HuggingFace
Using Grounded Theory for Agent Behavior Analysis at Scale
Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in lon...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origam...
HuggingFace
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
Multimodal models often build on architectures designed for generative vision-language modeling, typically combining ...
HuggingFace
Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
Spatial return models take the interaction matrix as given and leave feedback uninterpreted. We construct a bandwidth...
HuggingFace
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Portfolio risk assessment ordinarily relies on reliable estimates of cross-asset return covariances, which are diffic...
HuggingFace
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of...
HuggingFace
Small Language Models as Judges for Rubric-Based Reinforcement Learning
Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring res...
HuggingFace
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Agent performance depends jointly on the model parameters and the executable harness code that manages context and co...
HuggingFace
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
A language model's prediction of its next token develops across layers, and lens methods track this process by decodi...
HuggingFace
An Empirical Study on Zero-Data Bootstrapping for Conversational Recommender Systems
Conversational Recommender Systems (CRS) typically require domain-specific dialogue data, which is costly, scarce, an...
arXiv
Language Models Can Control Their Own Attention
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to fi...
arXiv
HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
Polymeric materials are central to modern technologies, with applications ranging from energy to health and transport...