Forking: Sudden Overfitting Under Replay
Research
Research News
New papers, breakthroughs and academic AI research
DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
Research
CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight
Research
The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization
Research
Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay
Research
T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
Research
ReHoPER: Receding-Horizon Planning for Enhanced Reasoning
Research
The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention
Research
Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo
Research
A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models
Research
Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
Research
Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation
Research