Effective Tuning Strategies for Generalist Robot Manipulation Policies

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty of collecting sufficient action data to cover extensively diverse domains. While fine-tuning offers a practical way to quickly adapt a GMPs to novel domains and tasks with limited samples, we observe that the performance of the resulting GMPs differs significantly with respect to the design choices of fine-tuning strategies. In this work, we first conduct an in-depth empirical study to investigate the effect of key factors in GMPs fine-tuning strategies, covering the action space, policy head, supervision signal and the choice of tunable parameters, where 2,500 rollouts are evaluated for a single configuration. We systematically discuss and summarize our findings and identify the key design choices, which we believe give a practical guideline for GMPs fine-tuning. We observe that in a low-data regime, with carefully chosen fine-tuning strategies, a GMPs significantly outperforms the state-of-the-art imitation learning algorithms. The results presented in this work establish a new baseline for future studies on fine-tuned GMPs, and provide a significant addition to the GMPs toolbox for the community.

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively.

Automated Review Generation Method Based on Large Language Models

Literature research, vital for scientific advancement, is overwhelmed by the vast ocean of available information. Addressing this, we propose an automated review generation method based on Large Language Models (LLMs) to streamline literature processing and reduce cognitive load. In case study on propane dehydrogenation (PDH) catalysts, our method swiftly generated comprehensive reviews from 343 articles, averaging seconds per article per LLM account. Extended analysis of 1041 articles provided deep insights into catalysts' composition, structure, and performance. Recognizing LLMs' hallucinations, we employed a multi-layered quality control strategy, ensuring our method's reliability and effective hallucination mitigation. Expert verification confirms the accuracy and citation integrity of generated reviews, demonstrating LLM hallucination risks reduced to below 0.5% with over 95% confidence. Released Windows application enables one-click review generation, aiding researchers in tracking advancements and recommending literature. This approach showcases LLMs' role in enhancing scientific research productivity and sets the stage for further exploration.

Mixture of Experts based Multi-task Supervise Learning from Crowds

Existing truth inference methods in crowdsourcing aim to map redundant labels and items to the ground truth. They treat the ground truth as hidden variables and use statistical or deep learning-based worker behavior models to infer the ground truth. However, worker behavior models that rely on ground truth hidden variables overlook workers' behavior at the item feature level, leading to imprecise characterizations and negatively impacting the quality of truth inference. This paper proposes a new paradigm of multi-task supervised learning from crowds, which eliminates the need for modeling of items's ground truth in worker behavior models. Within this paradigm, we propose a worker behavior model at the item feature level called Mixture of Experts based Multi-task Supervised Learning from Crowds (MMLC). Two truth inference strategies are proposed within MMLC. The first strategy, named MMLC-owf, utilizes clustering methods in the worker spectral space to identify the projection vector of the oracle worker. Subsequently, the labels generated based on this vector are considered as the inferred truth. The second strategy, called MMLC-df, employs the MMLC model to fill the crowdsourced data, which can enhance the effectiveness of existing truth inference methods. Experimental results demonstrate that MMLC-owf outperforms state-of-the-art methods and MMLC-df enhances the quality of existing truth inference methods.

BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.

Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation

Generalising vision-based manipulation policies to novel environments remains a challenging area with limited exploration. Current practices involve collecting data in one location, training imitation learning or reinforcement learning policies with this data, and deploying the policy in the same location. However, this approach lacks scalability as it necessitates data collection in multiple locations for each task. This paper proposes a novel approach where data is collected in a location predominantly featuring green screens. We introduce Green-screen Augmentation (GreenAug), employing a chroma key algorithm to overlay background textures onto a green screen. Through extensive real-world empirical studies with over 850 training demonstrations and 8.2k evaluation episodes, we demonstrate that GreenAug surpasses no augmentation, standard computer vision augmentation, and prior generative augmentation methods in performance. While no algorithmic novelties are claimed, our paper advocates for a fundamental shift in data collection practices. We propose that real-world demonstrations in future research should utilise green screens, followed by the application of GreenAug. We believe GreenAug unlocks policy generalisation to visually distinct novel locations, addressing the current scene generalisation limitations in robot learning.

Test-Time Generative Augmentation for Medical Image Segmentation

In this paper, we propose a novel approach to enhance medical image segmentation during test time. Instead of employing hand-crafted transforms or functions on the input test image to create multiple views for test-time augmentation, we advocate for the utilization of an advanced domain-fine-tuned generative model (GM), e.g., stable diffusion (SD), for test-time augmentation. Given that the GM has been trained to comprehend and encapsulate comprehensive domain data knowledge, it is superior than segmentation models in terms of representing the data characteristics and distribution. Hence, by integrating the GM into test-time augmentation, we can effectively generate multiple views of a given test sample, aligning with the content and appearance characteristics of the sample and the related local data distribution. This approach renders the augmentation process more adaptable and resilient compared to conventional handcrafted transforms. Comprehensive experiments conducted across three medical image segmentation tasks (nine datasets) demonstrate the efficacy and versatility of the proposed TTGA in enhancing segmentation outcomes. Moreover, TTGA significantly improves pixel-wise error estimation, thereby facilitating the deployment of a more reliable segmentation system. Code will be released at: https://github.com/maxiao0234/TTGA.

Safety Alignment Should Be Made More Than Just a Few Tokens Deep

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying issue: safety alignment can take shortcuts, wherein the alignment adapts a model's generative distribution primarily over only its very first few output tokens. We refer to this issue as shallow safety alignment. In this paper, we present case studies to explain why shallow safety alignment can exist and provide evidence that current aligned LLMs are subject to this issue. We also show how these findings help explain multiple recently discovered vulnerabilities in LLMs, including the susceptibility to adversarial suffix attacks, prefilling attacks, decoding parameter attacks, and fine-tuning attacks. Importantly, we discuss how this consolidated notion of shallow safety alignment sheds light on promising research directions for mitigating these vulnerabilities. For instance, we show that deepening the safety alignment beyond just the first few tokens can often meaningfully improve robustness against some common exploits. Finally, we design a regularized finetuning objective that makes the safety alignment more persistent against fine-tuning attacks by constraining updates on initial tokens. Overall, we advocate that future safety alignment should be made more than just a few tokens deep.

Redundancy-aware Action Spaces for Robot Learning

Joint space and task space control are the two dominant action modes for controlling robot arms within the robot learning literature. Actions in joint space provide precise control over the robot's pose, but tend to suffer from inefficient training; actions in task space boast data-efficient training but sacrifice the ability to perform tasks in confined spaces due to limited control over the full joint configuration. This work analyses the criteria for designing action spaces for robot manipulation and introduces ER (End-effector Redundancy), a novel action space formulation that, by addressing the redundancies present in the manipulator, aims to combine the advantages of both joint and task spaces, offering fine-grained comprehensive control with overactuated robot arms whilst achieving highly efficient robot learning. We present two implementations of ER, ERAngle (ERA) and ERJoint (ERJ), and we show that ERJ in particular demonstrates superior performance across multiple settings, especially when precise control over the robot configuration is required. We validate our results both in simulated and real robotic environments.

Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions

Video recognition remains an open challenge, requiring the identification of diverse content categories within videos. Mainstream approaches often perform flat classification, overlooking the intrinsic hierarchical structure relating categories. To address this, we formalize the novel task of hierarchical video recognition, and propose a video-language learning framework tailored for hierarchical recognition. Specifically, our framework encodes dependencies between hierarchical category levels, and applies a top-down constraint to filter recognition predictions. We further construct a new fine-grained dataset based on medical assessments for rehabilitation of stroke patients, serving as a challenging benchmark for hierarchical recognition. Through extensive experiments, we demonstrate the efficacy of our approach for hierarchical recognition, significantly outperforming conventional methods, especially for fine-grained subcategories. The proposed framework paves the way for hierarchical modeling in video understanding tasks, moving beyond flat categorization.