Retracing the Past: LLMs Emit Training Data When They Get Lost
arxiv.org·2h
🔬Synthetic Data
Flag this post
Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
arxiv.org·2h
🐻❄️Polars
Flag this post
Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning
arxiv.org·2h
🔄Data Engineering
Flag this post
AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent
arxiv.org·1d
⚙️Generators
Flag this post
Network and Risk Analysis of Surety Bonds
arxiv.org·2h
🔄Data Engineering
Flag this post
SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents
arxiv.org·1d
🐻❄️Polars
Flag this post
The Secret Life of Python: The String Intern Pool - When Two Strings Are One Object
🏷️Python Typing
Flag this post
Duality-based Mode Operations and Pyramid Multilayer Mapping for Rhetorical Modes
arxiv.org·2h
🎀Decorators
Flag this post
Adam symmetry theorem: characterization of the convergence of the stochastic Adam optimizer
arxiv.org·2h
🔲Ortholinear Keyboards
Flag this post
A Learning-Based Control Barrier Function for Car-Like Robots: Toward Less Conservative Collision Avoidance
arxiv.org·2h
🎀Decorators
Flag this post
Towards Optimal Constellation Design for Digital Over-the-Air Computation
arxiv.org·2h
📊Parquet
Flag this post
Reasoning Up the Instruction Ladder for Controllable Language Models
arxiv.org·1d
🎀Decorators
Flag this post
Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention
arxiv.org·2h
📓Jupyter Notebooks
Flag this post
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
arxiv.org·2h
🔄Data Pipelines
Flag this post
Multilingual Lexical Feature Analysis of Spoken Language for Predicting Major Depression Symptom Severity
arxiv.org·2h
📓Jupyter Notebooks
Flag this post
Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
arxiv.org·2h
🔄Data Engineering
Flag this post
ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning
arxiv.org·2h
🗺️OpenStreetMap
Flag this post
RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework
arxiv.org·2h
🔬Synthetic Data
Flag this post
Loading...Loading more...