Agent Memory Is a Surface for Endogenous Authorization Laundering
Paper • 2609.01836 • Published • 6 •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commentedon a paper about 16 hours ago
Agent Memory Is a Surface for Endogenous Authorization Laundering commentedon a paper about 16 hours ago
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models commentedon a paper about 16 hours ago
MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information RetrievalOrganizations
commented 5
papers about 16 hours ago
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
Paper • 2608.30751 • Published • 3 •
2
MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval
Paper • 2608.30949 • Published • 8 •
2
VibeVoice-ASR-Streaming Technical Report
Paper • 2609.02812 • Published • 14 •
2
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Paper • 2609.00196 • Published • 29 •
2
updated a
dataset about 16 hours ago
commented 14
papers about 16 hours ago
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Paper • 2609.01936 • Published • 2 •
2
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Paper • 2609.02496 • Published • 2 •
3
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation
Paper • 2608.29846 • Published • 15 •
2
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 236 •
4
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 512 •
3
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Paper • 2608.29692 • Published • 1 •
2
ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
Paper • 2609.01865 • Published • 6 •
2
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
Paper • 2609.01740 • Published • 23 •
2
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation
Paper • 2609.02272 • Published • 6 •
2
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
Paper • 2609.01657 • Published • 24 •
2
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
Paper • 2609.00638 • Published • 68 •
2
Aspire: Can Models Self-Evolve from Vague Goals?
Paper • 2608.31111 • Published • 210 •
2
Language Models Can Control Their Own Attention
Paper • 2609.02737 • Published • 59 •
3
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
Paper • 2609.00377 • Published • 3 •
2