papers

Publications (10)

cs.CV2025

Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classification

Zequn Zeng, Yudi Su, Jianqiao Sun +6

Concept-based models can map black-box representations to human-understandable concepts, which makes the decision-making process more transparent and then allows users to understan…

cs.LG2026

Scaling Attention via Feature Sparsity

Yan Xie, Tiansheng Wen, Tangda Huang +4

Scaling Transformers to ultra-long contexts is bottlenecked by the cost of self-attention. Existing methods reduce this cost along the sequence axis through local window…

cs.LG2024

A Non-negative VAE:the Generalized Gamma Belief Network

Zhibin Duan, Tiansheng Wen, Muyao Wang +2

The gamma belief network (GBN), often regarded as a deep topic model, has demonstrated its potential for uncovering multi-layer interpretable latent representations in text data. I…

cs.LG2026

Beyond Spectral Decomposition: Bayesian Contrastive Learning and its Non-negative Formulation via Factor Analysis

Zhibin Duan, Tiansheng Wen, Yifei Wang +3

Factor analysis, often regarded as a Bayesian variant of matrix factorization, offers superior capabilities in capturing uncertainty, modeling complex dependencies, and ensuring ro…

cs.CV2024

HICEScore: A Hierarchical Metric for Image Captioning Evaluation

Zequn Zeng, Jianqiao Sun, Hao Zhang +5

Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to eval…

cs.LG2025

Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

Tiansheng Wen, Yifei Wang, Zequn Zeng +7

Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learn…

cs.IR2026

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

Lixuan Guo, Yifei Wang, Tiansheng Wen +3

Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions. However, thi…

cs.LG2026

CSRv2: Unlocking Ultra-Sparse Embeddings

Lixuan Guo, Yifei Wang, Tiansheng Wen +5

In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dens…

cs.LG2026

Route Experts by Sequence, not by Token

Tiansheng Wen, Yifei Wang, Aosong Feng +7

Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed num…

cs.LG2026

On the Position Bias of On-Policy Distillation

Yan Xie, Sijie Zhu, Tiansheng Wen +2

On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective…