Arrow Research search

Author name cluster

Amirmohammad Izadi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

TMLR Journal 2025 Journal Article

CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives

  • Armin Saghafian
  • Amirmohammad Izadi
  • Negin Hashemi Dijujin
  • Mahdieh Soleymani Baghshah

Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose \textbf{CAREL} (\textit{\textbf{C}ross-modal \textbf{A}uxiliary \textbf{RE}inforcement \textbf{L}earning}) as a new framework to solve this problem using auxiliary loss functions inspired by video-text retrieval literature and a novel method called instruction tracking, which automatically keeps track of progress in an environment. The results of our experiments suggest superior sample efficiency and systematic generalization for this framework in multi-modal reinforcement learning problems.

PDF Details

NeurIPS Conference 2025 Conference Paper

Visual Structures Help Visual Reasoning: Addressing the Binding Problem in LVLMs

  • Amirmohammad Izadi
  • Mohammadali Banayeeanzade
  • Fatemeh Askari
  • Ali Rahimiakbar
  • Mohammad Vahedi
  • Hosein Hasani
  • Mahdieh Baghshah

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This limitation underlies persistent errors in tasks such as counting, visual search, scene description, and spatial relationship understanding. A key factor is that current LVLMs process visual features largely in parallel, lacking mechanisms for spatially grounded, serial attention. This paper introduces Visual Input Structure for Enhanced Reasoning (VISER), a simple, effective method that augments visual inputs with low-level spatial structures and pairs them with a textual prompt that encourages sequential, spatially-aware parsing. We empirically demonstrate substantial performance improvements across core visual reasoning tasks, using only a single-query inference. Specifically, VISER improves GPT-4o performance on visual search, counting, and spatial relationship tasks by 25. 0%, 26. 8%, and 9. 5%, respectively, and reduces edit distance error in scene description by 0. 32 on 2D datasets. Furthermore, we find that the visual modification is essential for these gains; purely textual strategies, including Chain-of-Thought prompting, are insufficient and can even degrade performance. VISER underscores the importance of visual input design over purely linguistically based reasoning strategies and suggests that visual structuring is a powerful and general approach for enhancing compositional and spatial reasoning in LVLMs.

PDF Details
v2026.09.13