mlsanityData to 7 Oct 2026

Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge

arXiv 2601.10228 ↗First posted 15 Jan 2026cs.CV cs.MM eess.IVcited by 3

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Multimodal Large Language Models (MLLMs) struggle with complex video QA benchmarks like HD-EPIC VQA due to ambiguous queries/options, poor long-range temporal reasoning, and non-standardized outputs. We propose a framework integrating query/choice pre-processing, domain-specific Qwen2.5-VL fine-tuning, a novel Temporal Chain-of-Thought (T-CoT) prompting for multi-step reasoning, and robust post-processing. This system achieves 41.6% accuracy on HD-EPIC VQA, highlighting the need for holistic pipeline optimization in demanding video understanding. Our code, fine-tuned models are available at https://github.com/YoungSeng/Egocentric-Co-Pilot.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 12 of its 25 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

12 of 25 references.

References · 12

  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2024GPT-4o System Cardcited by 4,467
  3. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  4. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  5. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  6. 2024DeepSeek-V3 Technical Reportcited by 724
  7. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  8. 2024EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptationcited by 44
  9. 2025EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real Worldcited by 7
  10. 2025Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Modelscited by 6
  11. 2025From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challengecited by 6
  12. 2025Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AIcited by 3
  2. 2026Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videoscited by 2
  3. 2026Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challengecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA
  2. 2025Advancing Egocentric Video Question Answering with Multimodal Large Language Models
  3. 2026V-CORE: Temporally Consistent Video Understanding for Video-LLM
  4. 2025Team of One: Cracking Complex Video QA with Model Synergy
  5. 2025EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
  6. 2025IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
  7. 2023Audio-Visual LLM for Video Understanding
  8. 2026Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs