1 citations · 1 across the 12 of their papers we have counts for
14 papers
Rethinking Contextualization by Reinterpreting Attention Head Channels
Hakaze Cho, Haolin Yang, Zhun Sun +3
Contextualization, the core operation of language modeling, transmits information across words to build sentence-specific word representations. Prior works mainly study contextuali…
VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments
Haolin Yang, Yuxing Long, Zihan Yang +1
Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset constr…
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
Zhitao He, Haolin Yang, Rui Min +2
Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation…
Neuro-Symbolic Synergy for World Modeling
Hongyu Zhao, Siyu Zhou, Haolin Yang +2
Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where strict compliance with de…
Structure-Aware Robust Counterfactual Explanations via Conditional Gaussian Network Classifiers
Zhan-Yi Liao, Jaewon Yoo, Hao-Tsung Yang +1
Counterfactual explanation (CE) is a core technique in explainable artificial intelligence (XAI), widely used to interpret model decisions and suggest actionable alternatives. This…
NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
Haolin Yang, Yuxing Long, Zhuoyuan Yu +8
Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigati…
Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
Haolin Yang, Hakaze Cho, Kaize Ding +1
Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations a…
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
Haolin Yang, Hakaze Cho, Naoya Inoue
We investigate the mechanistic underpinnings of in-context learning (ICL) in large language models by reconciling two dominant perspectives: the component-level analysis of attenti…
Mechanism of Task-oriented Information Removal in In-context Learning
Hakaze Cho, Haolin Yang, Gouki Minegishi +1
In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate th…
Binary Autoencoder for Mechanistic Interpretability of Large Language Models
Hakaze Cho, Haolin Yang, Yanshu Li +2
Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoenco…
Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
Haolin Yang, Hakaze Cho, Yiqiao Zhong +1
The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either speci…
Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines
Guanrong Li, Haolin Yang, Xinyu Liu +3
In the era of generative AI, recommender systems are moving from precise prediction to trustworthy generation. Large language models (LLMs) support this shift by inferring user int…
Pareto Optimal Algorithmic Recourse in Multi-cost Function
Wen-Ling Chen, Hong-Chang Huang, Kai-Hung Lin +2
In decision-making systems, algorithmic recourse aims to identify minimal-cost actions to alter an individual features, thereby obtaining a desired outcome. This empowers individua…
PXGen: A Post-hoc Explainable Method for Generative Models
Yen-Lung Huang, Ming-Hsi Weng, Hao-Tsung Yang
With the rapid growth of generative AI in numerous applications, explainable AI (XAI) plays a crucial role in ensuring the responsible development and deployment of generative AI t…