paper-with-me

홈 › Papers

BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding

2026-01-04 · Hongbing Li, Linhui Xiao, Zihan Zhao, Qi Shen, Yixiang Huang, Bo Xiao, Zhanyu Ma arxiv

Visual Grounding (VG), which aims to locate a specific region referred to by expressions, is a fundamental yet challenging task in the multimodal understanding fields. While recent grounding transfer works have advanced the field through one-tower architectures, they still suffer from two primary limitations: (1) over-entangled multimodal representations that exacerbate deceptive modality biases, and (2) insufficient semantic reasoning that hinders the comprehension of referential cues. In this paper, we propose BARE, a bias-aware and reasoning-enhanced framework for one-tower visual grounding. BARE introduces a mechanism that preserves modality-specific features and constructs referential semantics through three novel modules: (i) language salience modulator, (ii) visual bias correction and (iii) referential relationship enhancement, which jointly mitigate multimodal distractions and enhance referential comprehension. Extensive experimental results on five benchmarks demonstrate that BARE not only achieves state-of-the-art performance but also delivers superior computational efficiency compared to existing approaches. The code is publicly accessible at https://github.com/Marloweeee/BARE.

📄 PDF Abstract BibTeX arXiv:2601.01526

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyVisual Grounding

Similar Papers 제목 키워드 기반

FairRank: Fairness-aware Single-tower Ranking Framework for News Recommendation

2022-04-01 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang

Single-tower models are widely used in the ranking stage of news recommendation to accurately rank candidate news according to their fine-grained relatedness with user interest indicated by user behaviors. However, these…

AttributeFairnessNews Recommendation

Rethinking the Illusion of Thinking

2025-07-01 · Iñaki Dellibarda Varela, Pablo Romero-Sorozabal, Eduardo Rocon, Manuel Cebrian arxiv

Earlier this year, Apple ignited controversy by publishing "The Illusion of Thinking," prompting heated debate within the AI community. Critics seized upon the findings as conclusive evidence that Large Reasoning Models …

Relational inductive bias for physical construction in humans and machines

2018-06-04 · Jessica B. Hamrick, Kelsey R. Allen, Victor Bapst, Tina Zhu 외

While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these …

Deep Reinforcement LearningInductive BiasObjectReinforcement Learning

Towards Disentangling Relevance and Bias in Unbiased Learning to Rank

2022-12-28 · Yunan Zhang, Le Yan, Zhen Qin, Honglei Zhuang 외

Unbiased learning to rank (ULTR) studies the problem of mitigating various biases from implicit user feedback data such as clicks, and has been receiving considerable attention recently. A popular ULTR approach for real-…

Learning-To-Rank

Analysis of Optimality of Large Language Models on Planning Problems

2026-04-03 · Bernd Bohnet, Michael C. Mozer, Kevin Swersky, Wil Cunningham 외 arxiv

Classic AI planning problems have been revisited in the Large Language Model (LLM) era, with a focus of recent benchmarks on success rates rather than plan efficiency. We examine the degree to which frontier models reaso…