The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models Paper • 2610.02191 • Published 10 days ago • 15
ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation Paper • 2602.10113 • Published Feb 10 • 2
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences Paper • 2606.00931 • Published May 30
Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding Paper • 2602.00854 • Published Jan 31
BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature Paper • 2601.16993 • Published Jan 12
VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results Paper • 2509.06413 • Published Sep 8, 2025
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries Paper • 2511.00710 • Published Nov 1, 2025 • 5
The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models Paper • 2610.02191 • Published 10 days ago • 15
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics Paper • 2603.14375 • Published Mar 15 • 19
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation Paper • 2603.16864 • Published Mar 17 • 18
PISCO: Precise Video Instance Insertion with Sparse Control Paper • 2602.08277 • Published Feb 9 • 13
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling Paper • 2602.09084 • Published Feb 9 • 30
Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models Paper • 2601.01321 • Published Jan 4 • 20
MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding Paper • 2507.12463 • Published Jul 16, 2025 • 27
SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Paper • 2506.07564 • Published Jun 9, 2025 • 6
mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation Paper • 2505.24073 • Published May 29, 2025
GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution Paper • 2505.00687 • Published May 1, 2025
mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation Paper • 2505.24073 • Published May 29, 2025