相关论文: UniT: Toward a Unified Physical Language for Human…

UniT is an approach to tactile representation learning, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with…

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving…

We present a scalable framework for cross-embodiment humanoid robot control by learning a shared latent representation that unifies motion across humans and diverse humanoid platforms, including single-arm, dual-arm, and legged humanoid…

Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including…

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…

Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…

Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and Embodied AI. Prior work typically relies on object-centric cues or precise hand-object interaction sequences, foregoing the rich,…

We present X-UniMotion, a unified and expressive implicit latent representation for whole-body human motion, encompassing facial expressions, body poses, and hand gestures. Unlike prior motion transfer methods that rely on explicit skeletal…

User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in…

Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly…

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling,…

Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many…

Tactile sensing is crucial for robotic hands to achieve human-level dexterous manipulation, especially in scenarios with visual occlusion. However, its application is often hindered by the difficulty of collecting large-scale real-world…

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly…

This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animation. Specifically, to preserve the robust generative…

A long-standing objective in humanoid robotics is the realization of versatile agents capable of following diverse multimodal instructions with human-level flexibility. Despite advances in humanoid control, bridging high-level multimodal…

Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. However, the prevailing approaches primarily regard the visual…