Cover Image

Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Ziliang, Xiao, Tianang, Zhang, Jusheng, Zheng, Yongsen, Chen, Xipeng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Understanding Extrapolation: a Causal Lens
by: Kong, Lingjing, et al.
Published: (2025)

CF-VLM:CounterFactual Vision-Language Fine-tuning
by: Zhang, Jusheng, et al.
Published: (2025)

Spectral Gating Networks
by: Zhang, Jusheng, et al.
Published: (2026)

Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification
by: Fan, Yijia, et al.
Published: (2025)

Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
by: Zhang, Jusheng, et al.
Published: (2026)

Broad Critic Deep Actor Reinforcement Learning for Continuous Control
by: Thalagala, Shiron, et al.
Published: (2024)

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
by: Gong, Zhuocheng, et al.
Published: (2024)

Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
by: Zhang, Zhongjian, et al.
Published: (2026)

A Causal Lens for Learning Long-term Fair Policies
by: Lear, Jacob, et al.
Published: (2025)

HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
by: Li, Yang, et al.
Published: (2023)

Guardian: Decoupling Exploration from Safety in Reinforcement Learning
by: Cai, Kaitong, et al.
Published: (2025)

ConceptLens: from Pixels to Understanding
by: Dalal, Abhilekha, et al.
Published: (2024)

A Retrospect to Multi-prompt Learning across Vision and Language
by: Chen, Ziliang, et al.
Published: (2025)

Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction
by: Zhong, Qimin, et al.
Published: (2025)

HCP-DCNet: A Hierarchical Causal Primitive Dynamic Composition Network for Self-Improving Causal Understanding
by: Lei, Ming, et al.
Published: (2026)

Learning Dynamics of VLM Finetuning
by: Zhang, Jusheng, et al.
Published: (2025)

Composition Vision-Language Understanding via Segment and Depth Anything Model
by: Huo, Mingxiao, et al.
Published: (2024)

Soft Tokens, Hard Truths
by: Butt, Natasha, et al.
Published: (2025)

Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction
by: Zou, Tao, et al.
Published: (2025)

Kolmogorov-Arnold Fourier Networks
by: Zhang, Jusheng, et al.
Published: (2025)

Rational ANOVA Networks
by: Zhang, Jusheng, et al.
Published: (2026)

Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities
by: Lin, Zheng, et al.
Published: (2023)

HistoLens: An Interactive XAI Toolkit for Verifying and Mitigating Flaws in Vision-Language Models for Histopathology
by: Vissapragada, Sandeep, et al.
Published: (2025)

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
by: Campbell, Declan, et al.
Published: (2024)

Scaling Capability in Token Space: An Analysis of Large Vision Language Model
by: Li, Tenghui, et al.
Published: (2024)

TableRAG: Million-Token Table Understanding with Language Models
by: Chen, Si-An, et al.
Published: (2024)

CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
by: Wang, Ruiqi, et al.
Published: (2026)

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
by: Chen, Jiangwei, et al.
Published: (2026)

Understanding and Mitigating Tokenization Bias in Language Models
by: Phan, Buu, et al.
Published: (2024)

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
by: Zhao, Chongyang, et al.
Published: (2026)

HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models
by: Xie, Zhinan, et al.
Published: (2025)

Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
by: Liu, Qinyi, et al.
Published: (2026)

A Causal Lens for Evaluating Faithfulness Metrics
by: Zaman, Kerem, et al.
Published: (2025)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
by: Wang, Chaoqi, et al.
Published: (2025)

Revealing Multimodal Causality with Large Language Models
by: Li, Jin, et al.
Published: (2025)

Causality for Large Language Models
by: Wu, Anpeng, et al.
Published: (2024)

CLEAR: Can Language Models Really Understand Causal Graphs?
by: Chen, Sirui, et al.
Published: (2024)

Optimizing Prompts for Large Language Models: A Causal Approach
by: Chen, Wei, et al.
Published: (2026)

Compositional Steering of Large Language Models with Steering Tokens
by: Radevski, Gorjan, et al.
Published: (2026)

The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
by: Mueller, Aaron, et al.
Published: (2024)