Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
University of Haifa; Yale School of Medicine; Jönköping University
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
Peking University
Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling
Tianjin University; University of Nottingham Ningbo China
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
University of South Carolina; ALLT.AI, LLC; School of Medicine
Auditing the Risk Claims of Distributional Reinforcement Learning
Hari Prasad University
Interaction Scaling: Grounding the Third Axis of Test-Time Compute
Pine AI; University of Washington
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
The Chinese University of Hong Kong
HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference
Nanjing Vocational College of Information Technology
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
University of Bath; University of Ulster; Bath Institute for the Augmented Human
Comparative Analysis of GAT and BERT for Human-Like Playtesting
AI Center of Excellence; King
Enhancing Query Efficiency for d-DNNF Representations Through Preprocessing
CRIL, U. Artois; CNRS
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
Tongji University; The Hong Kong Polytechnic University; Shanghai Jiao Tong University
Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA
Chinese Academy of Sciences; University of Chinese Academy of Sciences; Tongyi Lab, Alibaba Group; Tsinghua University
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
University of California, San Diego; Aether AI Lab
OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis
Nankai University; Tsinghua University; Huawei Technologies Co., Ltd.
From Neural Network Decisions to Training Cases: An Exact Account via Case-Based Decision Theory
Huazhong University of Science and Technology
Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
The Hong Kong Polytechnic University; The University of Hong Kong; Zhejiang Normal University
AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic
Hunan University; Wuhan University of Technology; Huazhong University of Science and Technology
Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation
Central Conservatory of Music; Tsinghua University
Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors
Novelis Research