Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs
Reviewed by Pithpith:ZNXEPW6Xopen to challenge →
read the original abstract
While previous approaches to 3D human motion generation have achieved notable success, they often rely on extensive training and are limited to specific tasks. To address these challenges, we introduce Motion-Agent, an efficient conversational framework designed for general human motion generation, editing, and understanding. Motion-Agent employs an open-source pre-trained language model to develop a generative agent, MotionLLM, that bridges the gap between motion and text. This is accomplished by encoding and quantizing motions into discrete tokens that align with the language model's vocabulary. With only 1--3\% of the model's parameters fine-tuned using adapters, MotionLLM delivers performance on par with diffusion models and other transformer-based methods trained from scratch. By integrating MotionLLM with GPT-4 without additional training, Motion-Agent is able to generate highly complex motion sequences through multi-turn conversations, a capability that previous models have struggled to achieve. Motion-Agent supports a wide range of motion-language tasks, offering versatile capabilities for generating and customizing human motion through interactive conversational exchanges. Project page: https://knoxzhao.github.io/Motion-Agent
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models
NextMotionQA benchmark reveals VLMs have critical gaps in fine-grained human motion understanding and align with experts on coarse judgment (κ=0.70) but not fine-grained (κ=0.10).
-
MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation
MotionMERGE proposes a multi-granular LLM framework for fine-grained text-driven human motion editing, reasoning, generation, and explanation, supported by the new MotionFineEdit dataset with spatio-temporal annotations.
-
CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
-
MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
New benchmark diagnoses directional, attributional, and temporal hallucinations in multimodal motion comparison models and demonstrates gains from explicit measurement verification.
-
CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning
CogPortrait uses MLLM-based hierarchical planning to convert high-level labels into eye keypoints and a conditioned DiT model to produce portrait animations with improved eye-region accuracy on the new EMH benchmark.
-
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
-
Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs
LLMs can generate coherent multimodal behaviors for SIAs that align with intended ability and benevolence levels as confirmed by user perceptions, while also reproducing gender stereotypes.
-
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
Proposes LoRA-based mixture-of-experts with autoencoder routing for continual bidirectional motion-language learning, reporting near-zero forgetting on a 5-task HumanML3D benchmark derived via semantic clustering.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.