Papers

Towards an Argumentative Foundation for Evaluative AI

Data-Driven Fire-Zone Segmentation for Improved Short-Term Wildfire Prediction

Application of Artificial Intelligence for Fraudulent Banking Operations Recognition

MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models

Evidence-RL: Towards Evidence-intensive Visual Reasoning

Skaling: Chinchilla’s Exponents Meet Kaplan’s Coupling

PROTECT-90: A Fault Dataset for Power System Protection

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning Paradigms for LLMs

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

ENVACE: INTERNALIZING ENVIRONMENT DYNAMICS VIA WORLD REHEARSAL FOR AGENTIC REINFORCEMENT LEARNING

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

WorldClaw: Agentic 3D Open-World Generation at Scale

INTERPRETABLE MEG DECODING OF PERCEIVED SPEECH: CORTICAL SOURCES AND THE STIMULUS FEATURES THAT DRIVE RETRIEVAL

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

AGENTOPSD: RECURSIVE SELF-DISTILLATION FOR AGENTIC REINFORCEMENT LEARNING

ACM: Agentic Context Management for Long Horizon Tasks

AI-based single-shot structured-light depth reconstruction for real-time laparoscopic surgical guidance

Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth

Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning

Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift

Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment