NeurIPS 2024 论文列表

This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M$^3$GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M$^3$GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M$^3$GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: \url{https://github.com/luomingshuang/M3GPT}.

Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method results in sub-optimal cross-modal alignment by over-emphasizing the text tokens that are less correlated with or even contradictory with the input images. In this paper, we advocate for distinct contributions for each text token based on its visual correlation. Specifically, we present by contrasting image inputs, the difference in prediction logits on each text token provides strong guidance of visual correlation. We therefore introduce Contrastive Alignment (CAL), a simple yet effective re-weighting strategy that prioritizes training visually correlated tokens. Our experimental results demonstrate that CAL consistently improves different types of VLMs across different resolutions and model sizes on various benchmark datasets. Importantly, our method incurs minimal additional computational overhead, rendering it highly efficient compared to alternative data scaling strategies.

Diverse human motion prediction (HMP) is a fundamental application in computer vision that has recently attracted considerable interest. Prior methods primarily focus on the stochastic nature of human motion, while neglecting the specific impact of external environment, leading to the pronounced artifacts in prediction when applied to real-world scenarios. To fill this gap, this work introduces a novel task: predicting diverse human motion within real-world 3D scenes. In contrast to prior works, it requires harmonizing the deterministic constraints imposed by the surrounding 3D scenes with the stochastic aspect of human motion. For this purpose, we propose DiMoP3D, a diverse motion prediction framework with 3D scene awareness, which leverages the 3D point cloud and observed sequence to generate diverse and high-fidelity predictions. DiMoP3D is able to comprehend the 3D scene, and determines the probable target objects and their desired interactive pose based on the historical motion. Then, it plans the obstacle-free trajectory towards these interested objects, and generates diverse and physically-consistent future motions. On top of that, DiMoP3D identifies deterministic factors in the scene and integrates them into the stochastic modeling, making the diverse HMP in realistic scenes become a controllable stochastic generation process. On two real-captured benchmarks, DiMoP3D has demonstrated significant improvements over state-of-the-art methods, showcasing its effectiveness in generating diverse and physically-consistent motion predictions within real-world 3D environments.

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Although learnable approaches like Q-Former and Perceiver Resampler have been developed to reduce the vision token burden, they overlook the context causally modeled by LLMs (i.e., key-value cache), potentially leading to missed visual cues when addressing user queries. In this paper, we introduce a novel approach to reduce vision compute by leveraging redundant vision tokens ``skipping layers'' rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video. Specifically, for certain transformer layer, we learn to skip the computation for a high proportion (e.g., 80\%) of vision tokens, passing them directly to the next layer. This approach significantly enhances model efficiency, achieving approximately 42% time and 30% memory savings for the entire training. Moreover, our method reduces the computation in the context and avoid decreasing the vision tokens, thus preserving or even improving performance compared to the vanilla model. We conduct extensive experiments to demonstrate the effectiveness of VideoLLM-MoD, showing its state-of-the-art results on multiple benchmarks, including narration, forecasting, and summarization tasks in COIN, Ego4D, and Ego-Exo4D datasets. The code and checkpoints will be made available at github.com/showlab/VideoLLM-online.

Verbal and visual-spatial information processing are two critical subsystems that activate different brain regions and often collaborate together for cognitive reasoning. Despite the rapid advancement of LLM-based reasoning, the mainstream frameworks, such as Chain-of-Thought (CoT) and its variants, primarily focus on the verbal dimension, resulting in limitations in tackling reasoning problems with visual and spatial clues. To bridge the gap, we propose a novel dual-modality reasoning framework called Vision-Augmented Prompting (VAP). Upon receiving a textual problem description, VAP automatically synthesizes an image from the visual and spatial clues by utilizing external drawing tools. Subsequently, VAP formulates a chain of thought in both modalities and iteratively refines the synthesized image. Finally, a conclusive reasoning scheme based on self-alignment is proposed for final result generation. Extensive experiments are conducted across four versatile tasks, including solving geometry problems, Sudoku, time series prediction, and travelling salesman problem. The results validated the superiority of VAP over existing LLMs-based reasoning frameworks.

Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify salient objects, consistently achieving a high recall rate remains difficult due to the diversity of object types and their contextual complexity. In this work, we investigate using vision-language models (VLMs) to enhance object detection via a self-supervised prompt learning strategy. Our initial findings indicate that manually crafted text queries often result in undetected objects, primarily because detection confidence diminishes when the query words exhibit semantic overlap. To address this, we propose a Dispersing Prompt Expansion (DiPEx) approach. DiPEx progressively learns to expand a set of distinct, non-overlapping hyperspherical prompts to enhance recall rates, thereby improving performance in downstream tasks such as out-of-distribution OD. Specifically, DiPEx initiates the process by self-training generic parent prompts and selecting the one with the highest semantic uncertainty for further expansion. The resulting child prompts are expected to inherit semantics from their parent prompts while capturing more fine-grained semantics. We apply dispersion losses to ensure high inter-class discrepancy among child prompts while preserving semantic consistency between parent-child prompt pairs. To prevent excessive growth of the prompt sets, we utilize the maximum angular coverage (MAC) of the semantic space as a criterion for early termination. We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20.1% in AR and achieving a 21.3% AP improvement over SAM.

Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding suffer from severe limitations in data modality, scope, diversity, and scale. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated question answering pairs across 9 distinct question categories, covering complex scenarios and object modalities within 3D scenes. We introduce a novel interleaved multi modal input setting in our benchmark to provide both texts, images, and point clouds for situation and question description, aiming to resolve ambiguity in describing situations with single-modality inputs (e.g., texts). Additionally, we devise the Multi-modal Next-step Navigation (MSNN) benchmark to evaluate models’ grounding of actions and transitions between situations. Comprehensive evaluations on reasoning and navigation tasks highlight the limitations of existing vision-language models and underscore the importance of handling multi-modal interleaved inputs and situation modeling. Experiments on data scaling and cross domain transfer further demonstrate the effectiveness of leveraging MSQA as a pre-training dataset for developing more powerful situated reasoning models, contributing to advancements in 3D scene understanding for embodied AI.

Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like ImageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes; when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected ImageWikiQA dataset.

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In this paper, we present a novel framework for the interpretation of LMMs. We propose a dictionary learning based approach, applied to the representation of tokens. The elements of the learned dictionary correspond to our proposed concepts. We show that these concepts are well semantically grounded in both vision and text. Thus we refer to these as ``multi-modal concepts''. We qualitatively and quantitatively evaluate the results of the learnt concepts. We show that the extracted multimodal concepts are useful to interpret representations of test samples. Finally, we evaluate the disentanglement between different concepts and the quality of grounding concepts visually and textually. Our implementation is publicly available: https://github.com/mshukor/xl-vlms.

Domain generalization (DG) is a fundamental yet challenging topic in machine learning. Recently, the remarkable zero-shot capabilities of the large pre-trained vision-language model (e.g., CLIP) have made it popular for various downstream tasks. However, the effectiveness of this capacity often degrades when there are shifts in data distribution during testing compared to the training data. In this paper, we propose a novel method, known as CLIPCEIL, a model that utilizes Channel rEfinement and Image-text aLignment to facilitate the CLIP to the inaccessible $\textit{out-of-distribution}$ test datasets that exhibit domain shifts. Specifically, we refine the feature channels in the visual domain to ensure they contain domain-invariant and class-relevant features by using a lightweight adapter. This is achieved by minimizing the inter-domain variance while maximizing the inter-class variance. In the meantime, we ensure the image-text alignment by aligning text embeddings of the class descriptions and their corresponding image embedding while further removing the domain-specific features. Moreover, our model integrates multi-scale CLIP features by utilizing a self-attention fusion module, technically implemented through one Transformer layer. Extensive experiments on five widely used benchmark datasets demonstrate that CLIPCEIL outperforms the existing state-of-the-art methods. The source code is available at \url{https://github.com/yuxi120407/CLIPCEIL}.

Reflective photoplethysmography (PPG) has become the default sensing technique in wearable devices to monitor cardiac activity via a person’s heart rate (HR). However, PPG-based HR estimates can be substantially impacted by factors such as the wearer’s activities, sensor placement and resulting motion artifacts, as well as environmental characteristics such as temperature and ambient light. These and other factors can significantly impact and decrease HR prediction reliability. In this paper, we show that state-of-the-art HR estimation methods struggle when processing representative data from everyday activities in outdoor environments, likely because they rely on existing datasets that captured controlled conditions. We introduce a novel multimodal dataset and benchmark results for continuous PPG recordings during outdoor activities from 16 participants over 13.5 hours, captured from four wearable sensors, each worn at a different location on the body, totaling 216 hours. Our recordings include accelerometer, temperature, and altitude data, as well as a synchronized Lead I-based electrocardiogram for ground-truth HR references. Participants completed a round trip from Zurich to Jungfraujoch, a tall mountain in Switzerland over the course of one day. The trip included outdoor and indoor activities such as walking, hiking, stair climbing, eating, drinking, and resting at various temperatures and altitudes (up to 3,571 m above sea level) as well as using cars, trains, cable cars, and lifts for transport—all of which impacted participants’ physiological dynamics. We also present a novel method that estimates HR values more robustly in such real-world scenarios than existing baselines. Dataset & code for HR estimation: https://siplab.org/projects/WildPPG

Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of CAV often necessitates a large number of high-quality images, which are expensive to curate and thus limited to a predefined set of concepts. To address this issue, we propose Language-Guided CAV (LG-CAV) to harness the abundant concept knowledge within the certain pre-trained vision-language models (e.g., CLIP). This method allows training any CAV without labeled data, by utilizing the corresponding concept descriptions as guidance. To bridge the gap between vision-language model and the target model, we calculate the activation values of concept descriptions on a common pool of images (probe images) with vision-language model and utilize them as language guidance to train the LG-CAV. Furthermore, after training high-quality LG-CAVs related to all the predicted classes in the target model, we propose the activation sample reweighting (ASR), serving as a model correction technique, to improve the performance of the target model in return. Experiments on four datasets across nine architectures demonstrate that LG-CAV achieves significantly superior quality to previous CAV methods given any concept, and our model correction method achieves state-of-the-art performance compared to existing concept-based methods. Our code is available at https://github.com/hqhQAQ/LG-CAV.

We present the Noisy Ostracods, a noisy dataset for genus and species classification of crustacean ostracods with specialists’ annotations. Over the 71466 specimens collected, 5.58% of them are estimated to be noisy (possibly problematic) at genus level. The dataset is created to addressing a real-world challenge: creating a clean fine-grained taxonomy dataset. The Noisy Ostracods dataset has diverse noises from multiple sources. Firstly, the noise is open-set, including new classes discovered during curation that were not part of the original annotation. The dataset has pseudo-classes, where annotators misclassified samples that should belong to an existing class into a new pseudo-class. The Noisy Ostracods dataset is highly imbalanced with a imbalance factor ρ = 22429. This presents a unique challenge for robust machine learning methods, as existing approaches have not been extensively evaluated on fine-grained classification tasks with such diverse real-world noise. Initial experiments using current robust learning techniques have not yielded significant performance improvements on the Noisy Ostracods dataset compared to cross-entropy training on the raw, noisy data. On the other hand, noise detection methods have underperformed in error hit rate compared to naive cross-validation ensembling for identifying problematic labels. These findings suggest that the fine-grained, imbalanced nature, and complex noise characteristics of the dataset present considerable challenges for existing noiserobust algorithms. By openly releasing the Noisy Ostracods dataset, our goal is to encourage further research into the development of noise-resilient machine learning methods capable of effectively handling diverse, real-world noise in finegrained classification tasks. The dataset, along with its evaluation protocols, can be accessed at https://github.com/H-Jamieu/Noisy_ostracods.

Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on human-designed text prompts or fixed templates, limiting their diversity and complexity, and yielding low discriminative power. We propose ConceptMix, a scalable, controllable, and customizable benchmark which automatically evaluates compositional generation ability of T2I models. This is done in two stages. First, ConceptMix generates the text prompts: concretely, using categories of visual concepts (e.g., objects, colors, shapes, spatial relationships), it randomly samples an object and k-tuples of visual concepts, then uses GPT-4o to generate text prompts for image generation based on these sampled concepts. Second, ConceptMix evaluates the images generated in response to these prompts: concretely, it checks how many of the k concepts actually appeared in the image by generating one question per visual concept and using a strong VLM to answer them. Through administering ConceptMix to a diverse set of T2I models (proprietary as well as open ones) using increasing values of k, we show that our ConceptMix has higher discrimination power than earlier benchmarks. Specifically, ConceptMix reveals that the performance of several models, especially open models, drops dramatically with increased k. Importantly, it also provides insight into the lack of prompt diversity in widely-used training datasets. Additionally, we conduct extensive human studies to validate the design of ConceptMix and compare our automatic grading with human judgement. We hope it will guide future T2I model development.

Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through learnable latent variable optimization. We observe that attention, as the core module of MLLMs, connects text prompt tokens and visual tokens, ultimately determining the final results. Our approach involves adjusting visual tokens from the MLP output during inference, controlling the attention response to ensure text prompt tokens attend to visual tokens in referring regions. We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point. The results demonstrate that our method exhibits out-of-domain generalization and interpretability.

This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. Particularly focusing on visual and linguistic modalities, we categorize data knowledge into five unit types, namely, in-image, in-text, cross-image, cross-text, and image-text, and set up an efficient pipeline to help construct the multimodal knowledge graph from any data collection. Thanks to the logical information naturally contained in knowledge graph, organizing datasets under UKnow format opens up more possibilities of data usage compared to the commonly used image-text pairs. Following UKnow protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset that consists of 1,388,568 nodes (with 571,791 vision-related ones) and 3,673,817 triplets. The dataset is also annotated with rich event tags, including 11 coarse labels and 9,185 fine labels. Experiments on four benchmarks demonstrate the potential of UKnow in supporting common-sense reasoning and boosting vision-language pre-training with a single dataset, benefiting from its unified form of knowledge organization. Code, dataset, and models will be made publicly available. See Appendix to download the dataset.

Accurate estimation of human pose and the pose of interacting objects, like a hockey stick, is crucial for action recognition and performance analysis, particularly in sports. Existing methods capture the object along with the human in the bounding boxes, assuming all keypoints are visible within the bounding box. This necessitates larger bounding boxes to capture the object, introducing unnecessary visual features and hindering performance in real-world cluttered environments. We propose a simple image and text-based multimodal solution TokenCLIPose that addresses this limitation. Our approach focuses solely on human keypoints within the bounding box, treating objects as unseen. TokenCLIPose leverages the rich semantic representations endowed by language for inducing keypoint-specific context, even for occluded keypoints. We evaluate the performance of TokenCLIPose on a real-world Ice-Hockey dataset, and demonstrate its generalizability through zero-shot transfer to a smaller Lacrosse dataset. Additionally, we showcase its flexibility on CrowdPose, a popular occlusion benchmark with keypoints within the bounding box. Our method significantly improves over state-of-the-art approaches on all three datasets, with gains of 4.36\%, 2.35\%, and 3.8\%, respectively.

Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate scientific concepts, deriving symbolic equations, and solving advanced numerical calculations. To bridge these gaps, we introduce SciInstruct, a suite of scientific instructions for training scientific language models capable of college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This framework leverages existing LLMs to generate step-by-step reasoning for unlabelled scientific questions, followed by a process of self-reflective critic-and-revise. Applying this framework, we curated a diverse and high-quality dataset encompassing physics, chemistry, math, and formal proofs. We analyze the curated SciInstruct from multiple interesting perspectives (e.g., domain, scale, source, question type, answer length, etc.). To verify the effectiveness of SciInstruct, we fine-tuned different language models with SciInstruct, i.e., ChatGLM3 (6B and 32B), Llama3-8B-Instruct, and Mistral-7B: MetaMath, enhancing their scientific and mathematical reasoning capabilities, without sacrificing the language understanding capabilities of the base model. We release all codes and SciInstruct at https://github.com/THUDM/SciGLM.