2025-03-05s
2025
Wikipedia in the Era of LLMs: Evolution and Risks
·3967 words·19 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Huazhong University of Science and Technology
LLMs modestly affect Wikipedia, subtly altering content and potentially skewing NLP benchmarks.
SPIDER: A Comprehensive Multi-Organ Supervised Pathology Dataset and Baseline Models
·2619 words·13 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
AI Applications
Healthcare
🏢 HistAI
SPIDER: A comprehensive pathology dataset boosts AI diagnostic models.
RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification
·2593 words·13 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Hong Kong University of Science and Technology
RectifiedHR: Enables training-free high-resolution image generation via energy rectification, boosting both efficiency and effectiveness.
Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content
·3985 words·19 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Shanghai Jiao Tong University
Q-Eval-100K: A new, large dataset for evaluating visual quality and text alignment in AI-generated content.
Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
·2943 words·14 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Shanghai Jiao Tong University
Mask-DPO: Fine-grained Factuality Alignment improves LLMs’ factuality by masking sentence-level errors during DPO training for enhanced knowledge alignment.
Language Models can Self-Improve at State-Value Estimation for Better Search
·2765 words·13 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Reinforcement Learning
🏢 Georgia Institute of Technology
Self-Taught Lookahead improves LLM search via self-supervision, matching costly methods at a fraction of the compute!
Iterative Value Function Optimization for Guided Decoding
·2523 words·12 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Text Generation
🏢 Shanghai Artificial Intelligence Laboratory
IVO: Iterative Value Function Optimization for Guided Decoding
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
·3403 words·16 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Reinforcement Learning
🏢 University of Illinois Urbana-Champaign
MultiAgentBench: A benchmark for evaluating collaboration and competition in LLM agents across diverse, interactive scenarios with novel metrics and protocols.
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking
·3011 words·15 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Question Answering
🏢 FPT Software AI Center, Viet Nam
SemViQA: A new approach to boost Vietnamese fact-checking with semantic understanding and efficient evidence retrieval.
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
·3445 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Text Generation
🏢 Tsinghua University
FR-Spec: Frequency-Ranked Speculative Sampling accelerates LLMs by optimizing vocabulary space compression, achieving 1.12x speedup over EAGLE-2.