HuggingFace
Learning from the Self-future: On-policy Self-distillation for dLLMs
On-policy self-distillation (OPSD) has proven effective for post-training large language models (LLMs), yet its appli...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Text-Vision Co-Instructed Image Editing
Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based on...
arXiv
A Causal Model of Theory of Mind in Conflict for Artificial Intelligence
Theory of mind (ToM), the capacity to ascribe mental states to others and use those ascriptions for prediction and in...
arXiv
Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data
The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a priv...
arXiv
Probing Low Frame Rate Degradation in Neural Audio Codecs
Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost ...
arXiv
How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations
Incorporating textual reviews into a Recommender System has become a prominent strategy for enriching collaborative s...
arXiv
The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers
The reproducibility crisis has directed the AI research community toward improving documentation practices. Several s...
arXiv
Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification
Accurate Harmonized Tariff Schedule (HTS) code classification is essential for customs clearance, duty assessment, tr...
arXiv
Stable Menus of Public Goods: AI-Enabled Progress
Using an open problem from the EC 2025 paper "Stable Menus of Public Goods" as a testbed, we conduct experiments to u...
arXiv
When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning
Reinforcement Learning (RL) policies often degrade in unfamiliar environments because they lack explicit deliberation...
arXiv
ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation
Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it...
arXiv
Bayesian Inference and Decision Audits for Public Archives of Frontier AI Evaluations
Public AI evaluations are often read as terminal leaderboards, yet the underlying evidence is a selective time series...