collaborators

9 papers

cs.CL2026

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

Pengcheng Huang, Zhenghao Liu, Yukun Yan +8

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence. However, they remain susceptib…

cs.CL2026

SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

Ruochang Li, Pengcheng Huang, Zhenghao Liu +5

Retrieval-augmented generation (RAG) enhances LLMs by incorporating external knowledge to support response generation. However, conflicts between retrieved context and parametric k…

cs.CV2026

MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering

Qing Yang, Pengcheng Huang, Xinze Li +6

Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy…

cs.SE2026

Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction

Xingjie Gao, Pengcheng Huang, Zhenghao Liu +6

Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challen…

cs.LG2026

Revealing the Attention Floating Mechanism in Masked Diffusion Models

Xin Dai, Pengcheng Huang, Zhenghao Liu +6

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their…

cs.AI2026

Empirical Analysis of Decoding Biases in Masked Diffusion Models

Pengcheng Huang, Tianming Liu, Zhenghao Liu +5

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their…