FERPO: Forward Entropy-Regularized Policy Optimization
Research
Research News
New papers, breakthroughs and academic AI research
Two Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales Unfold
Research
The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating
Research
Hardening Soft Information: Evidence on Analyst Integration Costs
Research
Universal interpolation for deep residual self-attention networks
Research
Augmented Equivariant Mesh Networks for Anatomical Segmentation
Research
REALM: Retrospective Encoder Alignment for LFP Modeling
Research
Subtoken Vision Transformer for Fine-grained Recognition
Research
Towards Subject Consistency over Dynamic Subject Sets in Video Generation
Research
The Price of Correlated Tests: How Strict Should a Model Release Gate Be?
Research
When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts
Research
Learning ab initio phase-field models
Research