Tracked topic
GitHub is a web-based platform for hosting and collaborating on software using Git version control, offering features such as pull requests.
…In practice, ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches produced by image-editing denoising , using them as…
…remaining competitive on standard pixel-level metrics. The benchmarks and model will be made open-source at https://github.com/Luo-Z13/EO-WM. View arXiv page View PDF GitHub 28 Add…
…it adds only 5.2% to the captioning time, compared with 65.4% for CSTA and 211.9% for MaxInfo. We release our code and pre-trained checkpoint at https://github.com…
…https://github.com/PKU-YuanGroup/TIDE 🌐 Project: https://pku-yuangroup.github.io/TIDE-Page/ 🤗 Models: https://huggingface.co/TIDE-dllm/models 📚 Data: https://huggingface.co/TIDE-dllm/datasets reverse CALM is…
…View arXiv page View PDF Project page GitHub 136 Add to collection Community 🚀 CDM: High-Fidelity 4-Step Image Generation without GANs/Reward Models! We are excited to present Continuous-Time Distribution…
…AI-generated summary Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content. Distilling such generators from high-fidelity bidirectional teachers yields competitive few…
…competitive performance on mainstream audio tasks while unlocking capabilities inaccessible to offline LALMs, including real-time ASR, streaming audio instruction following, and proactive help. View arXiv page View PDF Project page GitHub…
…View arXiv page View PDF Project page GitHub 123 Add to collection Community On long-horizon tasks, an LLM agent has to manage a lot of memory — what to write down, what…
…Code and demos are available at https://data2story.github.io. View arXiv page View PDF Project page GitHub 132 Add to collection Community Can an AI agent act like an editor, turning…
…GitHub 2 Add to collection Community LLM agents often need memory to solve tasks in new tool environments, but memory is usually built only after seeing human tasks or deployment-time user…