AI Research Papers Daily

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

Flow-GRPO: Training Flow Matching Models via Online RL

Scalable Chain of Thoughts via Elastic Reasoning

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models

3D Scene Generation: A Survey

FG-CLIP: Fine-Grained Visual and Textual Alignment

ICon: In-Context Contribution for Automatic Data Selection

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Generating Physically Stable and Buildable LEGO Designs from Text

LiftFeat: 3D Geometry-Aware Local Feature Matching

Crosslingual Reasoning through Test-Time Scaling

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

WaterDrum: Watermarking for Data-centric Unlearning Metric

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Vision-Language-Action Models: Concepts, Progress, Applications and Challenges

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning

Chain-of-Thought Tokens are Computer Program Variables