Papers
arxiv:2603.06561

EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking

Published on Mar 31
Authors:
,
,
,
,
,
,
,
,
,
,
,

Abstract

A two-stage framework called EgoReasoner is proposed for egocentric 4D reasoning tasks, featuring task-adaptive thinking templates and reward functions that improve performance on complex spatial and temporal reasoning challenges.

Egocentric video understanding is inherently complex due to the dynamic 4D nature of the environment, where camera motion and object displacements necessitate a continuous re-evaluation of spatial relations. In this work, we target a suite of under-explored egocentric 4D reasoning tasks, including fixture interaction counting, viewpoint-relative fixture location, object movement itinerary tracking, and stationary object localization, that require fundamentally different cognitive operations: spatial anchoring, temporal tracking, and duration reasoning. We observe that these structural differences make task-agnostic approaches insufficient: generic Chain-of-Thought methods lack task-appropriate reasoning primitives, and uniform reinforcement learning actively destabilizes performance on spatial tasks. To address this, we propose EgoReasoner, a two-stage framework that aligns both the reasoning scaffold and the reward signal to each task's cognitive structure. In the first stage, Task-Adaptive Thinking Templates guide the synthesis of structured CoT traces that teach the model to reason adaptively across task types via supervised fine-tuning. In the second stage, task-aware reward functions verify entity grounding, temporal alignment, and task-adaptive logical consistency, selectively strengthening each reasoning pathway via reinforcement fine-tuning with GRPO. Our 3B-parameter model, trained on only 16K samples, achieves 37.5% average accuracy on the challenging HD-EPIC benchmark, surpassing Qwen2.5-VL-7B (25.7%) by over 10 points.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2603.06561
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.06561 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.06561 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.