MotionRFT introduces a reinforcement fine‑tuning framework for text‑to‑motion generation that unifies heterogeneous motion representations into a shared semantic space using the MotionReward model. The framework includes a fine‑grained, memory‑efficient fine‑tuning method called EasyTune, which optimizes step‑wise denoising steps to reduce computational overhead. Experiments show significant improvements in FID, R‑Precision, and memory usage across several motion models.
arXiv:2604. 27147v3 Announce Type: replace-cross Abstract: In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}.
arXiv:2609.14615v1 Announce Type: cross Abstract: Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world env...
arXiv:2608.23664v1 Announce Type: cross Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing method...
arXiv:2606. 30266v1 Announce Type: cross Abstract: Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M).
The Pistis Technical Report introduces the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5. The models are developed through a scalable post‑training framework that begins with large‑scale multimodal supervised fine‑tuning and then applies Interleaved Distillation and Reinforcement Learning (IDRL) to integrate on‑policy distillation and reinforcement learning within a single training loop. Two specialized variants—Pistis‑Thinking for deep multimodal reasoning and Pistis‑Agentic for long‑horizon planning, iterative reasoning, and tool use—are produced at both scales, and a system‑level method called Pistis‑Auto‑Harnessing (PAH) further improves inference harness performance without updating model parameters.
VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.
SCRIPT is a scalable diffusion policy that uses a Joint Action-State-Text Diffusion Transformer (JAST‑DiT) to jointly encode actions, physical states, and natural‑language instructions, enabling direct interaction between language semantics and control dynamics. The method employs a multi‑stage training framework, including supervised imitation pre‑training, a nonlinear history conditioning mechanism for stable autoregressive control, and a post‑training stage with Reinforcement Learning with Hybrid Rewards (RLHR) that injects learnable noise to improve motion quality and instruction following. Experiments on the 1200‑hour MotionMillion dataset show that SCRIPT outperforms prior state‑of‑the‑art methods across text alignment, motion quality, and physical realism, and its performance scales consistently with model size.
Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temporal, especially in compositional and long-duration sequences that require semantic consistency across multiple action segments and smooth kinematic transitions throughout the trajectory.
InternW0-Δ is a unified World Action Model that integrates pretrained visual dynamics, scene semantics, 4D geometry, and motion priors within a Mixture-of-Transformers framework to generate robot actions. It leverages a frozen VLM for semantic guidance, a 4D foundation model for geometric priors, and introduces Causal Imprint to learn future-relevant scene changes without future-video rollout. The model is pretrained on a newly curated 20K‑hour heterogeneous corpus of robot and human demonstrations, achieving superior performance on simulation benchmarks and real‑robot platforms.
The paper compares diffusion and rectified flow objectives within the MotionGPT3 framework for text-driven motion generation. Experiments on HumanML3D show that rectified flow converges faster, achieves strong test performance earlier, and matches or exceeds diffusion quality while requiring fewer sampling steps. The study isolates the generative objective’s impact, demonstrating that rectified flow’s benefits transfer to continuous-latent motion generation.
Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off between semantic fidelity and physical realism. Large language model (LLM)-based approaches can interpret diverse open-vocabulary instructions and compose high-level action plans, but they often generate motions that violate physical constraints.
arXiv:2606. 17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory.