3 citations · 8 across the 31 of their papers we have counts for
6 papers · 1 filter
DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment
Henan Sun, Zehua Li, Haitao Hu +4
Reinforcement learning (RL) has emerged as a key paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing reward systems, such as rule-b…
PhyMo: A Physical-Field Modality for Multimodal AI4Physics
Henan Sun, Haitao Hu, Jin Liu +4
Multimodal learning is emerging as a powerful paradigm for AI for Physics (AI4Physics), where predicting physical systems requires the joint interpretation of heterogeneous observa…
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Yan Wang, Qifan Zhang, Jiachen Yu +12
Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…
Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
Yifan Niu, Han Xiao, Dongyi Liu +2
As Large Language Models (LLMs) are increasingly deployed in real-world applications, it is important to ensure their behaviors align with human values, societal norms, and ethical…
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
Jiashun Cheng, Aochuan Chen, Nuo Chen +4
Low-Rank Adaptation (LoRA) has emerged as a prominent technique for fine-tuning large foundation models. Despite its successes, the substantial parameter redundancy, which limits t…
ControlMath: Controllable Data Generation Promotes Math Generalist Models
Nuo Chen, Ning Wu, Jianhui Chang +1
Utilizing large language models (LLMs) for data augmentation has yielded encouraging results in mathematical reasoning. However, these approaches face constraints in problem divers…