activity
20212024
most citedContrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition

15 citations · 24 across the 12 of their papers we have counts for

collaborators

12 papers

cs.LG2024

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Tianyu Guo, Druv Pai, Yu Bai +3

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks,…

cs.CL2024

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models

Ying Nie, Binwei Yan, Tianyu Guo +9

Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not b…

cs.CV20243 cited

SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation

Danni Yang, Jiayi Ji, Yiwei Ma +4

In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in appl…

stat.ML2024

Collaborative Heterogeneous Causal Inference Beyond Meta-analysis

Tianyu Guo, Sai Praneeth Karimireddy, Michael I. Jordan

Collaboration between different data centers is often challenged by heterogeneity across sites. To account for the heterogeneity, the state-of-the-art method is to re-weight the co…

cs.SD2024

A robust audio deepfake detection system via multi-view feature

Yujie Yang, Haochen Qin, Hang Zhou +4

With the advancement of generative modeling techniques, synthetic human speech becomes increasingly indistinguishable from real, and tricky challenges are elicited for the audio de…

cs.CL2023

Data-Free Distillation of Language Model by Text-to-Text Transfer

Zheyuan Bai, Xinduo Liu, Hailin Hu +3

Data-Free Knowledge Distillation (DFKD) plays a vital role in compressing the model when original training data is unavailable. Previous works for DFKD in NLP mainly focus on disti…