Empirical Analysis of Sim-and-Real Cotraining Of Diffusion Policies For Planar Pushing from Pixels

In imitation learning for robotics, cotraining with demonstration data generated both in simulation and on real hardware has emerged as a powerful recipe to overcome the sim2real gap. This work seeks to elucidate basic principles of this sim-and-real cotraining to help inform simulation design, sim-and-real dataset creation, and policy training. Focusing narrowly on the canonical task of planar pushing from camera inputs enabled us to be thorough in our study. These experiments confirm that cotraining with simulated data \emph{can} dramatically improve performance in real, especially when real data is limited. Performance gains scale with simulated data, but eventually plateau; real-world data increases this performance ceiling. The results also suggest that reducing the domain gap in physics may be more important than visual fidelity for non-prehensile manipulation tasks. Perhaps surprisingly, having some visual domain gap actually helps the cotrained policy -- binary probes reveal that high-performing policies learn to distinguish simulated domains from real. We conclude by investigating this nuance and mechanisms that facilitate positive transfer between sim-and-real. In total, our experiments span over 40 real-world policies (evaluated on 800+ trials) and 200 simulated policies (evaluated on 40,000+ trials).

PhysGen3D: Crafting a Miniature Interactive World from a Single Image

Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce PhysGen3D, a novel framework that transforms a single image into an amodal, camera-centric, interactive 3D scene. By combining advanced image-based geometric and semantic understanding with physics-based simulation, PhysGen3D creates an interactive 3D world from a static image, enabling us to "imagine" and simulate future scenarios based on user input. At its core, PhysGen3D estimates 3D shapes, poses, physical and lighting properties of objects, thereby capturing essential physical attributes that drive realistic object interactions. This framework allows users to specify precise initial conditions, such as object speed or material properties, for enhanced control over generated video outcomes. We evaluate PhysGen3D's performance against closed-source state-of-the-art (SOTA) image-to-video models, including Pika, Kling, and Gen-3, showing PhysGen3D's capacity to generate videos with realistic physics while offering greater flexibility and fine-grained control. Our results show that PhysGen3D achieves a unique balance of photorealism, physical plausibility, and user-driven interactivity, opening new possibilities for generating dynamic, physics-grounded video from an image.

History-Guided Video Diffusion

Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos. Website: https://boyuan.space/history-guidance

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar. Through extensive experiments with various LLMs and different sizes, we uncover the ingredients for specialization and scale for Long-CoT training. Surprisingly, even smaller models show significant performance gains with limited data, revealing the sample efficiency of Long-CoT and the critical role of sample difficulty in the learning process. Our findings demonstrate that Long-CoT reasoning can be effectively triggered with just a few thousand examples, while larger models achieve unparalleled improvements. We also introduce reinforcement learning (RL)-scale training as a promising direction for advancing slow-thinking systems. RedStar shines across domains: on the MATH-Hard benchmark, RedStar-code-math boosts performance from 66.2\% to 81.6\%, and on the USA Math Olympiad (AIME), it solves 46.7\% of problems using only 21k mixed-code-math datasets. In multimodal tasks like GeoQA and MathVista-GEO, RedStar-Geo achieves competitive results with minimal Long-CoT data, outperforming other slow-thinking systems like QvQ-Preview. Compared to QwQ, RedStar strikes the perfect balance between reasoning and generalizability. Our work highlights that, with careful tuning, scaling Long-CoT can unlock extraordinary reasoning capabilities-even with limited dataset and set a new standard for slow-thinking models across diverse challenges. Our data and models are released at https://huggingface.co/RedStar-Reasoning.

A Paragraph is All It Takes: Rich Robot Behaviors from Interacting, Trusted LLMs

Large Language Models (LLMs) are compact representations of all public knowledge of our physical environment and animal and human behaviors. The application of LLMs to robotics may offer a path to highly capable robots that perform well across most human tasks with limited or even zero tuning. Aside from increasingly sophisticated reasoning and task planning, networks of (suitably designed) LLMs offer ease of upgrading capabilities and allow humans to directly observe the robot's thinking. Here we explore the advantages, limitations, and particularities of using LLMs to control physical robots. The basic system consists of four LLMs communicating via a human language data bus implemented via web sockets and ROS2 message passing. Surprisingly, rich robot behaviors and good performance across different tasks could be achieved despite the robot's data fusion cycle running at only 1Hz and the central data bus running at the extremely limited rates of the human brain, of around 40 bits/s. The use of natural language for inter-LLM communication allowed the robot's reasoning and decision making to be directly observed by humans and made it trivial to bias the system's behavior with sets of rules written in plain English. These rules were immutably written into Ethereum, a global, public, and censorship resistant Turing-complete computer. We suggest that by using natural language as the data bus among interacting AIs, and immutable public ledgers to store behavior constraints, it is possible to build robots that combine unexpectedly rich performance, upgradability, and durable alignment with humans.

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback

Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplored in the cross-modality domain. As the number of modalities increases, aligning all-modality models with human intentions -- such as instruction following -- becomes a pressing challenge. In this work, we make the first attempt to fine-tune all-modality models (i.e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions. This endeavor presents several challenges. First, there is no large-scale all-modality human preference data in existing open-source resources, as most datasets are limited to specific modalities, predominantly text and image. Secondly, the effectiveness of binary preferences in RLHF for post-training alignment in complex all-modality scenarios remains an unexplored area. Finally, there is a lack of a systematic framework to evaluate the capabilities of all-modality models, particularly regarding modality selection and synergy. To address these challenges, we propose the align-anything framework, which includes meticulously annotated 200k all-modality human preference data. Then, we introduce an alignment method that learns from unified language feedback, effectively capturing complex modality-specific human preferences and enhancing the model's instruction-following capabilities. Furthermore, to assess performance improvements in all-modality models after post-training alignment, we construct a challenging all-modality capability evaluation framework -- eval-anything. All data, models, and code frameworks have been open-sourced for the community. For more details, please refer to https://github.com/PKU-Alignment/align-anything.

Software Performance Engineering for Foundation Model-Powered Software (FMware)

The rise of Foundation Models (FMs) like Large Language Models (LLMs) is revolutionizing software development. Despite the impressive prototypes, transforming FMware into production-ready products demands complex engineering across various domains. A critical but overlooked aspect is performance engineering, which aims at ensuring FMware meets performance goals such as throughput and latency to avoid user dissatisfaction and financial loss. Often, performance considerations are an afterthought, leading to costly optimization efforts post-deployment. FMware's high computational resource demands highlight the need for efficient hardware use. Continuous performance engineering is essential to prevent degradation. This paper highlights the significance of Software Performance Engineering (SPE) in FMware, identifying four key challenges: cognitive architecture design, communication protocols, tuning and optimization, and deployment. These challenges are based on literature surveys and experiences from developing an in-house FMware system. We discuss problems, current practices, and innovative paths for the software engineering community.

Automated Global Analysis of Experimental Dynamics through Low-Dimensional Linear Embeddings

Dynamical systems theory has long provided a foundation for understanding evolving phenomena across scientific domains. Yet, the application of this theory to complex real-world systems remains challenging due to issues in mathematical modeling, nonlinearity, and high dimensionality. In this work, we introduce a data-driven computational framework to derive low-dimensional linear models for nonlinear dynamical systems directly from raw experimental data. This framework enables global stability analysis through interpretable linear models that capture the underlying system structure. Our approach employs time-delay embedding, physics-informed deep autoencoders, and annealing-based regularization to identify novel low-dimensional coordinate representations, unlocking insights across a variety of simulated and previously unstudied experimental dynamical systems. These new coordinate representations enable accurate long-horizon predictions and automatic identification of intricate invariant sets while providing empirical stability guarantees. Our method offers a promising pathway to analyze complex dynamical behaviors across fields such as physics, climate science, and engineering, with broad implications for understanding nonlinear systems in the real world.

GUIDE: Real-Time Human-Shaped Agents

The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and sparse learning signals remain challenging. One way of improving the learning speed and performance of these agents is to leverage human guidance. In this work, we introduce GUIDE, a framework for real-time human-guided reinforcement learning by enabling continuous human feedback and grounding such feedback into dense rewards to accelerate policy learning. Additionally, our method features a simulated feedback module that learns and replicates human feedback patterns in an online fashion, effectively reducing the need for human input while allowing continual training. We demonstrate the performance of our framework on challenging tasks with sparse rewards and visual observations. Our human study involving 50 subjects offers strong quantitative and qualitative evidence of the effectiveness of our approach. With only 10 minutes of human feedback, our algorithm achieves up to 30% increase in success rate compared to its RL baseline.

Inverse Reinforcement Learning from Non-Stationary Learning Agents

In this paper, we study an inverse reinforcement learning problem that involves learning the reward function of a learning agent using trajectory data collected while this agent is learning its optimal policy. To address this problem, we propose an inverse reinforcement learning method that allows us to estimate the policy parameters of the learning agent which can then be used to estimate its reward function. Our method relies on a new variant of the behavior cloning algorithm, which we call bundle behavior cloning, and uses a small number of trajectories generated by the learning agent's policy at different points in time to learn a set of policies that match the distribution of actions observed in the sampled trajectories. We then use the cloned policies to train a neural network model that estimates the reward function of the learning agent. We provide a theoretical analysis to show a complexity result on bound guarantees for our method that beats standard behavior cloning as well as numerical experiments for a reinforcement learning problem that validate the proposed method.