cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents
Research
Research News
New papers, breakthroughs and academic AI research
A Quantitative Study of Sustained Focus in Large Language Models via Repetitive Deterministic Prediction Tasks
Research
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Research
Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
Research
Question-Specific Knowledge Graphs for Efficient Visual Reasoning
Research
A Character-Level Neural Approach to Sinhala Sandhi Splitting
Research
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Research
Concept Direction Reliability Across Languages with Different Tokenizer Fertility
Research
FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models
Research
Learning from Teacher Continuations at Student States
Research
Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering
Research
The Canonical Order Problem: When Large Language Models Are Unreliable Knowledge Bases for Multi-Valued Relations
Research