MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving. As these two tasks require strict and formal multi-step inference, they are appealing domains for exploring the reasoning ability of LLMs but still face important challenges. Previous studies such as Chain-of-Thought (CoT) have revealed the effectiveness of intermediate steps guidance. However, such step-wise annotation requires heavy labor, leading to insufficient training steps for current benchmarks. To fill this gap, this work introduces MUSTARD, a data generation framework that masters uniform synthesis of theorem and proof data of high quality and diversity. MUSTARD synthesizes data in three stages: (1) It samples a few mathematical concept seeds as the problem category. (2) Then, it prompts a generative language model with the sampled concepts to obtain both the problems and their step-wise formal solutions. (3) Lastly, the framework utilizes a proof assistant (e.g., Lean Prover) to filter the valid proofs. With the proposed MUSTARD, we present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points. Each data point contains an informal statement, an informal proof, and a translated formal proof that passes the prover validation. We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data. We further apply the MUSTARDSAUCE for fine-tuning smaller language models. The fine-tuned Llama 2-7B achieves a 15.41% average relative performance gain in automated theorem proving, and 8.18% in math word problems. Codes and data are available at https://github.com/Eleanor-H/MUSTARD.

GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data

3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations of point cloud lost the object's surface shape information and creates a gap between rendering results and 2D correspondences. To address this problem, we propose GS-CLIP for the first attempt to introduce 3DGS (3D Gaussian Splatting) into multimodal pre-training to enhance 3D representation. GS-CLIP leverages a pre-trained vision-language model for a learned common visual and textual space on massive real world image-text pairs and then learns a 3D Encoder for aligning 3DGS optimized per object. Additionally, a novel Gaussian-Aware Fusion is proposed to extract and fuse global explicit feature. As a general framework for language-image-3D pre-training, GS-CLIP is agnostic to 3D backbone networks. Experiments on challenging shows that GS-CLIP significantly improves the state-of-the-art, outperforming the previously best results.

MapGPT: Map-Guided Prompting for Unified Vision-and-Language Navigation

Embodied agents equipped with GPT as their brain have exhibited extraordinary thinking and decision-making abilities across various tasks. However, existing zero-shot agents for vision-and-language navigation (VLN) only prompt the GPT to handle excessive environmental information and select potential locations within localized environments, without constructing an effective ''global-view'' (e.g., a commonly-used map) for the agent to understand the overall environment. In this work, we present a novel map-guided GPT-based path-planning agent, dubbed MapGPT, for the zero-shot VLN task. Specifically, we convert a topological map constructed online into prompts to encourage map-guided global exploration, and require the agent to explicitly output and update multi-step path planning to avoid getting stuck in local exploration. Extensive experiments demonstrate that our MapGPT is effective, achieving impressive performance on both the R2R and REVERIE datasets (38.8% and 28.4% success rate, respectively) and showcasing the newly emerged global thinking and path planning capabilities of the GPT model. Unlike previous VLN agents, which require separate parameters fine-tuning or specific prompt design to accommodate various instruction styles across different datasets, our MapGPT is more unified as it can adapt to different instruction styles seamlessly, which is the first of its kind in this field.

3D Visibility-aware Generalizable Neural Radiance Fields for Interacting Hands

Neural radiance fields (NeRFs) are promising 3D representations for scenes, objects, and humans. However, most existing methods require multi-view inputs and per-scene training, which limits their real-life applications. Moreover, current methods focus on single-subject cases, leaving scenes of interacting hands that involve severe inter-hand occlusions and challenging view variations remain unsolved. To tackle these issues, this paper proposes a generalizable visibility-aware NeRF (VA-NeRF) framework for interacting hands. Specifically, given an image of interacting hands as input, our VA-NeRF first obtains a mesh-based representation of hands and extracts their corresponding geometric and textural features. Subsequently, a feature fusion module that exploits the visibility of query points and mesh vertices is introduced to adaptively merge features of both hands, enabling the recovery of features in unseen areas. Additionally, our VA-NeRF is optimized together with a novel discriminator within an adversarial learning paradigm. In contrast to conventional discriminators that predict a single real/fake label for the synthesized image, the proposed discriminator generates a pixel-wise visibility map, providing fine-grained supervision for unseen areas and encouraging the VA-NeRF to improve the visual quality of synthesized images. Experiments on the Interhand2.6M dataset demonstrate that our proposed VA-NeRF outperforms conventional NeRFs significantly. Project Page: \url{https://github.com/XuanHuang0/VANeRF}.

Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models

The rise of multimodal large language models (MLLMs) has spurred interest in language-based driving tasks. However, existing research typically focuses on limited tasks and often omits key multi-view and temporal information which is crucial for robust autonomous driving. To bridge these gaps, we introduce NuInstruct, a novel dataset with 91K multi-view video-QA pairs across 17 subtasks, where each task demands holistic information (e.g., temporal, multi-view, and spatial), significantly elevating the challenge level. To obtain NuInstruct, we propose a novel SQL-based method to generate instruction-response pairs automatically, which is inspired by the driving logical progression of humans. We further present BEV-InMLLM, an end-to-end method for efficiently deriving instruction-aware Bird's-Eye-View (BEV) features, language-aligned for large language models. BEV-InMLLM integrates multi-view, spatial awareness, and temporal semantics to enhance MLLMs' capabilities on NuInstruct tasks. Moreover, our proposed BEV injection module is a plug-and-play method for existing MLLMs. Our experiments on NuInstruct demonstrate that BEV-InMLLM significantly outperforms existing MLLMs, e.g. around 9% improvement on various tasks. We plan to release our NuInstruct for future research development.

Monocular 3D Hand Mesh Recovery via Dual Noise Estimation

Current parametric models have made notable progress in 3D hand pose and shape estimation. However, due to the fixed hand topology and complex hand poses, current models are hard to generate meshes that are aligned with the image well. To tackle this issue, we introduce a dual noise estimation method in this paper. Given a single-view image as input, we first adopt a baseline parametric regressor to obtain the coarse hand meshes. We assume the mesh vertices and their image-plane projections are noisy, and can be associated in a unified probabilistic model. We then learn the distributions of noise to refine mesh vertices and their projections. The refined vertices are further utilized to refine camera parameters in a closed-form manner. Consequently, our method obtains well-aligned and high-quality 3D hand meshes. Extensive experiments on the large-scale Interhand2.6M dataset demonstrate that the proposed method not only improves the performance of its baseline by more than 10$\%$ but also achieves state-of-the-art performance. Project page: \url{https://github.com/hanhuili/DNE4Hand}.

Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model

Text-guided motion synthesis aims to generate 3D human motion that not only precisely reflects the textual description but reveals the motion details as much as possible. Pioneering methods explore the diffusion model for text-to-motion synthesis and obtain significant superiority. However, these methods conduct diffusion processes either on the raw data distribution or the low-dimensional latent space, which typically suffer from the problem of modality inconsistency or detail-scarce. To tackle this problem, we propose a novel Basic-to-Advanced Hierarchical Diffusion Model, named B2A-HDM, to collaboratively exploit low-dimensional and high-dimensional diffusion models for high quality detailed motion synthesis. Specifically, the basic diffusion model in low-dimensional latent space provides the intermediate denoising result that to be consistent with the textual description, while the advanced diffusion model in high-dimensional latent space focuses on the following detail-enhancing denoising process. Besides, we introduce a multi-denoiser framework for the advanced diffusion model to ease the learning of high-dimensional model and fully explore the generative potential of the diffusion model. Quantitative and qualitative experiment results on two text-to-motion benchmarks (HumanML3D and KIT-ML) demonstrate that B2A-HDM can outperform existing state-of-the-art methods in terms of fidelity, modality consistency, and diversity.

WarpDiffusion: Efficient Diffusion Model for High-Fidelity Virtual Try-on

Image-based Virtual Try-On (VITON) aims to transfer an in-shop garment image onto a target person. While existing methods focus on warping the garment to fit the body pose, they often overlook the synthesis quality around the garment-skin boundary and realistic effects like wrinkles and shadows on the warped garments. These limitations greatly reduce the realism of the generated results and hinder the practical application of VITON techniques. Leveraging the notable success of diffusion-based models in cross-modal image synthesis, some recent diffusion-based methods have ventured to tackle this issue. However, they tend to either consume a significant amount of training resources or struggle to achieve realistic try-on effects and retain garment details. For efficient and high-fidelity VITON, we propose WarpDiffusion, which bridges the warping-based and diffusion-based paradigms via a novel informative and local garment feature attention mechanism. Specifically, WarpDiffusion incorporates local texture attention to reduce resource consumption and uses a novel auto-mask module that effectively retains only the critical areas of the warped garment while disregarding unrealistic or erroneous portions. Notably, WarpDiffusion can be integrated as a plug-and-play component into existing VITON methodologies, elevating their synthesis quality. Extensive experiments on high-resolution VITON benchmarks and an in-the-wild test set demonstrate the superiority of WarpDiffusion, surpassing state-of-the-art methods both qualitatively and quantitatively.

DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance

Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation models. Nevertheless, these methods often result in either low fidelity or flickering over time due to their limitation to shallow image guidance and poor temporal consistency. To tackle these problems, we propose a high-fidelity image-to-video generation method by devising a frame retention branch on the basis of a pre-trained video diffusion model, named DreamVideo. Instead of integrating the reference image into the diffusion process in a semantic level, our DreamVideo perceives the reference image via convolution layers and concatenate the features with the noisy latents as model input. By this means, the details of the reference image can be preserved to the greatest extent. In addition, by incorporating double-condition classifier-free guidance, a single image can be directed to videos of different actions by providing varying prompt texts. This has significant implications for controllable video generation and holds broad application prospects. We conduct comprehensive experiments on the public dataset, both quantitative and qualitative results indicate that our method outperforms the state-of-the-art method. Especially for fidelity, our model has powerful image retention ability and result in high FVD in UCF101 compared to other image-to-video models. Also, precise control can be achieved by giving different text prompts. Further details and comprehensive results of our model will be presented in https://anonymous0769.github.io/DreamVideo/.

CLOMO: Counterfactual Logical Modification with Large Language Models

In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes for their validity. Specifically, we introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. To effectively evaluate a generation model's counterfactual capabilities, we propose an innovative evaluation metric, the LogicAware Counterfactual Score to directly evaluate the natural language output of LLMs instead of modeling the task as a multiple-choice problem. Analysis shows that the proposed automatic metric aligns well with human preference. Our experimental results show that while LLMs demonstrate a notable capacity for logical counterfactual thinking, there remains a discernible gap between their current abilities and human performance.