papers

Publications (74)

cs.CL2025

Unshackling Context Length: An Efficient Selective Attention Approach through Query-Key Compression

Haoyu Wang, Tong Teng, Tianyu Guo +4

Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either e…

cs.LG2026

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

Xutao Wang, Hanting Chen, Tianyu Guo +1

The paper proposes PUe, a framework that improves positive‑unlabeled (PU) learning under biased label selection by using normalized propensity scores and inverse probability weight…

#positive-unlabeled learning#selection bias#propensity scoring#causal inference
cs.LG2026

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing

Miao Rang, Zhenni Bi, Hang Zhou +6

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, t…

cs.CV2021

AdderNet: Do We Really Need Multiplications in Deep Learning?

Hanting Chen, Yunhe Wang, Chunjing Xu +4

Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-co…

cs.CV2024

Data Upcycling Knowledge Distillation for Image Super-Resolution

Yun Zhang, Wei Li, Simiao Li +6

Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models. However, cu…

cs.CL2024

Multi-Granularity Semantic Revision for Large Language Model Distillation

Xiaoyu Liu, Yun Zhang, Wei Li +7

Knowledge distillation plays a key role in compressing the Large Language Models (LLMs), which boosts a small-size student model under large teacher models' guidance. However, exis…