Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
Paper
•
2512.04844
•
Published
•
4
CL
-
-
Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
Paper • 2512.03125 • Published • 1 -
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Paper • 2511.11007 • Published • 15 -
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 42 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 18 -
AI & Human Co-Improvement for Safer Co-Superintelligence
Paper • 2512.05356 • Published • 8 -
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Paper • 2511.12710 • Published • 38 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 125 -
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 140