MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

• URL: http://arxiv.org/abs/2605.25842v2
• Date: Fri, 29 May 2026 07:58:50 GMT
• Title: MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
• Abstract summary: We propose a structured pruning framework for vision-language models (VLMs)<n>MuCRASP targets reasoning-critical components while preserving cross-modal alignment and sensitivity under a global parameter budget.<n> Experiments show that MuCRASP consistently preserves reasoning quality under increasing compression.
• Score: 6.554737064099828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. Structured pruning offers a natural solution; however, existing methods fail to preserve CoT reasoning accuracy in VLMs. We identify two key reasons: (1) CoT consistency depends on sparse transition points (pivot tokens) in the generation trajectory, while existing pruning methods are CoT-agnostic; and (2) pruning methods designed for unimodal LLMs do not account for activation-distribution differences across visual and textual modalities. Motivated by these observations, we propose MuCRASP, a structured pruning framework that targets reasoning-critical components while preserving cross-modal alignment and accounting for layer-wise sensitivity under a global parameter budget. Experiments on four VLMs across three reasoning benchmarks show that MuCRASP consistently preserves reasoning quality under increasing compression. At 30% pruning on Qwen2.5-VL-7B, MuCRASP achieves an LLM-as-a-Judge score of 8.87 versus 7.32 for the strongest baseline on physical reasoning tasks. Furthermore, MuCRASP maintains high reasoning consistency up to 50% pruning, significantly outperforming prior pruning approaches while exhibiting lower perplexity degradation.

Related papers

• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck [28.83441191878705]
  We propose LaME, which formulates embedding-oriented latent reasoning as a weakly supervised information bottleneck.<n>LaME employs K learnable reason tokens as a fixed-capacity bottleneck, completing all reasoning within a single forward pass.<n> Experiments on MMEB-v2 and MRMR show that LaME achieves competitive performance, surpassing some explicit CoT-based models.
  arXiv  Detail & Related papers  (2026-06-11T08:47:25Z)
• Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture [5.59567612070537]
  Think When Needed (TWN) is a unified multimodal embedding framework with adaptive reasoning.<n>Building on this, an adaptive think mechanism uses a self-supervised routing gate to decide per input whether to generate chain-of-thought (CoT)<n>On the 78 tasks of MMEB-V2, TWN achieves state-of-the-art embedding quality while being substantially more efficient than existing generative methods.
  arXiv  Detail & Related papers  (2026-05-14T06:41:53Z)
• MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control [36.06412693943508]
  We propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework.<n>We formulate reasoning as a latent variable and introduce pair-aware reasoning selection to identify reasoning paths beneficial for query-target alignment.<n>Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.
  arXiv  Detail & Related papers  (2026-04-07T17:55:17Z)
• Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency [4.139013391483979]
  Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs)<n>In this work, we introduce Hierarchical Chain-of-Thought (Hi-CoT) prompting.<n>Hi-CoT decomposes the reasoning process into hierarchical substeps by alternating between instructional planning and step-by-step execution.
  arXiv  Detail & Related papers  (2026-03-31T18:35:22Z)
• Reinforcing Structured Chain-of-Thought for Video Understanding [49.3086326382764]
  We introduce Summary-Driven Reinforcement Learning (SDRL)<n>SDRL is a single-stage RL framework that obviates the need forSupervised Fine-Tuning (SFT)<n>Our method achieves state-of-the-art performance on seven public VideoQA datasets.
  arXiv  Detail & Related papers  (2026-03-26T22:11:14Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Reinforced Efficient Reasoning via Semantically Diverse Exploration [73.41112984160992]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs)<n>We propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs.<n>Our method incorporates a semantic-entropy-based branching strategy and an $varepsilon$-exploration mechanism.
  arXiv  Detail & Related papers  (2026-01-08T15:56:44Z)
• Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling [90.87033586963828]
  Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs)<n>We propose Self-Consistency Sampling (SCS) to correct this issue.<n>Based on Qwen2.5-VL-7B-Instruct, SCS improves accuracy by up to 7.7 percentage points on six multimodal benchmarks with negligible extra computation.
  arXiv  Detail & Related papers  (2025-11-13T18:59:57Z)
• Directional Reasoning Injection for Fine-Tuning MLLMs [51.53222423215055]
  Multimodal large language models (MLLMs) are rapidly advancing, yet their reasoning ability often lags behind that of strong text-only counterparts.<n>Existing methods to bridge this gap rely on supervised fine-tuning over large-scale multimodal reasoning data or reinforcement learning.<n>We propose Directional Reasoning Injection for Fine-Tuning (DRIFT) to solve this problem.
  arXiv  Detail & Related papers  (2025-10-16T18:06:46Z)
• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning [3.117335706912261]
  Chain of Evidences (CoE) and Evidence to Generate (E2G) are built upon two unique strategies.<n>Instead of unverified reasoning claims, our innovative approaches leverage the power of "evidence for decision making"<n>Our framework consistently achieves remarkable results across various knowledge-intensive reasoning and generation tasks.
  arXiv  Detail & Related papers  (2024-01-11T09:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.