论文检索

Deep Learning · Generative Models and Autoencoders

Sumeet Singh, Vikas Sindhwani, Stephen Tu

A crucial design decision for any robot learning pipeline is the choice of policy representation: what type of model should be used to generate the next set of robot actions? Owing to the inherent multi-modal nature of many robotic tasks, combined with the recent successes in generative modeling, researchers have turned to state-of-the-art probabilistic models such as diffusion models for policy representation. In this work, we revisit the choice of energy-based models (EBM) as a policy class. We show that the prevailing folklore---that energy models in high dimensional continuous spaces are impractical to train---is false. We develop a practical training objective and algorithm for energy models which combines several key ingredients: (i) ranking noise contrastive estimation (R-NCE), (ii) learnable negative samplers, and (iii) non-adversarial joint training. We prove that our proposed objective function is asymptotically consistent and quantify its limiting variance. On the other hand, we show that the Implicit Behavior Cloning (IBC) objective is actually biased even at the population level, providing a mathematical explanation for the poor performance of IBC trained energy policies in several independent follow-up works. We further extend our algorithm to learn a continuous stochastic process that bridges noise and data, modeling this process with a family of EBMs indexed by scale variable. In doing so, we demonstrate that the core idea behind recent progress in generative modeling is actually compatible with EBMs. Altogether, our proposed training algorithms enable us to train energy-based models as policies which compete with---and even outperform---diffusion models and other state-of-the-art approaches in several challenging multi-modal benchmarks: obstacle avoidance path planning and contact-rich block pushing.

Applications · Computer Vision

Jaeyeon Kim, Heeseung Yun, Gunhee Kim

Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating first-order ambisonics, a widely used spatial audio format, directly from silent videos. To support this task, we introduce YT-Ambigen, a dataset comprising 102K 5-second YouTube video clips paired with corresponding first-order ambisonics. We also propose new evaluation metrics to assess the spatial aspect of generated audio based on audio energy maps and saliency metrics. Furthermore, we present Video-to-Spatial Audio Generation (ViSAGe), an end-to-end framework that generates first-order ambisonics from silent video frames by leveraging CLIP visual features, autoregressive neural audio codec modeling with both directional and visual guidance. Experimental results demonstrate that ViSAGe produces plausible and coherent first-order ambisonics, outperforming two-stage approaches consisting of video-to-audio generation and audio spatialization. Qualitative examples further illustrate that ViSAGe generates temporally aligned high-quality spatial audio that adapts to viewpoint changes.

Applications · Time Series

Nian Ran, Peng Xiao, Yue Wang, Wesley Shi, Jianxin Lin, Qi Meng, Richard Allmendinger

The application of large deep learning models in weather forecasting has led tosignificant advancements in the field, including higher-resolution forecasting andextended prediction periods exemplified by models such as Pangu and Fuxi. Despitethese successes, previous research has largely been characterized by the neglectof extreme weather events, and the availability of datasets specifically curated forsuch events remains limited. Given the critical importance of accurately forecastingextreme weather, this study introduces a comprehensive dataset that incorporateshigh-resolution extreme weather cases derived from the High-Resolution RapidRefresh (HRRR) data, a 3-km real-time dataset provided by NOAA. We alsoevaluate the current state-of-the-art deep learning models and Numerical WeatherPrediction (NWP) systems on HR-Extreme, and provide a improved baselinedeep learning model called HR-Heim which has superior performance on bothgeneral loss and HR-Extreme compared to others. Our results reveal that theerrors of extreme weather cases are significantly larger than overall forecast error,highlighting them as an crucial source of loss in weather prediction. These findingsunderscore the necessity for future research to focus on improving the accuracy ofextreme weather forecasts to enhance their practical utility

Probabilistic Methods · Bayesian Models and Methods

Hyungi Lee, Chaeyun Jang, Dong Bok Lee, Juho Lee

Meta-learning aims to train models that can generalize to new tasks with limited labeled data by extracting shared features across diverse task datasets. Additionally, it accounts for prediction uncertainty during both training and evaluation, a concept known as uncertainty-aware meta-learning. Neural Process (NP) is a well-known uncertainty-aware meta-learning method that constructs implicit stochastic processes using parametric neural networks, enabling rapid adaptation to new tasks. However, existing NP methods face challenges in accommodating diverse input dimensions and learned features, limiting their broad applicability across regression tasks. To address these limitations and advance the utility of NP models as general regressors, we introduce Dimension Agnostic Neural Process (DANP). DANP incorporates Dimension Aggregator Block (DAB) to transform input features into a fixed-dimensional space, enhancing the model's ability to handle diverse datasets. Furthermore, leveraging the Transformer architecture and latent encoding layers, DANP learns a wider range of features that are generalizable across various tasks. Through comprehensive experimentation on various synthetic and practical regression tasks, we empirically show that DANP outperforms previous NP variations, showcasing its effectiveness in overcoming the limitations of traditional NP models and its potential for broader applicability in diverse regression scenarios.

Miscellaneous Aspects of Machine Learning · Representation Learning

Mohammad Omama, Po-han Li, Sandeep Chinchali

Image retrieval is crucial in robotics and computer vision, with downstream applications in robot place recognition and vision-based product recommendations. Modern retrieval systems face two key challenges: scalability and efficiency.State-of-the-art image retrieval systems train specific neural networks for each dataset, an approach that lacks scalability. Furthermore, since retrieval speed is directly proportional to embedding size, existing systems that use large embeddings lack efficiency. To tackle scalability, recent works propose using off-the-shelf foundation models. However, these models, though applicable across datasets, fall short in achieving performance comparable to that of dataset-specific models. Our key observation is that, while foundation models capture necessary subtleties for effective retrieval, the underlying distribution of their embedding space can negatively impact cosine similarity searches. We introduce Autoencoders with Strong Variance Constraints (AE-SVC), which, when used for projection, significantly improves the performance of foundation models. We provide an in-depth theoretical analysis of AE-SVC. Addressing efficiency, we introduce Single-Shot Similarity Space Distillation ((SS)2D), a novel approach to learn embeddings with adaptive sizes that offers a better trade-off between size and performance. We conducted extensive experiments on four retrieval datasets, including Stan-ford Online Products (SoP) and Pittsburgh30k, using four different off-the-shelf foundation models, including DinoV2 and CLIP. AE-SVC demonstrates up to a 16% improvement in retrieval performance, while (SS)2D shows a further 10% improvement for smaller embedding sizes.

Deep Learning · Large Language Models

Yu Wang, Xinshuang Liu, Xiusi Chen, Sean OBrien, Junda Wu, Julian McAuley

Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with sur- rounding objects, remains a substantial challenge. Two critical factors in assimilating these experiences are (1) **Efficacy**: the ability to accurately remember recent events; (2) **Retention**: the capacity to recall long-past experiences. Current methods either embed experiences within model parameters using continual learning, model editing, or knowledge distillation techniques, which often struggle with rapid updates and complex interactions, or rely on external storage to achieve long-term retention, thereby increasing storage requirements. In this paper, we propose **SELF-PARAM** (Self-Updatable Large Language Models with Parameter Integration). SELF-PARAM requires no extra parameters while ensuring near-optimal efficacy and long-term retention. Our method employs a training objective that minimizes the Kullback-Leibler (KL) divergence between the predictions of an original model (with access to contextual information) and a target model (without such access). By generating diverse question-answer pairs related to the knowledge and minimizing the KL divergence across this dataset, we update the target model to internalize the knowledge seamlessly within its parameters. Evaluations on question-answering and conversational recommendation tasks demonstrate that SELF-PARAM significantly outperforms existing methods, even when accounting for non-zero storage requirements. This advancement paves the way for more efficient and scalable integration of experiences in large language models by embedding knowledge directly into model parameters.

Deep Learning · Generative Models and Autoencoders

Yoad Tewel, Rinon Gal, Dvir Samuel, Yuval Atzmon, Lior Wolf, Gal Chechik

Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.

Joseph Turian, Jordie Shier

Our field has a secret: nobody fully trusts audio evaluation measures. As neural audio generation nears perceptual fidelity, these measures fail to detect subtle differences that human listeners readily identify, often contradicting each other when comparing state-of-the-art models. The gap between human perception and automatic measures means we have increasingly sophisticated models while losing our ability to understand their flaws.

Deep Learning · Large Language Models

Guy Kaplan, Matanel Oren, Yuval Reif, Roy Schwartz

Natural language is composed of words, but modern large language models (LLMs) process sub-words as input. A natural question raised by this discrepancy is whether LLMs encode words internally, and if so how. We present evidence that LLMs engage in an intrinsic detokenization process, where subword sequences are combined into coherent whole-word representations at their last token. Our experiments show that this process primarily takes place within the early and middle layers of the model. We further demonstrate its robustness to arbitrary splits (e.g., “cats” to “ca” and “ts”), typos, and importantly—to out-of-vocabulary words: when feeding the last token internal representations of such words to the model as input, it can “understand” them as the complete word despite never seeing such representations as input during training. Our findings suggest that LLMs maintain a latent vocabulary beyond the tokenizer’s scope. These insights provide a practical, finetuning-free application for expanding the vocabulary of pre-trained models. By enabling the addition of new vocabulary words, we reduce input length and inference iterations, which reduces both space and model latency, with little to no loss in model accuracy.

Deep Learning · Large Language Models

Barak Lenz, Opher Lieber, Alan Arazi, Amir Bergman, Avshalom Manevich, Barak Peleg, Ben Aviram, Chen Almagor, Clara Fridman, Dan Padnos 等

We present Jamba, a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model families. MoE is added in some of these layers to increase model capacity while keeping active parameter usage manageable. This flexible architecture allows resource- and objective-specific configurations. We implement two configurations: Jamba-1.5-Large, with 94B active parameters, and Jamba-1.5-mini, with 12B active parameters. Built at large scale, Jamba models provide high throughput and small memory footprint compared to vanilla Transformers, especially at long-context tasks, with an effective context length of 256K tokens, the largest amongst open-weight models. At the same time, they are also competitive on standard language modeling and chatbot benchmarks. We study various architectural decisions, such as how to combine Transformer and Mamba layers, and how to mix experts, and show that some of them are crucial in large scale modeling. To support cost-effective inference, we introduce ExpertsInt8, a novel quantization technique that allows fitting Jamba-1.5-Large on a machine with 8 80GB GPUs when processing 256K-token contexts without loss of quality. We also describe several interesting properties of this architecture that the training and evaluation of Jamba have revealed. The model weights are publicly available.

Arnas Uselis, Seong Joon Oh

Deep classifiers are known to be sensitive to data distribution shifts, primarily due to their reliance on spurious correlations in training data. It has been suggested that these classifiers can still find useful features in the network's last layer that hold up under such shifts. In this work, we question the use of last-layer representations for out-of-distribution (OOD) generalisation and explore the utility of intermediate layers. To this end, we introduce \textit{Intermediate Layer Classifiers} (ILCs). We discover that intermediate layer representations frequently offer substantially better generalisation than those from the penultimate layer. In many cases, zero-shot OOD generalisation using earlier-layer representations approaches the few-shot performance of retraining on penultimate layer representations. This is confirmed across multiple datasets, architectures, and types of distribution shifts. Our analysis suggests that intermediate layers are less sensitive to distribution shifts compared to the penultimate layer. These findings highlight the importance of understanding how information is distributed across network layers and its role in OOD generalisation, while also pointing to the limits of penultimate layer representation utility. Code is available at https://github.com/oshapio/intermediate-layer-generalization.

Deep Learning · Attention Mechanisms

Viet-Hoang Tran, Thieu Vo, An Nguyen, Tho-Huu Tran, Minh-Khoi Nguyen-Nhat, Thanh Tran, Duy-Tung Pham, Tan Nguyen

This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and have proven valuable for tasks such as learnable optimizers, implicit data representations, and weight editing. While NFN have been extensively developed for MLP and CNN, no prior work has addressed their design for transformers, despite the importance of transformers in modern deep learning. This paper aims to address this gap by providing a systematic study of NFN for transformers. We first determine the maximal symmetric group of the weights in a multi-head attention module as well as a necessary and sufficient condition under which two sets of hyperparameters of the multi-head attention module define the same function. We then define the weight space of transformer architectures and its associated group action, which leads to the design principles for NFN in transformers. Based on these, we introduce Transformer-NFN, an NFN that is equivariant under this group action. Additionally, we release a dataset of more than 125,000 Transformers model checkpoints trained on two datasets with two different tasks, providing a benchmark for evaluating Transformer-NFN and encouraging further research on transformer training and performance.

Deep Learning · Generative Models and Autoencoders

Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka, Tomoya Yamashita

Diffusion models are powerful generative models but often generate sensitive data that are unwanted by users,mainly because the unlabeled training data frequently contain such sensitive data.Since labeling all sensitive data in the large-scale unlabeled training data is impractical,we address this problem by using a small amount of labeled sensitive data.In this paper,we propose positive-unlabeled diffusion models,which prevent the generation of sensitive data using unlabeled and sensitive data.Our approach can approximate the evidence lower bound (ELBO) for normal (negative) data using only unlabeled and sensitive (positive) data.Therefore, even without labeled normal data,we can maximize the ELBO for normal data and minimize it for labeled sensitive data,ensuring the generation of only normal data.Through experiments across various datasets and settings,we demonstrated that our approach can prevent the generation of sensitive images without compromising image quality.

Applications · Computer Vision

Huayu Chen, Hang Su, Peize Sun, Jun Zhu

Classifier-Free Guidance (CFG) is a critical technique for enhancing the sample quality of visual generative models. However, in autoregressive (AR) multi-modal generation, CFG introduces design inconsistencies between language and visual content, contradicting the design philosophy of unifying different modalities for visual AR. Motivated by language model alignment methods, we propose Condition Contrastive Alignment (CCA) to facilitate guidance-free AR visual generation. Unlike guidance methods that alter the sampling process to achieve the ideal sampling distribution, CCA directly fine-tunes pretrained models to fit the same distribution target. Experimental results show that CCA can significantly enhance the guidance-free performance of all tested models with just one epoch of fine-tuning (1% of pretraining epochs) on the pretraining dataset. This largely removes the need for guided sampling in AR visual generation and cuts the sampling cost by half. Moreover, by adjusting training parameters, CCA can achieve trade-offs between sample diversity and fidelity similar to CFG. This experimentally confirms the strong theoretical connection between language-targeted alignment and visual-targeted guidance methods, unifying two previously independent research fields.

Applications · Computer Vision

Abhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker

A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses \~50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. With this observation, we propose a strategy termed PROgressive Token Length SCALing for Efficient transformer encoders (PRO-SCALE) that can be plugged-in to the Mask2Former segmentation architecture to significantly reduce the computational cost. The underlying principle of PRO-SCALE is: progressively scale the length of the tokens with the layers of the encoder. This allows PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance (\~52% encoder and \~27% overall GFLOPs reduction with no drop in performance on COCO dataset). Experiments conducted on public benchmarks demonstrates PRO-SCALE's flexibility in architectural configurations, and exhibits potential for extension beyond the settings of segmentation tasks to encompass object detection. Code is available here: https://github.com/abhishekaich27/proscale-pytorch

Social Aspects · Trustworthy Machine Learning

XINYUE HU, Zhibin Duan, Bo Chen, Mingyuan Zhou

Although deep neural networks have demonstrated significant success due to theirpowerful expressiveness, most models struggle to meet practical requirements foruncertainty estimation. Concurrently, the entangled nature of deep neural net-works leads to a multifaceted problem, where various localized explanation tech-niques reveal that multiple unrelated features influence the decisions, thereby un-dermining interpretability. To address these challenges, we develop a BayesianNonnegative Decision Layer (BNDL), which reformulates deep neural networksas a conditional Bayesian non-negative factor analysis. By leveraging stochasticlatent variables, the BNDL can model complex dependencies and provide robustuncertainty estimation. Moreover, the sparsity and non-negativity of the latentvariables encourage the model to learn disentangled representations and decisionlayers, thereby improving interpretability. We also offer theoretical guaranteesthat BNDL can achieve effective disentangled learning. In addition, we developeda corresponding variational inference method utilizing a Weibull variational in-ference network to approximate the posterior distribution of the latent variables.Our experimental results demonstrate that with enhanced disentanglement capa-bilities, BNDL not only improves the model’s accuracy but also provides reliableuncertainty estimation and improved interpretability.

Applications · Health

Michael Wornow, Suhana Bedi, Miguel Angel Fuentes Hernandez, Ethan Steinberg, Jason Fries, Christopher Re, Sanmi Koyejo, Nigam Shah

Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, prior EHR FMs typically have context windows of $<$1k tokens, which prevents them from modeling full patient EHRs which can exceed 10k's of events. For making clinical predictions, both model performance and robustness to the unique properties of EHR data are crucial. Recent advancements in subquadratic long-context architectures (e.g. Mamba) offer a promising solution. However, their application to EHR data has not been well-studied. We address this gap by presenting the first systematic evaluation of the effect of context length on modeling EHR data. We find that longer context models improve predictive performance -- our Mamba-based model surpasses the prior state-of-the-art on 9/14 tasks on the EHRSHOT prediction benchmark. Additionally, we measure robustness to three unique, previously underexplored properties of EHR data: (1) the prevalence of ``copy-forwarded" diagnoses which create artificial token repetition in EHR sequences; (2) the irregular time intervals between EHR events which can lead to a wide range of timespans within a context window; and (3) the natural increase in disease complexity over time which makes later tokens in the EHR harder to predict than earlier ones. Stratifying our EHRSHOT results, we find that higher levels of each property correlate negatively with model performance (e.g., a 14% higher Brier loss between the least and most irregular patients), but that longer context models are more robust to more extreme levels of these properties. Our work highlights the potential for using long-context architectures to model EHR data, and offers a case study on how to identify and quantify new challenges in modeling sequential data motivated by domains outside of natural language. We release all of our model checkpoints and code.

Applications · Genetics, Cell Biology, Health, etc

Pei Liu, Luping Ji, Jiaxiang Gou, Bo Fu, Mao Ye

Histopathology Whole-Slide Images (WSIs) provide an important tool to assess cancer prognosis in computational pathology (CPATH). While existing survival analysis (SA) approaches have made exciting progress, they are generally limited to adopting highly-expressive network architectures and only coarse-grained patient-level labels to learn visual prognostic representations from gigapixel WSIs. Such learning paradigm suffers from critical performance bottlenecks, when facing present scarce training data and standard multi-instance learning (MIL) framework in CPATH. To overcome it, this paper, for the first time, proposes a new Vision-Language-based SA (**VLSA**) paradigm. Concretely, (1) VLSA is driven by pathology VL foundation models. It no longer relies on high-capability networks and shows the advantage of *data efficiency*. (2) In vision-end, VLSA encodes textual prognostic prior and then employs it as *auxiliary signals* to guide the aggregating of visual prognostic features at instance level, thereby compensating for the weak supervision in MIL. Moreover, given the characteristics of SA, we propose i) *ordinal survival prompt learning* to transform continuous survival labels into textual prompts; and ii) *ordinal incidence function* as prediction target to make SA compatible with VL-based prediction. Notably, VLSA's predictions can be interpreted intuitively by our Shapley values-based method. The extensive experiments on five datasets confirm the effectiveness of our scheme. Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs. Our source code is available at https://github.com/liupei101/VLSA.

Theory · Domain Adaptation and Transfer Learning

Jaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, Suha Kwak

Joint finetuning of a pretrained encoder and a randomly initialized decoder has been the de facto standard in semantic segmentation, but the vulnerability of this approach to domain shift has not been studied. We investigate the vulnerability issue of joint finetuning, and propose a novel finetuning framework called Decoupled FineTuning (DeFT) for domain generalization as a solution. DeFT operates in two stages. Its first stage warms up the decoder with the frozen, pretrained encoder so that the decoder learns task-relevant knowledge while the encoder preserves its generalizable features. In the second stage, it decouples finetuning of the encoder and decoder into two pathways, each of which concatenates an adaptive component (AC) and retentive component (RC); the encoder and decoder play different roles between AC and RC in different pathways. ACs are updated by gradients of the loss on the source domain, while RCs are updated by exponential moving average biased toward their initialization to retain their generalization capability. By the two separate optimization pathways with opposite AC-RC configurations, DeFT reduces the number of learnable parameters virtually, and decreases the distance between learned parameters and their initialization, leading to improved generalization capability. DeFT significantly outperformed existing methods in various domain shift scenarios, and its performance was further boosted by incorporating a simple distance regularization.

Deep Learning · Large Language Models

Irena Gao, Percy Liang, Carlos Guestrin

Users often interact with large language models through black-box inference APIs, both for closed- and open-weight models (e.g., Llama models are popularly accessed via Amazon Bedrock and Azure AI Studio). In order to cut costs or add functionality, API providers may quantize, watermark, or finetune the underlying model, changing the output distribution --- possibly without notifying users. We formalize detecting such distortions as Model Equality Testing, a two-sample testing problem, where the user collects samples from the API and a reference distribution and conducts a statistical test to see if the two distributions are the same. We find that tests based on the Maximum Mean Discrepancy between distributions are powerful for this task: a test built on a simple string kernel achieves a median of 77.4% power against a range of distortions, using an average of just 10 samples per prompt. We then apply this test to commercial inference APIs from Summer 2024 for four Llama models, finding that 11 out of 31 endpoints serve different distributions than reference weights released by Meta.