arXiv
A Mathematical Theory of Reusable Neural Bases for Network Compression
As large AI models become increasingly prevalent across a wide range of applications, memory cost has become a critic...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Scientific equation discovery has long been central to scientific progress, proceeding through iterative cycles of hy...
arXiv
BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net
Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patte...
arXiv
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that sha...
arXiv
H3-World: Turning Language Understanding into World Control
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world m...
arXiv
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the ...
arXiv
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as polic...
arXiv
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during L...
arXiv
Designing Proactive Thought Partners for Writing
Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals ...
arXiv
Mechanism Design for Alignment and Control
We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible a...
arXiv
The Rise of Verbal Reinforcement Learning
Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent...
arXiv
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility bri...