From the 1 of 22 linked papers with an AI index.
22 papers
Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection
Hao Tan, Jun Lan, Zichang Tan +7
Veritas++ introduces a perception‑enhanced framework for detecting AI‑generated images by training models to capture fine‑grained visual details, semantic anomalies, and pixel‑leve…
Maintain Plasticity in Long-timescale Continual Test-time Adaptation
Yanshuo Wang, Xuesong Li, Jinguang Tong +5
Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods ha…
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
Yan Hong, Wei Li, Kedong Xiu +6
Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in non-updated behavior. Online d…
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
Yan Hong, Kedong Xiu, Wei Li +6
We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving gener…
Causal Probing for Internal Visual Representations in Multimodal Large Language Models
Zehao Deng, Tianjie Ju, Zheng Wu +5
Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concep…
Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
Yikun Ji, Yan Hong, Bowen Deng +5
The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs…