Search Results for author:
Found 17 papers, 10 papers with code
Composite Indicator-Guided Infilling Sampling for Expensive Multi-Objective Optimization
This indicator simultaneously considers convergence, diversity, and distribution to improve the efficiency of identifying promising candidate solutions, which significantly improves algorithm performance.
Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks
Temporal predictive models have the potential to improve decisions in health care, public services, and other domains, yet they often fail to effectively support decision-makers.
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unified multimodal systems with structural simplicity and efficient deployment.
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data
Despite the availability of several open-source multimodal datasets, limitations in the scale and quality of open-source instruction data hinder the performance of VLMs trained on these datasets, leading to a significant gap compared to models trained on closed-source data.
Ranked #4 on
Image Generation
on TextAtlasEval
InstructBioMol: Advancing Biomolecule Understanding and Design Following Human Instructions
Understanding and designing biomolecules, such as proteins and small molecules, is central to advancing drug discovery, synthetic biology, and enzyme engineering.
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Extensive experiments demonstrate the effectiveness of the proposed framework in both image reconstruction and downstream machine vision tasks such as object detection, segmentation, and facial landmark detection, achieving superior perceptual quality compared to state-of-the-art methods.
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
To facilitate the cutting-edge research of MLLMs on comprehensive vision perception, we thereby propose Perceptual Fusion, using a low-budget but highly effective caption engine for complete and accurate image descriptions.
Ranked #127 on
Visual Question Answering
on MM-Vet
Unveiling Encoder-Free Vision-Language Models
Training pure VLMs that accept the seamless vision and language inputs, i. e., without vision encoders, remains challenging and rarely explored.
Scientific Large Language Models: A Survey on Biological & Chemical Domains
Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelligence.
LEAD: Exploring Logit Space Evolution for Model Selection
The remarkable success of "pretrain-then-finetune" paradigm has led to a proliferation of available pre-trained models for vision tasks.
InstructProtein: Aligning Human and Protein Language via Knowledge Instruction
To address this challenge, we propose InstructProtein, an innovative LLM that possesses bidirectional generation capabilities in both human and protein languages: (i) taking a protein sequence as input to predict its textual function description and (ii) using natural language to prompt protein sequence generation.
Exploring Model Transferability through the Lens of Potential Energy
The experimental results on 10 downstream tasks and 12 self-supervised models demonstrate that our approach can seamlessly integrate into existing ranking techniques and enhance their performances, revealing its effectiveness for the model selection task and its potential for understanding the mechanism in transfer learning.
Modeling Uncertain Feature Representation for Domain Generalization
In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.
Masked Image Modeling with Denoising Contrast
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up.
mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning.
Uncertainty Modeling for Out-of-Distribution Generalization
In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
Generalizable Person Re-identification with Relevance-aware Mixture of Experts
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
