Trending Research
Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context
We construct a repository-level dataset PragmaticCode for method-completion in Java and evaluate MGD on it.
An Investigation of Incorporating Mamba for Speech Enhancement
This work aims to study a scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task.
Ranked #1 on
Speech Enhancement
on VoiceBank + DEMAND
Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information
alibaba-damo-academy/FunASR
•
•
In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set.
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
alibaba-damo-academy/FunASR
•
•
To the best of our knowledge, emotion2vec is the first universal representation model in various emotion-related tasks, filling a gap in the field.
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Compared to both open-source and proprietary models, InternVL 1. 5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks.
Ranked #6 on
Visual Question Answering
on MM-Vet
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
shi-labs/cumo
•
•
Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks.
Ranked #1 on
Visual Question Answering
on MMBench
(GPT-3.5 score metric)
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
We design models based off T5-Base and T5-Large to obtain up to 7x increases in pre-training speed with the same computational resources.
Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
However, due to a quadratic increase in memory during generating ultra-high-resolution images (e. g. 4096*4096), the resolution of generated images is often limited to 1024*1024.
