Models?

Zyphra
Abstract
11.

Leis de Escala para Destilação de LLM Específica para Tarefas

Scaling Laws for Task-Specific LLM Distillation

NVIDIA
Abstract
12.

Treinamento e Inferência de IA Descentralizados com BlockTrain

Decentralised AI Training and Inference with BlockTrain

Spheroid Labs
Abstract
13.

Diagramas de Decisão Custo-Ótimos para Avaliação Estocástica de Funções Booleanas

Cost-Optimal Decision Diagrams for Stochastic Boolean Function Evaluation

Aalto University
Abstract
14.

LaGO: Orientação de Ação Latente para Aprendizado por Reforço Online

LaGO: Latent Action Guidance for Online Reinforcement Learning

University of Illinois Urbana-Champaign; National Yang Ming Chiao Tung University; Academia Sinica
Abstract
15.

CineCap: Raciocínio Estruturado com Âncoras Espaço-Temporais para Legendagem de Vídeos Cinematográficos

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

The Chinese University of Hong Kong; Xiamen University; Kuaishou Technology; National University of Singapore; Southern University of Science and Technology
Abstract
16.

SAFARI: Escalonamento da Atribuição de Falhas com Agentes em Horizonte Longo por meio de Investigação Ativa

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

AI Foundations, Capital One; General Intelligence Company of New York; Northwestern University
Abstract
17.

Themis: Um framework habilitado por IA explicável para Aprendizado por Reforço com Feedback Humano

Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback

University College Dublin
Abstract
18.

Quando as CQs Dão Errado: Desafios na Verificação de CQ com OE-Assist

When CQs Go Wrong: Challenges in CQ Verification with OE-Assist

University of Bologna; ISTC-CNR; Linköping University
Abstract
19.

Abstrações de Consultas em Acesso a Dados Baseado em Ontologias

Abstractions of Queries in Ontology-Based Data Access

LIRMM; Inria; University of Montpellier; CNRS
Abstract
20.

Tokenomics de IA: A Economia dos Tokens, Computação e Precificação em Modelos Fundacionais

AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models

New York University Tandon School of Engineering
Abstract

Why ChatPaper

  • Interest-Driven Paper Curation

    Describe your interests as you like, be it keywords or sentence, you’ll get relevant papers every day via AI semantic matching.

  • Top Conferences, One-Stop

    IJCAI, ICML, CVPR, KDD... Access papers from top AI conferences, all in one tool, for free.

  • Paper Management Made Easy

    Keep your research organized with our bookmarking feature. Build a well-structured knowledge hub at your fingertips.

  • Chat With Any Paper

    Got questions? Ask in ChatDOC with one single click. Use AI to pull data, clarify terms, and verify facts with our precise word-level tracing feature.

See how it works

Watch now 1 min