Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition

• URL: http://arxiv.org/abs/2608.14854v1
• Date: Fri, 14 Aug 2026 19:50:31 GMT
• Title: Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition
• Abstract summary: Multimodal Large Language Models (MLLMs) excel in general video understanding, but their capability in fine-grained and motion-centric tasks remains limited.<n>We propose a novel test-time evidence calibration framework that improves both reasoning details and prediction reliability.<n>Our framework achieves mean-class accuracies of 26.84% on iMiGUE and 22.10% on MA-52, significantly outperforming the Qwen2.5-VL baseline.
• Score: 6.788919875409626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Multimodal Large Language Models (MLLMs) excel in general video understanding, their capability in fine-grained and motion-centric tasks remains limited. This limitation is particularly critical in micro-gesture recognition (MGR), where micro-gestures (MGs) - subtle, short-duration, and spatially localized human movements - serve as key discriminative signals for implicit affective analysis, yet are easily neglected following common prompting practices. Although MGR has been intensively studied by many discriminative approaches, the use of MLLMs for MGR is underexplored, with notably poor performance. We hypothesize that the motion-sensitive representation ability of MLLMs is constrained by their inherent single-pass forward inference, which can be substantially enhanced through carefully designed test-time guidance. Motivated by this, building on our prior findings regarding temporal insensitivity in Video LLMs, we diagnose zero-shot MGR errors in the Negative Log-Likelihood (NLL) space. We observe that MLLMs suffer from two bottlenecks: 1) insufficient localized evidence and 2) severe score biases driven by language and motion-agnostic appearances. Thus, we propose a novel test-time evidence calibration framework that improves both reasoning details and prediction reliability. Specifically, we introduce a tree search mechanism to progressively acquire localized, fine-grained visual evidence, coupled with a test-time calibration module to mitigate score biases. The multi-cue fusion module then integrates evidence from multiple cues without relying on a single cue for final prediction. Our framework achieves mean-class accuracies of 26.84\% on iMiGUE and 22.10\% on MA-52, significantly outperforming the Qwen2.5-VL baseline, which produces 16.15\% and 10.20\%, respectively. The code will be available at https://zero-melo.github.io/Zero-MELO.

Related papers

• Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs? [25.03825424390989]
  multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision.<n>We decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes.<n>We introduce the first training-free framework that leverages Collaborative attention for Unified SOD (FOCUS)
  arXiv  Detail & Related papers  (2026-07-31T09:54:23Z)
• RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models [58.83401587988675]
  RoboAlign trains vision-language-action models (VLAs) to translate multimodal understanding into low-level actions.<n>Our key idea is to sample action tokens via zero-shot natural language reasoning and refine this reasoning using reinforcement learning (RL) to improve action accuracy.<n>RoboAlign achieves performance improvements of 17.5%, 18.9%, and 106.6% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.
  arXiv  Detail & Related papers  (2026-03-22T17:57:55Z)
• Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild [9.42132060759461]
  Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding.<n>In this work, we evaluate state-of-the-art MLLMs on the ShanghaiTech and CHAD benchmarks.<n>We investigate how prompt specificity and temporal window lengths (1s--3s) influence performance, focusing on the precision--recall trade-off.
  arXiv  Detail & Related papers  (2026-03-05T02:00:53Z)
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification [9.397157329808254]
  MUSE is a simple information-theoretic method to identify and aggregate well-calibrated subsets of large language models.<n> Experiments on binary prediction tasks demonstrate improved calibration and predictive performance compared to single-model and na"ive ensemble baselines.
  arXiv  Detail & Related papers  (2025-07-09T19:13:25Z)
• Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models [32.30528039193554]
  Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training.<n>Recent studies suggest that LLMs lack inherent effectiveness in forecasting.<n>Our experiments show that LLM-based zero-shot forecasters often struggle to achieve high accuracy due to their sensitivity to noise.
  arXiv  Detail & Related papers  (2025-05-31T08:24:01Z)
• Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought [58.321044666612174]
  Vad-R1 is an end-to-end MLLM-based framework for Video Anomaly Reasoning.<n>We design a Perception-to-Cognition Chain-of-Thought (P2C-CoT) that simulates the human process of recognizing anomalies.<n>We also propose an improved reinforcement learning algorithm AVA-GRPO, which explicitly incentivizes the anomaly reasoning capability of MLLMs.
  arXiv  Detail & Related papers  (2025-05-26T12:05:16Z)
• Grounded Chain-of-Thought for Multimodal Large Language Models [66.04061083611863]
  We propose a new learning task for multimodal large language models (MLLMs) called Grounded Chain-of-Thought (GCoT)<n>GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis.<n>To facilitate this task, we also carefully design and construct a dataset called multimodal grounded chain-of-thought (MM-GCoT) consisting of 24,022 GCoT examples for 5,033 images.
  arXiv  Detail & Related papers  (2025-03-17T04:07:47Z)
• Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon [12.13060272830352]
  Large language models (LLMs) often appear to excel on public benchmarks.<n>These high scores may mask an overreliance on dataset-specific surface cues rather than true language understanding.<n>We introduce the Chameleon Benchmark Overfit Detector (C-BOD), a meta-evaluation framework that distorts benchmark prompts.
  arXiv  Detail & Related papers  (2025-02-11T10:43:36Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

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.