Sign in
1.The Impact of Generative AI on Architectural Conceptual Design: Performance, Creative Self-Efficacy and Cognitive Load
Worcester Polytechnic Institute
Abstract
2.Structure and Diversity Aware Context Bubble Construction for Enterprise Retrieval Augmented Systems
Bravada Group; Eye Dream Pty Ltd
Abstract
3.Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
Shanghai Qi Zhi Institute; Tsinghua University
Abstract
4.Multi-Property Synthesis
University of Oxford; Rice University
Abstract
5.From Single to Multi-Agent Reasoning: Advancing GeneGPT for Genomics QA
University of Padua; Aalto University
Abstract
6.Generative AI collective behavior needs an interactionist paradigm
Fondazione Bruno Kessler; University of Trento; Not Diamond; City St. George’s University of London; Carnegie Mellon University; Massachusetts Institute of Technology; Stanford University; Google DeepMind; University of Chicago
Abstract
7.Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
Northeastern University
Abstract
8.A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Fudan University; Shanghai Innovation Institute; Deakin University; UIUC
Abstract
9.Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
Naval Surface Warfare Center Panama City Division
Abstract
10.Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment
German Research Center for Artificial Intelligence; Center for European Research in Trusted AI; Saarland Informatics Campus; TU Darmstadt; Hessian.AI
Abstract
11.Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge
National University of Defense Technology; Peking University; Tsinghua University; The Hong Kong University of Science and Technology
Abstract
12.ChartComplete: A Taxonomy-based Inclusive Chart Dataset
American University of Beirut
Abstract
13.NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
Tianjin University; Qfin Holdings, Inc.
Abstract
14.LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
Nanyang Technological University; Yunnan University; Yokohama National University; Xi’an Jiaotong University
Abstract
15.LADFA: A Framework of Using Large Language Models and Retrieval-Augmented Generation for Personal Data Flow Analysis in Privacy Policies
University of Kent; Honda Research Institute Europe GmbH
Abstract
16.ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics
Xi’an Jiaotong University; National University of Defense Technology; Shaanxi Province Key Laboratory of Big Data Knowledge Engineering
Abstract
17.Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Shanghai Jiao Tong University; Eigen AI; 3DP Technology; Beihang University
Abstract
18.LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
Fudan University; Pennsylvania State University Abington College
Abstract
19.C-GRASP: Clinically-Grounded Reasoning for Affective Signal Processing
National Central University; Center for Education
Abstract
20.Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning
Tongyi Lab; Alibaba Group
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