Search Results for author:
Found 18 papers, 11 papers with code
Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method
Extensive experiments on our OmniVQA demonstrate the superiority of our proposed method in omnidirectional space (+6% improvement).
J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
The current focus of AI research is shifting from emphasizing model training towards enhancing evaluation quality, a transition that is crucial for driving further advancements in AI systems.
YuE: Scaling Open Foundation Models for Long-Form Music Generation
We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture.
Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis.
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
In this paper, we introduce LLaSE-G1, a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute.
ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges
By integrating visual elements and embedded programming logic, ScratchEval requires the model to process both visual information and code structure, thereby comprehensively evaluating its programming intent understanding ability.
Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation
However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions.
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
By enhancing the semantic ability of the codec, X-Codec significantly reduces WER in speech synthesis tasks and extends these benefits to non-speech applications, including music and sound generation.
MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models
Large vision-language models (LVLMs) have significantly improved multimodal reasoning tasks, such as visual question answering and image captioning.
FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
By intensive experimental studies, we demonstrate that the proposed method can generate better samples than SingSong, and accelerate the generation by at least 30 times.
FlashSpeech: Efficient Zero-Shot Speech Synthesis
The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation.
CoMoSVC: Consistency Model-based Singing Voice Conversion
The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable performances, producing natural audios with high similarity to the target timbre.
NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation
Since expert knowledge is hard to acquire, it hinders the flexibility to quickly design and tune digital synthesizers for diverse sounds.
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality.
Pairwise Point Cloud Registration using Graph Matching and Rotation-invariant Features
Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds.
Financial risk prediction with multi-round QA attention network. International Joint Conference on Artificial Intelligence
Financial risk prediction with multi-round QA attention network.
BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
Instead, BLVD aims to provide a platform for the tasks of dynamic 4D (3D+temporal) tracking, 5D (4D+interactive) interactive event recognition and intention prediction.
