Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning

• URL: http://arxiv.org/abs/2603.15008v1
• Date: Mon, 16 Mar 2026 09:15:12 GMT
• Title: Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning
• Abstract summary: This work bridges the perception-to-generation gap in MLLM video understanding, providing an interpretable, faithful reasoning paradigm for VideoQA applications.<n>Inspired by hierarchical human visual cognition, we propose ClueNet, a clue-aware video reasoning framework with a two-stage supervised fine-tuning paradigm.
• Score: 14.945921705882725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal Large Language Models (MLLMs) have significantly advanced video reasoning, yet Video Question Answering (VideoQA) remains challenging due to its demand for temporal causal reasoning and evidence-grounded answer generation. Prevailing end-to-end MLLM frameworks lack explicit structured reasoning between visual perception and answer derivation, causing severe hallucinations and poor interpretability. Existing methods also fail to address three core gaps: faithful visual clue extraction, utility-aware clue filtering, and end-to-end clue-answer alignment. Inspired by hierarchical human visual cognition, we propose ClueNet, a clue-aware video reasoning framework with a two-stage supervised fine-tuning paradigm without extensive base model modifications. Decoupled supervision aligns clue extraction and chain-based reasoning, while inference supervision with an adaptive clue filter refines high-order reasoning, alongside lightweight modules for efficient inference. Experiments on NExT-QA, STAR, and MVBench show that ClueNet outperforms state-of-the-art methods by $\ge$ 1.1%, with superior generalization, hallucination mitigation, inference efficiency, and cross-backbone compatibility. This work bridges the perception-to-generation gap in MLLM video understanding, providing an interpretable, faithful reasoning paradigm for high-stakes VideoQA applications.

Related papers

• HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning [0.764671395172401]
  Hierarchical Program Probing (HPP) is a framework that reformulates long video understanding as iterative, programmatic exploration of a hierarchically segmented video.<n>To make probing tractable over long videos, we introduce three components: information--aware hierarchical segmentation, late-interaction semantic retrieval, structured and probing functions for coarse-to-fine temporal localization.
  arXiv  Detail & Related papers  (2026-06-19T20:43:49Z)
• MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism [70.69809410471993]
  Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution.<n>We introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process.<n>MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points.
  arXiv  Detail & Related papers  (2026-06-05T17:59:21Z)
• Video-ToC: Video Tree-of-Cue Reasoning [65.66891474457466]
  Video Large Language Models (Video LLMs) struggle with complex video understanding.<n>Video-ToC is a novel video reasoning framework that enhances video understanding through tree-of-cue reasoning.
  arXiv  Detail & Related papers  (2026-04-22T12:02:24Z)
• Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method [96.63801368613177]
  We present a new task that elevates video anomaly analysis from descriptive understanding to structured, multi-stage reasoning.<n>We present a new dataset with 8,641 videos, totaling more than 50,000 samples, making it one of the largest datasets for video anomaly understanding.<n>Building upon the proposed task and dataset, we develop an end-to-end MLLM-based VAR model termed Vad-R1-Plus, which supports adaptive hierarchical reasoning and risk-aware decision making.
  arXiv  Detail & Related papers  (2026-01-15T08:09:04Z)
• LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering [10.060267989615813]
  We introduce LeAdQA, an innovative approach that bridges these gaps through synergizing causal-aware query refinement with fine-grained visual grounding.<n> Experiments on NExT-QA, IntentQA, and NExT-GQA demonstrate that our method's precise visual grounding substantially enhances the understanding of video-question relationships.
  arXiv  Detail & Related papers  (2025-07-20T01:57:00Z)
• Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning [95.44766931218896]
  Multi-modal large language models (MLLMs) still lag behind text-based reasoning.<n>We introduce Perception-Reasoning Decoupling, which modularizes the MLLM's reasoning component and makes it easily replaceable.<n>We propose a novel reinforcement learning algorithm called Visual Perception Optimization (VPO) to align the MLLM's perceptual output with the final reasoning task.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning [53.790502697674754]
  We propose Take-along Visual Conditioning (TVC), a strategy that shifts image input to critical reasoning stages.<n>TVC helps the model retain attention to the visual components throughout the reasoning.<n>Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T16:45:12Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)
• Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies [69.28082193942991]
  This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet previously overlooked video reasoning skills. utilizing tropes from movie storytelling, TiM evaluates the reasoning capabilities of state-of-the-art LLM-based approaches. To address these deficiencies, we propose Face-Enhanced Viper of Role Interactions (FEVoRI) and Context Query Reduction (ConQueR)
  arXiv  Detail & Related papers  (2024-06-16T12:58:31Z)

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.