Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

✦

Analysis 2026.06.02

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

✦

Analysis 2026.06.01

Stateful Online Monitoring Catches Distributed Agent Attacks

✦

Analysis 2026.05.31

Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching

✦

Analysis 2026.05.30

Unlocking the Working Memory of Large Language Models for Latent Reasoning

✦

Analysis 2026.05.29

Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software

✦

Analysis 2026.05.28

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective