3 papers
cs.CV2026
Stable Routing for Mixture-of-Experts in Class-Incremental Learning
Zirui Guo, Quan Cheng, Da-Wei Zhou +1
Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine pre-trained models with mixtu…
cs.AI2026
Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences
Quan Cheng
Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human fee…
cs.AI2026
Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones
Quan Cheng
This paper proposes and argues for a counterintuitive thesis: the truly valuable capabilities of large language models (LLMs) reside precisely in the part that cannot be fully capt…