Trending Research
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
We outperform encoder-only models by a large margin on word-level tasks and reach a new unsupervised state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB).
LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition
This enables our method - namely LAndmark-based Facial Self-supervised learning LAFS), to learn key representation that is more critical for face recognition.
Multi-domain Learning for Updating Face Anti-spoofing Models
In this work, we study multi-domain learning for face anti-spoofing(MD-FAS), where a pre-trained FAS model needs to be updated to perform equally well on both source and target domains while only using target domain data for updating.
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i. e., high-resolution visual tokens, high-quality data, and VLM-guided generation.
Ranked #8 on
Visual Question Answering
on MM-Vet
The Unreasonable Ineffectiveness of the Deeper Layers
arcee-ai/PruneMe
•
•
We empirically study a simple layer-pruning strategy for popular families of open-weight pretrained LLMs, finding minimal degradation of performance on different question-answering benchmarks until after a large fraction (up to half) of the layers are removed.
UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
This paper presents the UniMER dataset to provide the first study on Mathematical Expression Recognition (MER) towards complex real-world scenarios.
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.
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
Although some large-scale pretrained vision encoders such as vision encoders in CLIP and DINOv2 have brought promising performance, we found that there is still no single vision encoder that can dominate various image content understanding, e. g., the CLIP vision encoder leads to outstanding results on general image understanding but poor performance on document or chart content.
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Answering real-world user queries, such as product search, often requires accurate retrieval of information from semi-structured knowledge bases or databases that involve blend of unstructured (e. g., textual descriptions of products) and structured (e. g., entity relations of products) information.
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
liming-ai/ControlNet_Plus_Plus
•
•
To this end, we propose ControlNet++, a novel approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency between generated images and conditional controls.
