相关论文: EgoTL: Egocentric Think-Aloud Chains for Long-Hori…

The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, track object state…

Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in vision-language understanding. Yet, human perception is inherently multisensory, integrating sight, sound, and motion to reason about the world. Among…

Vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspective, and only a few…

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current…

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal…

Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing…

Understanding 3D spatial relationships remains a major limitation of current Vision-Language Models (VLMs). Prior work has addressed this issue by creating spatial question-answering (QA) datasets based on single images or indoor videos.…

Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life. Whether multimodal large language models (MLLMs) can perform such embodied 3D reasoning…

As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs,…

Deploying humanoid robots in real-world settings is fundamentally challenging, as it demands tight integration of perception, locomotion, and manipulation under partial-information observations and dynamically changing environments. As well…

We introduce Ego-R1, a novel framework for reasoning over ultra-long (i.e., in days and weeks) egocentric videos, which leverages a structured Chain-of-Tool-Thought (CoTT) process, orchestrated by an Ego-R1 Agent trained via reinforcement…

Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric…

We introduce EgoToM, a new video question-answering benchmark that extends Theory-of-Mind (ToM) evaluation to egocentric domains. Using a causal ToM model, we generate multi-choice video QA instances for the Ego4D dataset to benchmark the…

We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world,…

Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer from content drift, where object identity and scene…

Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to…

Egocentric AI agents, such as smart glasses, rely on pointing gestures to resolve referential ambiguities in natural language commands. However, despite advancements in Multimodal Large Language Models (MLLMs), current systems often fail to…

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable video reasoning capabilities across diverse tasks. However, their ability to understand human intent at a fine-grained level in egocentric videos remains largely…

Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally, aligning LVLMs is not just a safety challenge but a problem of economic efficiency. Current…