Trending Research
RETSim: Resilient and Efficient Text Similarity
This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks.
Efficient Part-level 3D Object Generation via Dual Volume Packing
Recent progress in 3D object generation has greatly improved both the quality and efficiency.
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
To support further research, we release our open-source models along with a curated math reasoning-intensive corpus of over 70 billion tokens (i. e., MegaMath-Web-Pro-Max).
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction.
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
royshil/obs-backgroundremoval
•
•
MODNet is easy to be trained in an end-to-end manner.
Ranked #1 on
Image Matting
on PPM-100
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
k2-fsa/ZipVoice
•
•
Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters.
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.
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Finally, we show how self-supervised learning can be applied to robotic planning tasks by post-training a latent action-conditioned world model, V-JEPA 2-AC, using less than 62 hours of unlabeled robot videos from the Droid dataset.
Ranked #4 on
Video Question Answering
on TVBench
Efficient Reasoning Models: A Survey
Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer.
