arXiv
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga
Comics are one of the great visual records of the twentieth century: hundreds of thousands of pages in which a mass r...
arXiv
X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of th...
arXiv
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing met...
arXiv
Task Context Shapes Component Roles in Language Models
Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explai...
arXiv
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
While deep learning models for tabular data have recently received significant research attention, the choice of obje...
arXiv
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Con...
arXiv
Can Language Models Play the Wikipedia Game?
Language models increasingly support or automate information retrieval from document collections too large to index. ...
HuggingFace
Recurrent Harness for Agentic Continual Learning
Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution...
HuggingFace
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods su...
HuggingFace
Reflex: Visually Grounded Reactive Humanoid Control
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a pas...
HuggingFace
Continually Post-training Small Models via Synthetic Self-distillation
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while...