In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

Moving objects to find a fully-occluded target object, known as mechanical search, is a challenging problem in robotics. As objects are often organized semantically, we conjecture that semantic information about object relationships can facilitate mechanical search and reduce search time. Large pretrained vision and language models (VLMs and LLMs) have shown promise in generalizing to uncommon objects and previously unseen real-world environments. In this work, we propose a novel framework called Semantic Mechanical Search (SMS). SMS conducts scene understanding and generates a semantic occupancy distribution explicitly using LLMs. Compared to methods that rely on visual similarities offered by CLIP embeddings, SMS leverages the deep reasoning capabilities of LLMs. Unlike prior work that uses VLMs and LLMs as end-to-end planners, which may not integrate well with specialized geometric planners, SMS can serve as a plug-in semantic module for downstream manipulation or navigation policies. For mechanical search in closed-world settings such as shelves, we compare with a geometric-based planner and show that SMS improves mechanical search performance by 24% across the pharmacy, kitchen, and office domains in simulation and 47.1% in physical experiments. For open-world real environments, SMS can produce better semantic distributions compared to CLIP-based methods, with the potential to be integrated with downstream navigation policies to improve object navigation tasks. Code, data, videos, and the appendix are available: https://sites.google.com/view/semantic-mechanical-search

Tracing - estimating the spatial state of - long deformable linear objects such as cables, threads, hoses, or ropes, is useful for a broad range of tasks in homes, retail, factories, construction, transportation, and healthcare. For long deformable linear objects (DLOs or simply cables) with many (over 25) crossings, we present HANDLOOM (Heterogeneous Autoregressive Learned Deformable Linear Object Observation and Manipulation), a learning-based algorithm that fits a trace to a greyscale image of cables. We evaluate HANDLOOM on semi-planar DLO configurations where each crossing involves at most 2 segments. HANDLOOM makes use of neural networks trained with 30,000 simulated examples and 568 real examples to autoregressively estimate traces of cables and classify crossings. Experiments find that in settings with multiple identical cables, HANDLOOM can trace each cable with 80% accuracy. In single-cable images, HANDLOOM can trace and identify knots with 77% accuracy. When HANDLOOM is incorporated into a bimanual robot system, it enables state-based imitation of knot tying with 80% accuracy, and it successfully untangles 64% of cable configurations across 3 levels of difficulty. Additionally, HANDLOOM demonstrates generalization to knot types and materials (rubber, cloth rope) not present in the training dataset with 85% accuracy. Supplementary material, including all code and an annotated dataset of RGB-D images of cables along with ground-truth traces, is at https://sites.google.com/view/cable-tracing.

Accurate 3D sensing of suturing thread is a challenging problem in automated surgical suturing because of the high state-space complexity, thinness and deformability of the thread, and possibility of occlusion by the grippers and tissue. In this work we present a method for tracking surgical thread in 3D which is robust to occlusions and complex thread configurations, and apply it to autonomously perform the surgical suture "tail-shortening" task: pulling thread through tissue until a desired "tail" length remains exposed. The method utilizes a learned 2D surgical thread detection network to segment suturing thread in RGB images. It then identifies the thread path in 2D and reconstructs the thread in 3D as a NURBS spline by triangulating the detections from two stereo cameras. Once a 3D thread model is initialized, the method tracks the thread across subsequent frames. Experiments suggest the method achieves a 1.33 pixel average reprojection error on challenging single-frame 3D thread reconstructions, and an 0.84 pixel average reprojection error on two tracking sequences. On the tail-shortening task, it accomplishes a 90% success rate across 20 trials. Supplemental materials are available at https://sites.google.com/berkeley.edu/autolab-surgical-thread/ .

Deep ensembles have been shown to extend the positive effect seen in typical ensemble learning to neural networks and to reinforcement learning (RL). However, there is still much to be done to improve the efficiency of such ensemble models. In this work, we present Diverse Ensembles for Fast Transfer in RL (DEFT), a new ensemble-based method for reinforcement learning in highly multimodal environments and improved transfer to unseen environments. The algorithm is broken down into two main phases: training of ensemble members, and synthesis (or fine-tuning) of the ensemble members into a policy that works in a new environment. The first phase of the algorithm involves training regular policy gradient or actor-critic agents in parallel but adding a term to the loss that encourages these policies to differ from each other. This causes the individual unimodal agents to explore the space of optimal policies and capture more of the multimodality of the environment than a single actor could. The second phase of DEFT involves synthesizing the component policies into a new policy that works well in a modified environment in one of two ways. To evaluate the performance of DEFT, we start with a base version of the Proximal Policy Optimization (PPO) algorithm and extend it with the modifications for DEFT. Our results show that the pretraining phase is effective in producing diverse policies in multimodal environments. DEFT often converges to a high reward significantly faster than alternatives, such as random initialization without DEFT and fine-tuning of ensemble members. While there is certainly more work to be done to analyze DEFT theoretically and extend it to be even more robust, we believe it provides a strong framework for capturing multimodality in environments while still using RL methods with simple policy representations.