Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
Research
Research News
New papers, breakthroughs and academic AI research
Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance
Research
Behavioral Coherence: A Method for Sensitive-Domain LLM Evaluation
Research
A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities
Research
Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support
Research
Teach and Grow: An Agent-Centered Architecture for General Robot Learning
Research
Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models
Research
Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability
Research
Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
Research
Model-Aware Data Cleaning for Tabular Foundation Models
Research
The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion
Research
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
Research