🏢 Alibaba Group

ChatAnyone: Stylized real-time portrait video generation with hierarchical motion diffusion model.

TaoAvatar: Lifelike talking avatars in AR, using 3D Gaussian Splatting for real-time rendering and high fidelity.

LHM: Animatable 3D avatars from a single image in seconds.

WritingBench: A new benchmark for generative writing evaluation, enhancing LLMs across diverse domains.

R1-Omni: RLVR enhances multimodal emotion recognition, boosting reasoning and generalization.

EMO2 achieves realistic audio-driven avatar video generation by employing a two-stage framework: first generating hand poses directly from audio and then using a diffusion model to synthesize full-bod…

Textoon: Generating vivid 2D cartoon characters from text descriptions in under a minute, revolutionizing animation workflow.

HiFi-SR: A unified generative network achieves high-fidelity speech super-resolution, outperforming existing methods by seamlessly integrating transformer and convolutional components for end-to-end a…

DiffuEraser: a novel video inpainting model based on stable diffusion, surpasses existing methods by using injected priors and temporal consistency improvements for superior results.

CODEELO benchmark uses CodeForces to fairly evaluate LLMs’ coding abilities, providing human-comparable Elo ratings and addressing limitations of existing benchmarks.

CodeArena, a novel benchmark, evaluates code LLMs based on human preferences, revealing performance gaps between open-source and proprietary models, and a large-scale synthetic instruction corpus impr…

Boost LLM accuracy exponentially by using a two-stage algorithm with provable scaling laws: generate multiple candidate solutions then compare them in a knockout tournament!

TeaCache: a training-free method boosts video diffusion model speed by up to 4.41x with minimal quality loss by cleverly caching intermediate outputs.

M2RC-EVAL: A new massively multilingual benchmark for repository-level code completion, featuring fine-grained annotations and a large instruction dataset, enabling better evaluation of code LLMs acro…