HuggingFace
Safin-1: Safety from Within through Memory-Native State Evolution
Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt o...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver performance can pl...
HuggingFace
Agents in the Large: Perception-Centered Architecture for Persistent Agents
Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and dec...
HuggingFace
Recursive Criticality of AI Self-Improvement
AI is increasingly used in the R\&D process that produces future AI systems. We study the conditions under which this...
HuggingFace
Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth ...
HuggingFace
EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants
Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an exe...
HuggingFace
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model...
HuggingFace
ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we ...
HuggingFace
SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models
Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-ca...
HuggingFace
MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal Misinformation
Multimodal misinformation on social media is highly prevalent, potent, and harmful, yet difficult to detect and count...
HuggingFace
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Chain-of-thought (CoT) reasoning has dramatically improved large language models (LLMs) by allowing them to decompose...
HuggingFace
RECAP-Forcing: Retaining Content Appearances for Long Video Generation
Long autoregressive video generation faces a fundamental memory challenge: with a finite attention window, a model mu...