3 citations · 7 across the 13 of their papers we have counts for
11 papers · 1 filter
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
Daijiao Liu, Huiyi Wang, Lina Yao +1
Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can yield highly similar trajecto…
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
Haodong Lu, Dong Gong
A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed agents face streams of relat…
One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning
Huiyi Wang, Daijiao Liu, Lina Yao +1
Low-rank adaptation (LoRA) has become the standard for parameter-efficient fine-tuning of large language models. Most LoRA variants follow a uniform-LR convention, applying a singl…
Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments
Zhichen Lai, Huan Li, Dalin Zhang +3
Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation. Existing methods emphasiz…
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
Chongyang Zhao, Mingsong Li, Haodong Lu +1
Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge.…
Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
Ruilin Tong, Haodong Lu, Yuhang Liu +1
Continual learning (CL) aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones. However, storing and replaying data is often infeasibl…
Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
Haodong Lu, Chongyang Zhao, Minhui Xue +3
Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based Mixture-of-Experts (MoE) methods…
Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learning
Chongyang Zhao, Dong Gong
Continual learning (CL) learns from a non-stationary data stream without storing or re-training on all seen samples. Meta-continual learning (MCL) casts CL as sequence prediction a…
Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
Huiyi Wang, Haodong Lu, Lina Yao +1
Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between…
Learning with Mixture of Prototypes for Out-of-Distribution Detection
Haodong Lu, Dong Gong, Shuo Wang +3
Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learnin…
NPCL: Neural Processes for Uncertainty-Aware Continual Learning
Saurav Jha, Dong Gong, He Zhao +1
Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge…