7 papers
Denser Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu +7
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgett…
Practical Continual Forgetting for Pre-trained Vision Models
Hongbo Zhao, Fei Zhu, Bolin Ni +3
For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests ori…
VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
Hongbo Zhao, Meng Wang, Fei Zhu +5
The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC)…
MLLM-CL: Continual Learning for Multimodal Large Language Models
Hongbo Zhao, Fei Zhu, Haiyang Guo +4
Recent Multimodal Large Language Models (MLLMs) excel in vision-language understanding but face challenges in adapting to dynamic real-world scenarios that require continuous integ…
Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning
Geng Liu, Fei Zhu, Rong Feng +4
Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continua…
TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data
Fei Zhu, Zhaoxiang Zhang
Reliable prediction is an essential requirement for deep neural models that are deployed in open environments, where both covariate and semantic out-of-distribution (OOD) data aris…