STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games
Research
Research News
New papers, breakthroughs and academic AI research
Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
Research
LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
Research
The Advantages of Fresh Sketching for Ridge Regression
Research
How Much Can Reliability Drift Under a Fixed Confidence Distribution?
Research
An Empirical Study of On-Device Translation for Real-Time Live-Stream Chat on Mobile Devices
Research
Predicting Multi-View Rashomon Representation: Can We Learn Where Models Disagree?
Research
Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing
Research
STEPS: Selective On-Policy Self-Distillation for Reasoning
Research
When Context Changes: Understanding Update Failures in LLMs
Research
Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions
Research
Consistent Plan-Act for Long-Horizon Agentic Tasks
Research