The Cantor Experiment: Forcing a GPT-5-Class AI to Forget a Century of Math
🔁Fixed-Point Theory
Flag this post
ShadowLogic: Backdoors in Any Whitebox LLM
arxiv.org·8h
🛡️seL4
Flag this post
AI Models Write Code with Security Flaws 18–50% of the Time, New Study Finds
🏃Escape Analysis
Flag this post
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning
arxiv.org·1d
🎮Verification Games
Flag this post
OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data
arxiv.org·8h
📦OPAM
Flag this post
Efficient Curvature-aware Graph Network
arxiv.org·8h
🕸️Graph Theory
Flag this post
Incremental Selection of Most-Filtering Conjectures and Proofs of the Selected Conjectures
arxiv.org·8h
⏱️Computational Complexity
Flag this post
Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
arxiv.org·8h
❓Existential Types
Flag this post
Efficient Test-Time Retrieval Augmented Generation
arxiv.org·8h
📚Automata Learning
Flag this post
AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
arxiv.org·8h
🎯Hindley-Milner
Flag this post
Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs
arxiv.org·8h
🔲Cellular Automata
Flag this post
STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
arxiv.org·8h
🔲Cellular Automata
Flag this post
Enhanced Richardson Extrapolation via Adaptive Kernel Regression and Uncertainty Quantification
👁️Observability
Flag this post
Leakage-abuse Attack Against Substring-SSE with Partially Known Dataset
arxiv.org·8h
❓Existential Types
Flag this post
Code Smell 313 - Workslop Code
🔲Cellular Automata
Flag this post
Unleash AI Potential: Mastering Automated Data Labeling for Unprecedented Model Accuracy
✓Automated Theorem Proving
Flag this post
DynBERG: Dynamic BERT-based Graph neural network for financial fraud detection
arxiv.org·8h
🕸️Graph Theory
Flag this post
Loading...Loading more...