Test-time training could lead to LLMs that are better at complex reasoning
techxplore.com·1h
🏆LLM Benchmarking
Citrix NetScaler Memory Disclosure (CitrixBleed 2 CVE-2025-5777)
labs.watchtowr.com·17h·
Discuss: Hacker News
🔓Hacking
Query OpenStreetMap Using SQL
github.com·4h·
Discuss: Hacker News
💾Databases
Graph Diffusion-Based AeBS Deployment and Resource Allocation for RSMA-Enabled URLLC Low-Altitude Economy Networks
arxiv.org·13h
🏗️Infrastructure Economics
Conformal Information Pursuit for Interactively Guiding Large Language Models
arxiv.org·13h
🧠LLM Inference
Lambda calculus cooked N ways: Benchmarks for capture-avoiding substitution
github.com·21h·
Discuss: Hacker News
💻Programming languages
Controlling Thinking Speed in Reasoning Models
arxiv.org·13h
🧠LLM Inference
Federated Learning for Big Data: A Survey on Opportunities, Applications, and Future Directions
arxiv.org·13h
🌐Distributed systems
Reconstructing Biological Pathways by Applying Selective Incremental Learning to (Very) Small Language Models
arxiv.org·13h
💻Programming languages
Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
arxiv.org·13h
🛡️AI Safety
Skipper: Maximal Matching with a Single Pass over Edges
arxiv.org·13h
🔍Vector Search Algorithms
Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
arxiv.org·13h
🧠LLM Inference
On Jailbreaking Quantized Language Models Through Fault Injection Attacks
arxiv.org·13h
🕳LLM Vulnerabilities
Game-Theoretic Modeling of Vehicle Unprotected Left Turns Considering Drivers' Bounded Rationality
arxiv.org·13h
🆕New AI
Spatio-Temporal LLM: Reasoning about Environments and Actions
arxiv.org·13h
🏆LLM Benchmarking
Tractable Representation Learning with Probabilistic Circuits
arxiv.org·13h
🧠LLM Inference
Optimizing Shanghai's Household Waste Recycling Collection Program by Decision-Making based on Mathematical Modeling
arxiv.org·13h
🏗️Infrastructure Economics
AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
arxiv.org·13h
📊Vector Databases
The Frequency Response of Networks as Open Systems
arxiv.org·13h
🌐Distributed systems
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
arxiv.org·13h
🧠LLM Inference