Trending Research
SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video
Video body-swapping aims to replace the body in an existing video with a new body from arbitrary sources, which has garnered more attention in recent years.
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert annotated benchmark for evaluating ALMs on long audio understanding capabilities.
Visual-RFT: Visual Reinforcement Fine-Tuning
Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce.
Few-Shot Object Detection
Fine-Grained Image Classification
+4
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
pku-alignment/align-anything
•
•
In this work, we make the first attempt to fine-tune all-modality models (i. e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions.
Lanpaint: Training-Free Diffusion Inpainting with Exact and Fast Conditional Inference
Diffusion models generate high-quality images but often lack efficient and universally applicable inpainting capabilities, particularly in community-trained models.
PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC
From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture that decomposes decision-making processes into Instruction-Subtask-Action levels.
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
We present MM-Eureka, a multimodal reasoning model that successfully extends large-scale rule-based reinforcement learning (RL) to multimodal reasoning.
Scaling Synthetic Data Creation with 1,000,000,000 Personas
lightaime/camel
•
•
We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Video inpainting, which aims to restore corrupted video content, has experienced substantial progress.
Atom of Thoughts for Markov LLM Test-Time Scaling
Based on this observation, we propose Atom of Thoughts (AoT), where each state transition in the reasoning process consists of decomposing the current question into a dependency-based directed acyclic graph and contracting its subquestions, forming a new atomic question state.
