AI
SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance
Researchers have developed a new method for launching denial-of-service (DoS) attacks against large ...
AI
Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
Researchers have tested five different techniques for improving language model outputs at test time,...
AI
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Researchers propose a new framework called SkillForge to help large language models resolve specific...
AI
Graphical Design of Interpretable Architectures
Researchers have developed a graphical notation system for designing interpretable AI architectures....
AI
MedUAG: Unified Understanding and Generation for Medical Multimodal Models
Researchers have developed a unified medical model called MedUAG that can unders...
AI
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Researchers have developed a new approach to training large language models for ...
AI
AlphaClifford: Efficient Clifford Synthesis and Transpilation with Model-based RL
Researchers have developed AlphaClifford, a model-based Reinforcement Learning f...
AI
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
Researchers propose a method called rEDMRec that compresses the reasoning proces...