NeurIPS 2024 论文列表

We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP-2D) has many benchmarks measuring performance on real-world videos, such as TAPVid-DAVIS, three-dimensional point tracking has none. To this end, leveraging existing footage, we build a new benchmark for 3D point tracking featuring 4,000+ real-world videos, composed of three different data sources spanning a variety of object types, motion patterns, and indoor and outdoor environments. To measure performance on the TAP-3D task, we formulate a collection of metrics that extend the Jaccard-based metric used in TAP-2D to handle the complexities of ambiguous depth scales across models, occlusions, and multi-track spatio-temporal smoothness. We manually verify a large sample of trajectories to ensure correct video annotations, and assess the current state of the TAP-3D task by constructing competitive baselines using existing tracking models. We anticipate this benchmark will serve as a guidepost to improve our ability to understand precise 3D motion and surface deformation from monocular video.

Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for audio captioning, where the joint image-language decoder can be leveraged to describe auditory content associated with image sequences within videos featuring audiovisual content. This can be achieved via multimodal alignment. Yet, this multimodal alignment task is non-trivial due to the inherent disparity between audible and visible elements in real-world videos. Moreover, multimodal representation learning often relies on contrastive learning, facing the challenge of the so-called modality gap which hinders smooth integration between modalities. In this work, we introduce a novel methodology for bridging the audiovisual modality gap by matching the distributions of tokens produced by an audio backbone and those of an image captioner. Our approach aligns the audio token distribution with that of the image tokens, enabling the model to perform zero-shot audio captioning in an unsupervised fashion. This alignment allows for the use of either audio or audiovisual input by combining or substituting the image encoder with the aligned audio encoder. Our method achieves significantly improved performances in zero-shot audio captioning, compared to existing approaches.

Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. As shown in Fig.1, a lightweight transformer interface without tuning any foundation model weights is enough for segmentation, grounding, and retrieval in an interleaved manner. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval. We are the first work aligning foundations models' embeddings for interleave understanding. Meanwhile, our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings.

With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is required to answer the questions according to different key information scattered throughout the given multimodal document. Evaluating the leading MLLMs on MM-NIAH, we observe that existing models still have significant room for improvement on these tasks, especially on vision-centric evaluation. We hope this work can provide a platform for further research on long multimodal document comprehension and contribute to the advancement of MLLMs. Code and benchmark are released at https://github.com/OpenGVLab/MM-NIAH.

Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermore, they differ in their evaluation procedures and the scope of the evaluation, making it difficult to compare models. To address these issues, we extend the HELM framework to VLMs to present the Holistic Evaluation of Vision Language Models (VHELM). VHELM aggregates various datasets to cover one or more of the 9 aspects: *visual perception*, *knowledge*, *reasoning*, *bias*, *fairness*, *multilinguality*, *robustness*, *toxicity*, and *safety*. In doing so, we produce a comprehensive, multi-dimensional view of the capabilities of the VLMs across these important factors. In addition, we standardize the standard inference parameters, methods of prompting, and evaluation metrics to enable fair comparisons across models. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast. Our initial run evaluates 22 VLMs on 21 existing datasets to provide a holistic snapshot of the models. We uncover new key findings, such as the fact that efficiency-focused models (e.g., Claude 3 Haiku or Gemini 1.5 Flash) perform significantly worse than their full models (e.g., Claude 3 Opus or Gemini 1.5 Pro) on the bias benchmark but not when evaluated on the other aspects. For transparency, we release the raw model generations and complete results on our website at https://crfm.stanford.edu/helm/vhelm/v2.0.1. VHELM is intended to be a living benchmark, and we hope to continue adding new datasets and models over time.

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to construct a new Large $\textbf{V}$ision-$\textbf{L}$anguage Model $\textbf{K}$nowledge $\textbf{E}$diting $\textbf{B}$enchmark, $\textbf{VLKEB}$, and extend the Portability metric for more comprehensive evaluation. Leveraging a multi-modal knowledge graph, our image data are bound with knowledge entities. This can be further used to extract entity-related knowledge, which constitutes the base of editing data. We conduct experiments of different editing methods on five LVLMs, and thoroughly analyze how do they impact the models. The results reveal strengths and deficiencies of these methods and hopefully provide insights for future research. The codes and dataset are available at: https://github.com/VLKEB/VLKEB.

As Archimedes famously said, ``Give me a lever long enough and a fulcrum on which to place it, and I shall move the world'', in this study, we propose to use a tiny Language Model (LM), \eg, a Transformer with 67M parameters, to lever much larger Vision-Language Models (LVLMs) with 9B parameters. Specifically, we use this tiny \textbf{Lever-LM} to configure effective in-context demonstration (ICD) sequences to improve the In-Context Learinng (ICL) performance of LVLMs. Previous studies show that diverse ICD configurations like the selection and ordering of the demonstrations heavily affect the ICL performance, highlighting the significance of configuring effective ICD sequences. Motivated by this and by re-considering the the process of configuring ICD sequence, we find this is a mirror process of human sentence composition and further assume that effective ICD configurations may contain internal statistical patterns that can be captured by Lever-LM. Then a dataset with effective ICD sequences is constructed to train Lever-LM. After training, given novel queries, new ICD sequences are configured by the trained Lever-LM to solve vision-language tasks through ICL. Experiments show that these ICD sequences can improve the ICL performance of two LVLMs compared with some strong baselines in Visual Question Answering and Image Captioning, validating that Lever-LM can really capture the statistical patterns for levering LVLMs. The code is available at \url{https://anonymous.4open.science/r/Lever-LM-604A/}.

Prevalent text-to-video retrieval methods represent multimodal text-video data in a joint embedding space, aiming at bridging the relevant text-video pairs and pulling away irrelevant ones. One main challenge in state-of-the-art retrieval methods lies in the modality gap, which stems from the substantial disparities between text and video and can persist in the joint space. In this work, we leverage the potential of Diffusion models to address the text-video modality gap by progressively aligning text and video embeddings in a unified space. However, we identify two key limitations of existing Diffusion models in retrieval tasks: The L2 loss does not fit the ranking problem inherent in text-video retrieval, and the generation quality heavily depends on the varied initial point drawn from the isotropic Gaussian, causing inaccurate retrieval. To this end, we introduce a new Diffusion-Inspired Truncated Sampler (DITS) that jointly performs progressive alignment and modality gap modeling in the joint embedding space. The key innovation of DITS is to leverage the inherent proximity of text and video embeddings, defining a truncated diffusion flow from the fixed text embedding to the video embedding, enhancing controllability compared to adopting the isotropic Gaussian. Moreover, DITS adopts the contrastive loss to jointly consider the relevant and irrelevant pairs, not only facilitating alignment but also yielding a discriminatively structured embedding. Experiments on five benchmark datasets suggest the state-of-the-art performance of DITS. We empirically find that DITS can also improve the structure of the CLIP embedding space. Code is available at https://github.com/Jiamian- Wang/DITS-text-video-retrieval

Large Language Models (LLMs) are increasingly deployed in various applications. As their usage grows, concerns regarding their safety are rising, especially in maintaining harmless responses when faced with malicious instructions. Many defense strategies have been developed to enhance the safety of LLMs. However, our research finds that existing defense strategies lead LLMs to predominantly adopt a rejection-oriented stance, thereby diminishing the usability of their responses to benign instructions. To solve this problem, we introduce the MoGU framework, designed to enhance LLMs' safety while preserving their usability. Our MoGU framework transforms the base LLM into two variants: the usable LLM and the safe LLM, and further employs dynamic routing to balance their contribution. When encountering malicious instructions, the router will assign a higher weight to the safe LLM to ensure that responses are harmless. Conversely, for benign instructions, the router prioritizes the usable LLM, facilitating usable and helpful responses. On various open-sourced LLMs, we compare multiple defense strategies to verify the superiority of our MoGU framework. Besides, our analysis provides key insights into the effectiveness of MoGU and verifies that our designed routing mechanism can effectively balance the contribution of each variant by assigning weights. Our work released the safer Llama2, Vicuna, Falcon, Dolphin, and Baichuan2.

Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting visual representation, e.g., resolution, aspect ratio, and semantic priors, which could impede the flexibility and efficiency of the VLMs. Training pure VLMs that accept the seamless vision and language inputs, i.e., without vision encoders, remains challenging and rarely explored. Empirical observations reveal that direct training without encoders results in slow convergence and large performance gaps. In this work, we bridge the gap between encoder-based and encoder-free models, and present a simple yet effective training recipe towards pure VLMs. Specifically, we unveil the key aspects of training encoder-free VLMs efficiently via thorough experiments: (1) Bridging vision-language representation inside one unified decoder; (2) Enhancing visual recognition capability via extra supervision. With these strategies, we launch EVE, an encoder-free vision-language model that can be trained and forwarded efficiently. Notably, solely utilizing 35M publicly accessible data, EVE can impressively rival the encoder-based VLMs of similar capacities across multiple vision-language benchmarks. It significantly outperforms the counterpart Fuyu-8B with mysterious training procedures and undisclosed training data. We believe that EVE provides a transparent and efficient route for developing pure decoder-only architecture across modalities.

Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core concept of GC is to create a smaller, more manageable graph that retains the characteristics of the original graph. Despite the proliferation of graph condensation methods developed in recent years, there is no comprehensive evaluation and in-depth analysis, which creates a great obstacle to understanding the progress in this field. To fill this gap, we develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation in different scenarios systematically. Specifically, GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We comprehensively evaluate 12 state-of-the-art graph condensation algorithms in node-level and graph-level tasks and analyze their performance in 12 diverse graph datasets. Further, we have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research.The GC-Bench library is available at https://github.com/RingBDStack/GC-Bench.

Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend structural information and conduct general graph reasoning. The potential benefits and capabilities of representing graph structures as visual images (i.e., $\textit{visual graph}$) are still unexplored. To fill the gap, we innovatively propose an end-to-end framework, called $\textbf{G}$raph to v$\textbf{I}$sual and $\textbf{T}$extual Integr$\textbf{A}$tion (GITA), which firstly incorporates visual graphs into general graph reasoning. Besides, we establish $\textbf{G}$raph-based $\textbf{V}$ision-$\textbf{L}$anguage $\textbf{Q}$uestion $\textbf{A}$nswering (GVLQA) dataset from existing graph data, which is the first vision-language dataset for general graph reasoning purposes. Extensive experiments on the GVLQA dataset and five real-world datasets show that GITA outperforms mainstream LLMs in terms of general graph reasoning capabilities. Moreover, We highlight the effectiveness of the layout augmentation on visual graphs and pretraining on the GVLQA dataset.

Vision-Language Models (VLMs) have emerged as the state-of-the-art representation learning solution, with myriads of downstream applications such as image classification, retrieval and generation. A natural question is whether these models memorize their training data, which also has implications for generalization. We propose a new method for measuring memorization in VLMs, which we call dèjá vu memorization. For VLMs trained on image-caption pairs, we show that the model indeed retains information about individual objects in the training images beyond what can be inferred from correlations or the image caption. We evaluate dèjá vu memorization at both sample and population level, and show that it is significant for OpenCLIP trained on as many as 50M image-caption pairs. Finally, we show that text randomization considerably mitigates memorization risk while only moderately impacting the model’s downstream task performance. The code is available here: https://github.com/facebookresearch/VLMDejaVu.

Although Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data, they invariably suffer from hallucinations, leading to a disconnection between the generated text and the corresponding images. Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information that appropriately widens the contrastive logits gap between hallucinatory and targeted ones. However, due to uncontrollable nature of the global visual uncertainty, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations and may even lead to the generation of undesired hallucinations. To tackle this issue, we conducted the theoretical analysis to promote the effectiveness of contrast decoding. Building on this insight, we introduce a novel optimization strategy named Hallucination-Induced Optimization (HIO). This strategy seeks to amplify the contrast between hallucinatory and targeted tokens relying on a fine-tuned theoretical preference model (i.e., Contrary Bradley-Terry Model), thereby facilitating efficient contrast decoding to alleviate hallucinations in LVLMs. Extensive experimental research demonstrates that our HIO strategy can effectively reduce hallucinations in LVLMs, outperforming state-of-the-art methods across various benchmarks.

We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are ideal for processing data captured by event cameras, which are built to simulate neural activities in the human retina. We discuss how to represent the membrane potential of an artificial neuron by a parametric piecewise linear function with learnable coefficients. This design echoes the idea of building deep models from learnable parametric functions recently popularized by Kolmogorov–Arnold Networks (KANs). Experiments demonstrate the state-of-the-art performance of PPLNs in event-based and image-based vision applications, including steering prediction, human pose estimation, and motion deblurring.

We propose to explore an interesting and promising problem, Cloud Object Detector Adaptation (CODA), where the target domain leverages detections provided by a large cloud model to build a target detector. Despite with powerful generalization capability, the cloud model still cannot achieve error-free detection in a specific target domain. In this work, we present a novel Cloud Object detector adaptation method by Integrating different source kNowledge (COIN). The key idea is to incorporate a public vision-language model (CLIP) to distill positive knowledge while refining negative knowledge for adaptation by self-promotion gradient direction alignment. To that end, knowledge dissemination, separation, and distillation are carried out successively. Knowledge dissemination combines knowledge from cloud detector and CLIP model to initialize a target detector and a CLIP detector in target domain. By matching CLIP detector with the cloud detector, knowledge separation categorizes detections into three parts: consistent, inconsistent and private detections such that divide-and-conquer strategy can be used for knowledge distillation. Consistent and private detections are directly used to train target detector; while inconsistent detections are fused based on a consistent knowledge generation network, which is trained by aligning the gradient direction of inconsistent detections to that of consistent detections, because it provides a direction toward an optimal target detector. Experiment results demonstrate that the proposed COIN method achieves the state-of-the-art performance.

With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness---the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness metrics have been proposed, leveraging advances in cross-modal embeddings and vision-language models (VLMs). However, these metrics are not rigorously compared and benchmarked, instead presented with correlation to human Likert scores over a set of easy-to-discriminate images against seemingly weak baselines. We introduce T2IScoreScore, a curated set of semantic error graphs containing a prompt and a set of increasingly erroneous images. These allow us to rigorously judge whether a given prompt faithfulness metric can correctly order images with respect to their objective error count and significantly discriminate between different error nodes, using meta-metric scores derived from established statistical tests. Surprisingly, we find that the state-of-the-art VLM-based metrics (e.g., TIFA, DSG, LLMScore, VIEScore) we tested fail to significantly outperform simple (and supposedly worse) feature-based metrics like CLIPScore, particularly on a hard subset of naturally-occurring T2I model errors. TS2 will enable the development of better T2I prompt faithfulness metrics through more rigorous comparison of their conformity to expected orderings and separations under objective criteria.

High-quality, large-scale corpora are the cornerstone of building foundation models. In this work, we introduce MathPile, a diverse and high-quality math-centric corpus comprising about 9.5 billion tokens. Throughout its creation, we adhered to the principle of “less is more”, firmly believing in the supremacy of data quality over quantity, even in the pre-training phase. Our meticulous data collection and processing efforts included a complex suite of preprocessing, prefiltering, language identification, cleaning, filtering, and deduplication, ensuring the high quality of our corpus. Furthermore, we performed data contamination detection on downstream benchmark test sets to eliminate duplicates and conducted continual pre-training experiments, booting the performance on common mathematical reasoning benchmarks. We aim for our MathPile to boost language models’ mathematical reasoning abilities and open-source its different versions and processing scripts to advance the field.

Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical tasks. This work targets ante hoc interpretability, and specifically Concept Bottleneck Models (CBMs). Our goal is to design a framework that admits a highly interpretable decision making process with respect to human understandable concepts, on two levels of granularity. To this end, we propose a novel two-level concept discovery formulation leveraging: (i) recent advances in vision-language models, and (ii) an innovative formulation for coarse-to-fine concept selection via data-driven and sparsity inducing Bayesian arguments. Within this framework, concept information does not solely rely on the similarity between the whole image and general unstructured concepts; instead, we introduce the notion of concept hierarchy to uncover and exploit more granular concept information residing in patch-specific regions of the image scene. As we experimentally show, the proposed construction not only outperforms recent CBM approaches, but also yields a principled framework towards interpetability.