Category: Papers

1. Video-R1: Reinforcing Video Reasoning in MLLMs 🔑 Keywords: Video Reasoning, T-GRPO Algorithm, Multi-Modal Large Language Models, Temporal Modeling, Video-R1 💡 Category: […]

1. Qwen2.5-Omni Technical Report 🔑 Keywords: Multimodal model, End-to-end, Thinker-Talker architecture, TMRoPE, Streaming 💡 Category: Multi-Modal Learning 🌟 Research Objective: – The […]

1. When Less is Enough: Adaptive Token Reduction for Efficient Image Representation 🔑 Keywords: Collection, Knowledge Representation, AI Systems 💡 Category: Knowledge […]

1. φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation 🔑 Keywords: Collection 💡 Category: Knowledge Representation and Reasoning 🌟 Research […]

1. RWKV-7 “Goose” with Expressive Dynamic State Evolution 🔑 Keywords: Collection 💡 Category: Knowledge Representation and Reasoning 🌟 Research Objective: – To […]

1. ReCamMaster: Camera-Controlled Generative Rendering from A Single Video Collection 1. Multi-Modal Learning 2. Generative Models 3. Reinforcement Learning 4. Computer Vision […]

1. CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing 🔑 Keywords: Collection 💡 Category: Foundations of AI 🌟 Research Objective: – Investigate […]

1. TPDiff: Temporal Pyramid Video Diffusion Model 🔑 Keywords: Collection 💡 Category: Foundations of AI 🌟 Research Objective: – The paper focuses […]

1. Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Collection 🔑 Keywords: Collection 💡 Category: Foundations of […]

1. Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders 🔑 Keywords: Collection 💡 Category: Foundations of AI 🌟 Research Objective: – […]

1. START: Self-taught Reasoner with Tools 🔑 Keywords: Large reasoning models, Chain-of-thought, External tools, Self-taught reasoner, Hint-infer 💡 Category: Knowledge Representation and […]

1. Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers 🔑 Keywords: Large language models, Multilingual, Open-source, Performance, Fine-tuning […]