From the 1 of 14 linked papers with an AI index.
7 papers · 1 filter
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Ligong Han, Kai Xu, Hao Wang +3
The paper introduces Structured Newton Layer Parallelism (SNLP) to reduce the sequential nonlinear depth of encrypted Transformer inference under fully homomorphic encryption, achi…
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
Ningyuan Shi, Zhipeng Zhou, Hao Wang +2
Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most exi…
Uncertainty-Aware Reward Modeling for Stable RLHF
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. H…
SQuat: Subspace-orthogonal KV Cache Quantization
Hao Wang, Ligong Han, Kai Xu +1
The key-value (KV) cache accelerates LLMs decoding by storing KV tensors from previously generated tokens. It reduces redundant computation at the cost of increased memory usage. T…
Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning
Nikhil Shivakumar Nayak, Krishnateja Killamsetty, Ligong Han +8
Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. E…
Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
Aldo Pareja, Nikhil Shivakumar Nayak, Hao Wang +10
The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructure…