/recent-trend-paper

recent-trend-paper

2024

Title Publication Review Source
Mamba: Linear-Time Sequence Modeling with Selective State Spaces ICLR Blog Paper
Improving fine-grained understanding in image-text pre-training CV Blog Paper
DoLA: DECODING BY CONTRASTING LAYERS IMPROVES FACTUALITY IN LARGE LANGUAGE MODELS ICLR Blog Paper

2023

NLP

Title Publication Review Source
Do PLMs Know and Understand Ontological Knowledge? ACL Blog Paper
FRUIT: Faithfully Reflecting Updated Information in Text NAACL Blog Paper
CogAgent: A Visual Language Model for GUI Agents - Blog Paper
Generative Agents: Interactive Simulacra of Human Behavior UIST Blog Paper
UniMath: A Foundational and Multimodal Mathematical Reasoner EMNLP Blog Paper
Active Retrieval Augmented Generation EMNLP Blog Paper
PaperMage: A Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents EMNLP Blog Paper
Extractive Summarization via ChatGPT for Faithful Summary Generation EMNLP Blog Paper
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment EMNLP Blog Paper
Large language models are human-level prompt engineers ICLR Blog Paper
Improving the Domain Adaptation of Retrieval Augmented Generation(RAG) Models for Open Domain Question Answering TACL Blog Paper
Mistral 7B preprint Blog Paper

Computer Vision

Title Publication Review Source
Token Merging: Your ViT But Faster ICLR Blog Paper
Visual Programming: Compositional visual reasoning without training CVPR Blog Paper
AnyText: Multilingual Visual Text Generation And Editing CVPR Blog Paper
What the DAAM: Interpreting Stable Diffusion Using Cross Attention ACL Blog Paper
Erasing Concepts from Diffusion Models ICCV Blog Paper
Zero-shot Referring Image Segmentation with Global-Local Context Features CVPR Blog Paper

Recommender Systems

Title Publication Review Source
Learning Fair Graph Representations via Automated Data Augmentations ICLR Blog Paper
Going Beyond Local; Global-Graph-Enhanced Personalized News Recommendation RecSys Blog Paper
Cracking the Code of Negative Transfer: A Cooperative Game Theoretic Approach for Cross-Domain Sequential Recommendation CIKM Blog Paper
Goal-Oriented Multi-Modal Interactive Recommendation with Verbal and Non-Verbal Relevance Feedback RecSys Blog Paper
Of Spiky SVDs and Music Recommendation RecSys Blog Paper
Denoising Self-Attentive Sequential Recommendation RecSys Blog Paper
Interpretable User Retention Modeling in Recommendation RecSys Blog Paper
Diffusion Recommender Model SIGIR Blog Paper
GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation - Blog Paper
Collaborative filtering algorithms are prone to mainstream-taste bias RecSys Blog Paper

Multi-Modal

Title Publication Review Source
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models - Blog Paper
Osprey: Pixel Understanding with Visual Instruction Tuning - Blog Paper
TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation ICCV - Paper
Unifying Vision, Text, and Layout for Universal Document Processing CVPR Blog Paper

Speech

Title Publication Review Source
Robust Speech Recognition via Large-Scale Weak Supervision ICML Blog Paper

Others

Title Publication Review Source
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers ICLR Blog Paper
Are Emergent Abilities of Large Language Models a Mirage? NIPS Blog Paper
Two-way Multi-Label Loss CVPR Blog Paper

2022

Title Field Publication Review Source
Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation RecSys IJCAI Blog Paper
Do Prompt-Based Models Really Understand the Meaning of Their Prompts? NLP NAACL Blog Paper
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning NLP NIPS Blog Paper
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Multi-Modal CVPR Blog Paper
Rethinking Personalized Ranking at Pinterest: An End-to-End Approach RecSys RecSys Blog Paper