activity
20242026
collaborators

11 papers

cs.LG2026

On the Geometry of On-Policy Distillation

Zhennan Shen, Yanshu Li, Qingyu Yin +6

On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O…

cs.CL2026

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

Chengguang Gan, Sunbowen Lee, Qingyu Yin +9

The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improve each other when jointly modele…

cs.AI2026

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering

Chak Tou Leong, Dingwei Chen, Heming Xia +4

Large reasoning models (LRMs) have achieved remarkable success in complex problem-solving, yet they often suffer from computational redundancy or reasoning unfaithfulness. Current…

cs.CL2025

Probing the Difficulty Perception Mechanism of Large Language Models

Sunbowen Lee, Qingyu Yin, Chak Tou Leong +5

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an es…

cs.SD2025

PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis

Dinghao Zou, Yicheng Gong, Xiaokang Li +2

Multimodal music emotion analysis leverages both audio and MIDI modalities to enhance performance. While mainstream approaches focus on complex feature extraction networks, we prop…

cs.SD2025

Emoanti: audio anti-deepfake with refined emotion-guided representations

Xiaokang Li, Yicheng Gong, Dinghao Zou +2

Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained s…