Trending Research
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters
tencent-hunyuan/hunyuanvideo-avatar
?
?
26 May 2025
This ensures the dynamic motion and strong character consistency; (ii) An Audio Emotion Module (AEM) is introduced to extract and transfer the emotional cues from an emotion reference image to the target generated video, enabling fine-grained and accurate emotion style control; (iii) A Face-Aware Audio Adapter (FAA) is proposed to isolate the audio-driven character with latent-level face mask, enabling independent audio injection via cross-attention for multi-character scenarios.
Emerging Properties in Unified Multimodal Pretraining
ByteDance-Seed/Bagel
?
?
20 May 2025
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems.
AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment
In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes.
RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
microsoft/renderformer
?
?
28 May 2025
We present RenderFormer, a neural rendering pipeline that directly renders an image from a triangle-based representation of a scene with full global illumination effects and that does not require per-scene training or fine-tuning.
WebDancer: Towards Autonomous Information Seeking Agency
We instantiate this framework in a web agent based on the ReAct, WebDancer.
syftr: Pareto-Optimal Generative AI
datarobot/syftr
?
?
26 May 2025
Retrieval-Augmented Generation (RAG) pipelines are central to applying large language models (LLMs) to proprietary or dynamic data.
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
bytedance/dolphin
?
?
20 May 2025
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables.
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning.
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
index-tts/index-tts
?
?
8 Feb 2025
Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities. Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model.
ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation.
