Trending Research
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
To address this challenge, we introduce the first benchmark and metric suite for poster generation, which pairs recent conference papers with author-designed posters and evaluates outputs on (i)Visual Quality-semantic alignment with human posters, (ii)Textual Coherence-language fluency, (iii)Holistic Assessment-six fine-grained aesthetic and informational criteria scored by a VLM-as-judge, and notably (iv)PaperQuiz-the poster's ability to convey core paper content as measured by VLMs answering generated quizzes.
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters
tencent-hunyuan/hunyuanvideo-avatar
•
•
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.
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
nvlabs/queen
•
•
Online free-viewpoint video (FVV) streaming is a challenging problem, which is relatively under-explored.
RWKV-7 "Goose" with Expressive Dynamic State Evolution
fla-org/flash-linear-attention
•
•
We present RWKV-7 "Goose", a new sequence modeling architecture with constant memory usage and constant inference time per token.
Representing Long Volumetric Video with Temporal Gaussian Hierarchy
dendenxu/fast-gaussian-rasterization
•
•
In addition, the tree-like structure of the Gaussian hierarchy allows us to efficiently represent the scene at a particular moment with a subset of Gaussian primitives, leading to nearly constant GPU memory usage during the training or rendering regardless of the video length.
OmniAudio: Generating Spatial Audio from 360-Degree Video
To generate spatial audio from 360-degree video, we propose a novel framework OmniAudio, which leverages self-supervised pre-training using both spatial audio data (in FOA format) and large-scale non-spatial data.
Advanced long-term earth system forecasting by learning the small-scale nature
easylearningscores/triton_ai4earth
•
•
Reliable long-term forecast of Earth system dynamics is heavily hampered by instabilities in current AI models during extended autoregressive simulations.
SEW: Self-Evolving Agentic Workflows for Automated Code Generation
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks.
VACE: All-in-One Video Creation and Editing
ali-vilab/vace
•
•
Further pursuing the unification of generation and editing tasks has yielded significant progress in the domain of image content creation.
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
mingyin1/agents_failure_attribution
•
•
In this paper, we propose and formulate a new research area: automated failure attribution for LLM multi-agent systems.
