Saved in:
Bibliographic Details
Main Authors: Zhang, Longyin, Sun, Shuo, He, Yingxu, Lewis, Won Cheng Yi, Shahrin, Muhammad Huzaifah Bin Md, Sailor, Hardik Bhupendra, Wong, Heng Meng Jeremy, Vangani, Tarun Kumar, Ma, Yi, Wang, Qiongqiong, Pham, Minh Duc, Jiang, Ridong, Li, Jingtao, Liao, Jingyi, Liu, Zhuohan, Lu, Yanfeng, Gupta, Manas, Aw, Ai Ti
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.23730
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914356312145920
author Zhang, Longyin
Sun, Shuo
He, Yingxu
Lewis, Won Cheng Yi
Shahrin, Muhammad Huzaifah Bin Md
Sailor, Hardik Bhupendra
Wong, Heng Meng Jeremy
Vangani, Tarun Kumar
Ma, Yi
Wang, Qiongqiong
Pham, Minh Duc
Jiang, Ridong
Li, Jingtao
Liao, Jingyi
Liu, Zhuohan
Lu, Yanfeng
Gupta, Manas
Aw, Ai Ti
author_facet Zhang, Longyin
Sun, Shuo
He, Yingxu
Lewis, Won Cheng Yi
Shahrin, Muhammad Huzaifah Bin Md
Sailor, Hardik Bhupendra
Wong, Heng Meng Jeremy
Vangani, Tarun Kumar
Ma, Yi
Wang, Qiongqiong
Pham, Minh Duc
Jiang, Ridong
Li, Jingtao
Liao, Jingyi
Liu, Zhuohan
Lu, Yanfeng
Gupta, Manas
Aw, Ai Ti
contents Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a challenge, particularly for underrepresented regions. In this report, we introduce the research preview of MERaLiON2-Omni (Alpha), a 10B-parameter multilingual omni-perception tailored for Southeast Asia (SEA). We present a progressive training pipeline that explicitly decouples and then integrates "System 1" (Perception) and "System 2" (Reasoning) capabilities. First, we establish a robust Perception Backbone by aligning region-specific audio-visual cues (e.g., Singlish code-switching, local cultural landmarks) with a multilingual LLM through orthogonal modality adaptation. Second, to inject cognitive capabilities without large-scale supervision, we propose a cost-effective Generate-Judge-Refine pipeline. By utilizing a Super-LLM to filter hallucinations and resolve conflicts via a consensus mechanism, we synthesize high-quality silver data that transfers textual Chain-of-Thought reasoning to multimodal scenarios. Comprehensive evaluation on our newly introduced SEA-Omni Benchmark Suite reveals an Efficiency-Stability Paradox: while reasoning acts as a non-linear amplifier for abstract tasks (boosting mathematical and instruction-following performance significantly), it introduces instability in low-level sensory processing. Specifically, we identify Temporal Drift in long-context audio, where extended reasoning desynchronizes the model from acoustic timestamps, and Visual Over-interpretation, where logic overrides pixel-level reality. This report details the architecture, the data-efficient training recipe, and a diagnostic analysis of the trade-offs between robust perception and structured reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23730
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off
Zhang, Longyin
Sun, Shuo
He, Yingxu
Lewis, Won Cheng Yi
Shahrin, Muhammad Huzaifah Bin Md
Sailor, Hardik Bhupendra
Wong, Heng Meng Jeremy
Vangani, Tarun Kumar
Ma, Yi
Wang, Qiongqiong
Pham, Minh Duc
Jiang, Ridong
Li, Jingtao
Liao, Jingyi
Liu, Zhuohan
Lu, Yanfeng
Gupta, Manas
Aw, Ai Ti
Artificial Intelligence
Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a challenge, particularly for underrepresented regions. In this report, we introduce the research preview of MERaLiON2-Omni (Alpha), a 10B-parameter multilingual omni-perception tailored for Southeast Asia (SEA). We present a progressive training pipeline that explicitly decouples and then integrates "System 1" (Perception) and "System 2" (Reasoning) capabilities. First, we establish a robust Perception Backbone by aligning region-specific audio-visual cues (e.g., Singlish code-switching, local cultural landmarks) with a multilingual LLM through orthogonal modality adaptation. Second, to inject cognitive capabilities without large-scale supervision, we propose a cost-effective Generate-Judge-Refine pipeline. By utilizing a Super-LLM to filter hallucinations and resolve conflicts via a consensus mechanism, we synthesize high-quality silver data that transfers textual Chain-of-Thought reasoning to multimodal scenarios. Comprehensive evaluation on our newly introduced SEA-Omni Benchmark Suite reveals an Efficiency-Stability Paradox: while reasoning acts as a non-linear amplifier for abstract tasks (boosting mathematical and instruction-following performance significantly), it introduces instability in low-level sensory processing. Specifically, we identify Temporal Drift in long-context audio, where extended reasoning desynchronizes the model from acoustic timestamps, and Visual Over-interpretation, where logic overrides pixel-level reality. This report details the architecture, the data-efficient training recipe, and a diagnostic analysis of the trade-offs between robust perception and structured reasoning.
title Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off
topic Artificial Intelligence
url https://arxiv.org/abs/2602.23730