9 citations · 11 across the 14 of their papers we have counts for
15 papers
Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
Chenming Shang, Yujin Tang, Jun Jie Ou Yang +3
The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds only weak pointwise s…
Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance
Hengyuan Zhang, Chenming Shang, Zunhai Su +10
Best-of- is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths.…
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
Ruize Xu, Xiao Yu, Yujin Tang +2
How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state predi…
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Yujin Tang, Chenming Shang, Ruize Xu +1
Agent benchmarks for measuring memory largely study textual cases, in which information is deliberately extracted from the environment, written down, and then later retrieved. In o…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
Hengyuan Zhang, Shiping Yang, Xiao Liang +8
Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that strong…
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
Ling Yang, Xinchen Zhang, Ye Tian +4
The remarkable success of the autoregressive paradigm has made significant advancement in Multimodal Large Language Models (MLLMs), with powerful models like Show-o, Transfusion an…
AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance
Zhao Wang, Hao Wen, Lingting Zhu +3
Character video generation is a significant real-world application focused on producing high-quality videos featuring specific characters. Recent advancements have introduced vario…
ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework
Hengyuan Zhang, Chenming Shang, Sizhe Wang +6
Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the…
Incremental Residual Concept Bottleneck Models
Chenming Shang, Shiji Zhou, Hengyuan Zhang +3
Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predic…
Understanding Multimodal Deep Neural Networks: A Concept Selection View
Chenming Shang, Hengyuan Zhang, Hao Wen +1
The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-m…
A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models
Hengyuan Zhang, Zitao Liu, Chenming Shang +2
Knowledge tracing (KT) plays a crucial role in predicting students' future performance by analyzing their historical learning processes. Deep neural networks (DNNs) have shown grea…
Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning
Hengyuan Zhang, Zitao Liu, Shuyan Huang +3
Knowledge tracing (KT) aims to estimate student's knowledge mastery based on their historical interactions. Recently, the deep learning based KT (DLKT) approaches have achieved imp…
Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning
Hengyuan Zhang, Dawei Li, Yanran Li +3
The standard definition generation task requires to automatically produce mono-lingual definitions (e.g., English definitions for English words), but ignores that the generated def…
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
Kai Zhang, Shuhang Gu, Radu Timofte +60
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input im…