Archive
Publication Timeline
18 Articles
2026
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
#AI
#NLP
#Novel Research
Agent-based Automated Claim Matching with Instruction-following LLMs
#AI
#NLP
#Novel Research
The 10,000x Explosion: Reproducing DeepSeek’s mHC at Scale
#AI
#NLP
#Technical
mHC: Manifold-Constrained Hyper-Connections
#AI
#NLP
#Novel Research
ConfTuner: Training Large Language Models to Express Their Confidence Verbally
#AI
#NLP
#Novel Research
The Zero Temperature Myth: Why "Greedy" Doesn't Always Mean "Same"
#AI
#NLP
#Technical
HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
#AI
#NLP
#Novel Research
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
#AI
#NLP
#Novel Research
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
#AI
#NLP
#Novel Research
2025
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
#AI
#NLP
#Novel Research
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
#AI
#NLP
#Novel Research
LightMem: Lightweight and Efficient Memory-Augmented Generation
#AI
#NLP
#Novel Research
The Cockpit of AI: A Beginner’s Guide to LLM Parameters
#AI
#Technical
BriLLM: Brain-inspired Large Language Model
#AI
#NLP
#Novel Research
Revisiting Long-Context Modeling From Context Denoising Perspective
#AI
#NLP
#Novel Research