NeurIPS 2024 论文列表

Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on domain-specific empirical approaches utilizing downstream tasks, primarily because of the lack of a standardized framework for comparison. However, acquiring adequately large and representative datasets for conducting these assessments is not always viable and can prove to be prohibitively expensive and time-consuming. In this paper, we present a unified approach to evaluate embedders. First, we establish theoretical foundations for comparing embedding models, drawing upon the concepts of sufficiency and informativeness. We then leverage these concepts to devise a tractable comparison criterion (information sufficiency), leading to a task-agnostic and self-supervised ranking procedure. We demonstrate experimentally that our approach aligns closely with the capability of embedding models to facilitate various downstream tasks in both natural language processing and molecular biology. This effectively offers practitioners a valuable tool for prioritizing model trials.

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently explored and disconnected from visual representation learning research. This gap hinders accurate sensory grounding in real-world scenarios. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations, offering new insights into different models and architectures—self-supervised, strongly supervised, or combinations thereof—based on experiments with over 15 vision models. We critically examine existing MLLM benchmarks, addressing the difficulties involved in consolidating and interpreting results from various tasks. To further improve visual grounding, we propose spatial vision aggregator (SVA), a dynamic and spatially-aware connector that integrates vision features with LLMs while reducing the number of tokens. Additionally, we discuss the curation of high-quality visual instruction-tuning data from publicly available sources, emphasizing the importance of distribution balancing. Collectively, Cambrian-1 not only achieves state-of-the-art performances but also serves as a comprehensive, open cookbook for instruction-tuned MLLMs. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes. We hope our release will inspire and accelerate advancements in multimodal systems and visual representation learning.

Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. To address this issue, we propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements, and vice versa. Our results indicate that the synthetic data pipeline can provide useful training data and improve the performance of LLMs in translating and understanding complex mathematical problems and proofs. Our final dataset contains about 57K formal-informal question pairs along with searched proof from the math contest forum and 21 new IMO questions. We open-source our code at \url{https://github.com/InternLM/InternLM-Math} and our data at \url{https://huggingface.co/datasets/InternLM/Lean-Workbook}.

Drug-induced toxicity is one of the leading reasons new drugs fail clinical trials. Machine learning models that predict drug toxicity from molecular structure could help researchers prioritize less toxic drug candidates. However, current toxicity datasets are typically small and limited to a single organ system (e.g., cardio, renal, or liver). Creating these datasets often involved time-intensive expert curation by parsing drug labelling documents that can exceed 100 pages per drug. Here, we introduce UniTox, a unified dataset of 2,418 FDA-approved drugs with drug-induced toxicity summaries and ratings created by using GPT-4o to process FDA drug labels. UniTox spans eight types of toxicity: cardiotoxicity, liver toxicity, renal toxicity, pulmonary toxicity, hematological toxicity, dermatological toxicity, ototoxicity, and infertility. This is, to the best of our knowledge, the largest such systematic human in vivo database by number of drugs and toxicities, and the first covering nearly all non-combination FDA-approved medications for several of these toxicities. We recruited clinicians to validate a random sample of our GPT-4o annotated toxicities, and UniTox's toxicity ratings concord with clinician labelers 85-96\% of the time. Finally, we benchmark several machine learning models trained on UniTox to demonstrate the utility of this dataset for building molecular toxicity prediction models.

Due to the recent remarkable advances in artificial intelligence, researchers have begun to consider challenging learning problems such as learning to generalize behavior from large offline datasets or learning online in non-Markovian environments. Meanwhile, recent advances in both of these areas have increasingly relied on conditioning policies on large context lengths. A natural question is if there is a limit to the performance benefits of increasing the context length if the computation needed is available. In this work, we establish a novel theoretical result that links the context length of a policy to the time needed to reliably evaluate its performance (i.e., its mixing time) in large scale partially observable reinforcement learning environments that exhibit latent sub-task structure. This analysis underscores a key tradeoff: when we extend the context length, our policy can more effectively model non-Markovian dependencies, but this comes at the cost of potentially slower policy evaluation and as a result slower downstream learning. Moreover, our empirical results highlight the relevance of this analysis when leveraging Transformer based neural networks. This perspective will become increasingly pertinent as the field scales towards larger and more realistic environments, opening up a number of potential future directions for improving the way we design learning agents.

Current benchmarks for evaluating large language models (LLMs) in medicine are primarily focused on question-answering involving domain knowledge and descriptive reasoning. While such qualitative capabilities are vital to medical diagnosis, in real-world scenarios, doctors frequently use clinical calculators that follow quantitative equations and rule-based reasoning paradigms for evidence-based decision support. To this end, we propose MedCalc-Bench, a first-of-its-kind dataset focused on evaluating the medical calculation capability of LLMs. MedCalc-Bench contains an evaluation set of over 1000 manually reviewed instances from 55 different medical calculation tasks. Each instance in MedCalc-Bench consists of a patient note, a question requesting to compute a specific medical value, a ground truth answer, and a step-by-step explanation showing how the answer is obtained. While our evaluation results show the potential of LLMs in this area, none of them are effective enough for clinical settings. Common issues include extracting the incorrect entities, not using the correct equation or rules for a calculation task, or incorrectly performing the arithmetic for the computation. We hope our study highlights the quantitative knowledge and reasoning gaps in LLMs within medical settings, encouraging future improvements of LLMs for various clinical calculation tasks. MedCalc-Bench is publicly available at: https://github.com/ncbi-nlp/MedCalc-Bench.

Neural operators effectively solve PDE problems from data without knowing the explicit equations, which learn the map from the input sequences of observed samples to the predicted values. Most existing works build the model in the original geometric space, leading to high computational costs when the number of sample points is large. We present the Latent Neural Operator (LNO) solving PDEs in the latent space. In particular, we first propose Physics-Cross-Attention (PhCA) transforming representation from the geometric space to the latent space, then learn the operator in the latent space, and finally recover the real-world geometric space via the inverse PhCA map. Our model retains flexibility that can decode values in any position not limited to locations defined in the training set, and therefore can naturally perform interpolation and extrapolation tasks particularly useful for inverse problems. Moreover, the proposed LNO improves both prediction accuracy and computational efficiency. Experiments show that LNO reduces the GPU memory by 50%, speeds up training 1.8 times, and reaches state-of-the-art accuracy on four out of six benchmarks for forward problems and a benchmark for inverse problem. Code is available at https://github.com/L-I-M-I-T/LatentNeuralOperator.

Recent work demonstrates that, post-training large language models with open-domain instruction following data have achieved colossal success. Simultaneously, human Chatbot Arena has emerged as one of the most reasonable benchmarks for model evaluation and developmental guidance. However, the processes of manually curating high-quality training data and utilizing online human evaluation platforms are both expensive and limited. To mitigate the manual and temporal costs associated with post-training, this paper introduces a Simulated Chatbot Arena named WizardArena, which is fully based on and powered by open-source LLMs. For evaluation scenario, WizardArena can efficiently predict accurate performance rankings among different models based on offline test set. For training scenario, we simulate arena battles among various state-of-the-art models on a large scale of instruction data, subsequently leveraging the battle results to constantly enhance target model in both the supervised fine-tuning and reinforcement learning . Experimental results demonstrate that our WizardArena aligns closely with the online human arena rankings, and our models trained on offline extensive battle data exhibit significant performance improvements during SFT, DPO, and PPO stages.

Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning. In this paper, we evaluate the effectiveness of $12$ state-of-the-art (SOTA) VLMs in the field of organismal biology using a novel dataset, VLM4Bio, consisting of $469K$ question-answer pairs involving $30K$ images from three groups of organisms: fishes, birds, and butterflies, covering five biologically relevant tasks. We also explore the effects of applying prompting techniques and tests for reasoning hallucination on the performance of VLMs, shedding new light on the capabilities of current SOTA VLMs in answering biologically relevant questions using images.

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class pairs. Despite rigorous filtering, these pre-training datasets often inevitably contain corrupted pairs where conditions do not accurately describe the data. This paper presents the first comprehensive study on the impact of such corruption in pre-training data of DMs. We synthetically corrupt ImageNet-1K and CC3M to pre-train and evaluate over $50$ conditional DMs. Our empirical findings reveal that various types of slight corruption in pre-training can significantly enhance the quality, diversity, and fidelity of the generated images across different DMs, both during pre-training and downstream adaptation stages. Theoretically, we consider a Gaussian mixture model and prove that slight corruption in the condition leads to higher entropy and a reduced 2-Wasserstein distance to the ground truth of the data distribution generated by the corruptly trained DMs. Inspired by our analysis, we propose a simple method to improve the training of DMs on practical datasets by adding condition embedding perturbations (CEP). CEP significantly improves the performance of various DMs in both pre-training and downstream tasks. We hope that our study provides new insights into understanding the data and pre-training processes of DMs.

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked in existing datasets. In this paper, we address this underexplored problem by presenting a framework for "renovating" names in open-vocabulary segmentation benchmarks (RENOVATE). Our framework features a renaming model that enhances the quality of names for each visual segment. Through experiments, we demonstrate that our renovated names help train stronger open-vocabulary models with up to 15% relative improvement and significantly enhance training efficiency with improved data quality. We also show that our renovated names improve evaluation by better measuring misclassification and enabling fine-grained model analysis. We provide our code and relabelings for several popular segmentation datasets to the research community on our project page: https://andrehuang.github.io/renovate.

Offline safe reinforcement learning (RL) aims to find an optimal policy using a pre-collected dataset when data collection is impractical or risky. We propose a novel linear programming (LP) based primal-dual algorithm for convex MDPs that incorporates ``uncertainty'' parameters to improve data efficiency while requiring only partial data coverage assumption. Our theoretical results achieve a sample complexity of $\mathcal{O}(1/(1-\gamma)\sqrt{n})$ under general function approximation, improving the current state-of-the-art by a factor of $1/(1-\gamma)$, where $n$ is the number of data samples in an offline dataset, and $\gamma$ is the discount factor. The numerical experiments validate our theoretical findings, demonstrating the practical efficacy of our approach in achieving improved safety and learning efficiency in safe offline settings.

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems. The precision of the solution to ODEs significantly affects parameter optimization, thereby impacting model performance. In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true ``solution.'' First, we introduce a predictor-corrector learning framework to minimize truncation errors, which consists of a high-order predictor and a multistep corrector. Second, we propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Extensive experiments on large-scale machine translation, abstractive summarization, language modeling, and natural language understanding benchmarks demonstrate the superiority of our approach. On the WMT'14 English-German and English-French tasks, our model achieved BLEU scores of 30.95 and 44.27, respectively. Furthermore, on the OPUS multilingual machine translation task, our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters. Notably, it also beats LLama models by 5.7 accuracy points on the LM Harness Evaluation.

AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model”. This raises questions. Do such models "know'' that they are LLMs and reliably act on this knowledge? Are they "aware" of their current circumstances, such as being deployed to the public? We refer to a model's knowledge of itself and its circumstances as **situational awareness**. To quantify situational awareness in LLMs, we introduce a range of behavioral tests, based on question answering and instruction following. These tests form the **Situational Awareness Dataset (SAD)**, a benchmark comprising 7 task categories and over 13,000 questions. The benchmark tests numerous abilities, including the capacity of LLMs to (i) recognize their own generated text, (ii) predict their own behavior, (iii) determine whether a prompt is from internal evaluation or real-world deployment, and (iv) follow instructions that depend on self-knowledge. We evaluate 16 LLMs on SAD, including both base (pretrained) and chat models. While all models perform better than chance, even the highest-scoring model (Claude 3 Opus) is far from a human baseline on certain tasks. We also observe that performance on SAD is only partially predicted by metrics of general knowledge. Chat models, which are finetuned to serve as AI assistants, outperform their corresponding base models on SAD but not on general knowledge tasks. The purpose of SAD is to facilitate scientific understanding of situational awareness in LLMs by breaking it down into quantitative abilities. Situational awareness is important because it enhances a model's capacity for autonomous planning and action. While this has potential benefits from automation, it also introduces novel risks related to AI safety and control.

We study cultural and socioeconomic diversity in contrastive vision-language models (VLMs). Using a broad range of benchmark datasets and evaluation metrics, we bring to attention several important findings. First, the common filtering of training data to English image-text pairs disadvantages communities of lower socioeconomic status and negatively impacts cultural understanding. Notably, this performance gap is not captured by - and even at odds with - the currently popular evaluation metrics derived from the Western-centric ImageNet and COCO datasets. Second, pretraining with global, unfiltered data before fine-tuning on English content can improve cultural understanding without sacrificing performance on said popular benchmarks. Third, we introduce the task of geo-localization as a novel evaluation metric to assess cultural diversity in VLMs. Our work underscores the value of using diverse data to create more inclusive multimodal systems and lays the groundwork for developing VLMs that better represent global perspectives.

We propose a new comprehensive benchmark to revolutionize the current deepfake detection field to the next generation. Predominantly, existing works identify top-notch detection algorithms and models by adhering to the common practice: training detectors on one specific dataset (*e.g.,* FF++) and testing them on other prevalent deepfake datasets. This protocol is often regarded as a "golden compass" for navigating SoTA detectors. But can these stand-out "winners" be truly applied to tackle the myriad of realistic and diverse deepfakes lurking in the real world? If not, what underlying factors contribute to this gap? In this work, we found the **dataset** (both train and test) can be the "primary culprit" due to the following: (1) *forgery diversity*: Deepfake techniques are commonly referred to as both face forgery (face-swapping and face-reenactment) and entire image synthesis (AIGC, especially face). Most existing datasets only contain partial types of them, with limited forgery methods implemented (*e.g.,* 2 swapping and 2 reenactment methods in FF++); (2) *forgery realism*: The dominated training dataset, FF++, contains out-of-date forgery techniques from the past four years. "Honing skills" on these forgeries makes it difficult to guarantee effective detection generalization toward nowadays' SoTA deepfakes; (3) *evaluation protocol*: Most detection works perform evaluations on one type, *e.g.,* face-swapping types only, which hinders the development of universal deepfake detectors. To address this dilemma, we construct a highly diverse and large-scale deepfake detection dataset called **DF40**, which comprises **40** distinct deepfake techniques (10 times larger than FF++). We then conduct comprehensive evaluations using **4** standard evaluation protocols and **8** representative detection methods, resulting in over **2,000** evaluations. Through these evaluations, we provide an extensive analysis from various perspectives, leading to **7** new insightful findings contributing to the field. We also open up **4** valuable yet previously underexplored research questions to inspire future works. We release our dataset, code, and pre-trained weights at https://github.com/YZY-stack/DF40.

A popular paradigm for offline Reinforcement Learning (RL) tasks is to first fit the offline trajectories to a sequence model, and then prompt the model for actions that lead to high expected return. In addition to obtaining accurate sequence models, this paper highlights that tractability, the ability to exactly and efficiently answer various probabilistic queries, plays an important role in offline RL. Specifically, due to the fundamental stochasticity from the offline data-collection policies and the environment dynamics, highly non-trivial conditional/constrained generation is required to elicit rewarding actions. While it is still possible to approximate such queries, we observe that such crude estimates undermine the benefits brought by expressive sequence models. To overcome this problem, this paper proposes Trifle (Tractable Inference for Offline RL), which leverages modern tractable generative models to bridge the gap between good sequence models and high expected returns at evaluation time. Empirically, Trifle achieves $7$ state-of-the-art scores and the highest average scores in $9$ Gym-MuJoCo benchmarks against strong baselines. Further, Trifle significantly outperforms prior approaches in stochastic environments and safe RL tasks with minimum algorithmic modifications.

In this work, we introduce *Scribbles for All*, a label and training data generation algorithm for semantic segmentation trained on scribble labels. Training or fine-tuning semantic segmentation models with weak supervision has become an important topic recently and was subject to significant advances in model quality. In this setting, scribbles are a promising label type to achieve high quality segmentation results while requiring a much lower annotation effort than usual pixel-wise dense semantic segmentation annotations. The main limitation of scribbles as source for weak supervision is the lack of challenging datasets for scribble segmentation, which hinders the development of novel methods and conclusive evaluations. To overcome this limitation, *Scribbles for All* provides scribble labels for several popular segmentation datasets and provides an algorithm to automatically generate scribble labels for any dataset with dense annotations, paving the way for new insights and model advancements in the field of weakly supervised segmentation. In addition to providing datasets and algorithm, we evaluate state-of-the-art segmentation models on our datasets and show that models trained with our synthetic labels perform competitively with respect to models trained on manual labels. Thus, our datasets enable state-of-the-art research into methods for scribble-labeled semantic segmentation. The datasets, scribble generation algorithm, and baselines are publicly available at https://github.com/wbkit/Scribbles4All.

The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to automatically augment datasets, unlocking the full potential of deep models. Current data expansion techniques include image transformation and image synthesis methods. Transformation-based methods introduce only local variations, leading to limited diversity. In contrast, synthesis-based methods generate entirely new content, greatly enhancing informativeness. However, existing synthesis methods carry the risk of distribution deviations, potentially degrading model performance with out-of-distribution samples. In this paper, we propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model. DistDiff constructs hierarchical prototypes to approximate the real data distribution, optimizing latent data points within diffusion models with hierarchical energy guidance. We demonstrate its capability to generate distribution-consistent samples, significantly improving data expansion tasks. DistDiff consistently enhances accuracy across a diverse range of datasets compared to models trained solely on original data. Furthermore, our approach consistently outperforms existing synthesis-based techniques and demonstrates compatibility with widely adopted transformation-based augmentation methods. Additionally, the expanded dataset exhibits robustness across various architectural frameworks.