A novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning is presented, and a novel metric, the vision-to-text attention ratio, is proposed, to dynamically gauge the model's cognitive focus.
Abstract
Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We identify that this failure stems from their reliance on token-level entropy, which fundamentally conflates perceptual ambiguity (e.g., unclear visual details) with logical uncertainty (e.g., complex reasoning steps). To overcome this bottleneck, we present a novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning. We propose a novel metric, the vision-to-text attention ratio, to dynamically gauge the model's cognitive focus. Guided by this metric, our proposed framework, Attention-Guided Switching (AGS), adaptively triggers latent reasoning for perceptual tokens to preserve high-fidelity visual information in the continuous space, while enforcing explicit text generation for logical tokens to maintain structural anchoring. Extensive experiments demonstrate that our method achieves state-of-the-art performance, significantly improving both accuracy and inference efficiency by reducing autoregressive steps and latency. Code is released at https://github.com/swordAndSnow/MM26-AGS.
This work introduces Spatially-Grounded Thought Tokenization to explicitly align special tokens with spatial locations for clear spatial correspondence and visual interpretability, and proposes Mixture-of-Thought-Tokens, a new free-form multimodal grounding method that bridges the perception-reasoning gap.
Tianyi Gao, Han Fang, Tianyi Ding et al.· arXiv.org· 0 citations
Think with Structured Grounding (TwSG), a novel fine-grained image perception framework designed to internalize complex images's tool-use capabilities within the model, is proposed, endowing models with native fine-grained region description and flexible reasoning capabilities.
Chang-Jiang Jiang, Qiannian Zhao, Lei Xin et al.· 0 citations
Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the"Thinking with Images"(TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency.
Xiuwei Chen, Quanlin Chen, Wentao Hu et al.· 0 citations
GLaQ, a grounded latent-query framework that replaces sequential latent rollout with a fixed set of context-conditioned queries grounded in the original visual tokens, is introduced, suggesting that direct query-to-image grounding can recover localized evidence from the full image without external visual operations or autoregressive latent rollouts.
Zesheng Yang, Lingling Zhang, Xinyu Zhang et al.· 0 citations
The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models to reason beyond common assumptions. Recent studies mainly improve visual counter-commonsense reasoning by enhancing visual inputs, following the assumption that failures originate from insufficient visual grounding. However, our empirical analysis reveals that the bottleneck is not visual perception. MLLMs already capture the relevant visual evidence, and the correct answer exists in their decoding space. Instead, the shared language decoder resolves prior--evidence conflicts by favoring dominant language priors, especially for low-frequency factual scenarios. Motivated by this, we first propose a text-anchored data construction pipeline, whose core component, Fact-Frequency Distillation (FFD), estimates the prior strength of commonsense facts and distills verified counter-commonsense scenarios into a high-quality text corpus. Building upon this corpus, we introduce TACT, a text-anchored post-training framework that debiases the shared language decoder without requiring any visual training data. TACT routes evidence-following and prior-driven reasoning trajectories into different optimization stages, enabling the decoder to resolve prior--evidence conflicts. Across counter-commonsense visual benchmarks, TACT substantially improves visual reasoning while preserving general capabilities, demonstrating effective text-to-vision cross-modal transfer.
Chen Ling, Hanqian Li, Dongnan Liu et al.· 0 citations
Multimodal Large Language Models (MLLMs) have demonstrated great performance, yet they often suffer from severe modality misalignment when confronted with densely constrained spaces for interior design. Due to the loss of high-frequency local topological details and fine-grained aesthetic shifts during visual encoding, existing MLLMs frequently hallucinate, yielding physical spatial collisions and visual aesthetic dissonance. To address this, we propose Dual-prior Activation Residual Task-vectors Injection mechanism (DART-I) for MLLMs. It shifts the paradigm from lossy text-prompting to direct latent intervention, utilizing weak-to-strong deterministic rules to anchor the causal reasoning of MLLMs for interior design. Specifically, DART-I operates in three steps: it first explicitly extracts continuous spatial distance and color typography features from images using extremely lightweight weak experts; subsequently, it transforms these deterministic priors into directional task vectors via a linear projection network; these vectors are dynamically injected as residual terms into the latent space of the frozen MLLMs, steering MLLMs towards precise reasoning for interior design. Stepping outside the conventional paradigms, our method achieves precise reasoning without fine-tuning the MLLMs, effectively bypassing expensive computational costs and catastrophic forgetting. Extensive experiments on various benchmarks demonstrate the effectiveness and advantages of DART-I.
