activity
20242026
collaborators

8 papers

cs.LG2026

IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning

Wei Zhang, Xinwu Liu, Yihang Cheng

Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT) of LLMs whose effectiveness depends on rank allocation. Existing adaptive LoRA method…

cs.LG2026

Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents

Kexin Chu, Dawei Xiang, Wei Zhang

Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers, or LLM backends exposed be…

cs.AI2026

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Junwei Liao, Haoting Shi, Ruiwen Zhou +9

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…

cs.CV2026

Probing Routing-Conditional Calibration in Attention-Residual Transformers

Wenhao Liang, Lin Yue, Wei Emma Zhang +4

Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly accompany predictions with sampl…

cs.AI2026

Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning

Siyu Wu, Cong Xu, Wei Zhang

Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy…

cs.AI2025

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation

Huimin Xu, Xin Mao, Feng-Lin Li +4

Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte C…