works on

From the 1 of 14 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…