Arrow Research search

Author name cluster

Dina Katabi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

21 papers
2 author rows

Possible papers

21

NeurIPS Conference 2025 Conference Paper

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning

  • Kaiwen Zha
  • Zhengqi Gao
  • Maohao Shen
  • Zhang-Wei Hong
  • Duane Boning
  • Dina Katabi

Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward model). However, current RL post-training methods for LLMs typically use verifiers that are fixed (rule-based or frozen pretrained) or trained discriminatively via supervised fine-tuning (SFT). Such designs are susceptible to reward hacking and generalize poorly beyond their training distributions. To overcome these limitations, we propose Tango, a novel framework that uses RL to concurrently train both an LLM generator and a verifier in an interleaved manner. A central innovation of Tango is its generative, process-level LLM verifier, which is trained via RL and co-evolves with the generator. Importantly, the verifier is trained solely based on outcome-level verification correctness rewards without requiring explicit process-level annotations. This generative RL-trained verifier exhibits improved robustness and superior generalization compared to deterministic or SFT-trained verifiers, fostering effective mutual reinforcement with the generator. Extensive experiments demonstrate that both components of Tango achieve state-of-the-art results among 7B/8B-scale models: the generator attains best-in-class performance across five competition-level math benchmarks and four challenging out-of-domain reasoning tasks, while the verifier leads on the ProcessBench dataset. Remarkably, both components exhibit particularly substantial improvements on the most difficult mathematical reasoning problems.

PDF Details

NeurIPS Conference 2025 Conference Paper

Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity

  • Seonghoon Yu
  • Dongjun Nam
  • Dina Katabi
  • Jeany Son

Knowledge Distillation (KD) aims to train a lightweight student model by transferring knowledge from a large, high-capacity teacher. Recent studies have shown that leveraging diverse teacher perspectives can significantly improve distillation performance; however, achieving such diversity typically requires multiple teacher networks, leading to high computational costs. In this work, we propose a novel cost-efficient knowledge augmentation method for KD that generates diverse multi-views by attaching multiple branches to a single teacher. To ensure meaningful semantic variation across multi-views, we introduce two angular diversity objectives: 1) $\textit{constrained inter-angle diversify loss}$, which maximizes angles between augmented views while preserving proximity to the original teacher output, and 2) $\textit{intra-angle diversify loss}$, which encourages an even distribution of views around the original output. The ensembled knowledge from these angularly diverse views, along with the original teacher, is distilled into the student. We further theoretically demonstrate that our objectives increase the diversity among ensemble members and thereby reduce the upper bound of the ensemble's expected loss, leading to more effective distillation. Experimental results show that our method surpasses an existing knowledge augmentation method across diverse configurations. Moreover, the proposed method is compatible with other KD frameworks in a plug-and-play fashion, providing consistent improvements in generalization performance.

PDF Details

ICLR Conference 2024 Conference Paper

Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency

  • Tianhong Li
  • Sangnie Bhardwaj
  • Yonglong Tian
  • Han Zhang 0010
  • Jarred Barber
  • Dina Katabi
  • Guillaume Lajoie
  • Huiwen Chang

Current vision-language generative models rely on expansive corpora of $\textit{paired}$ image-text data to attain optimal performance and generalization capabilities. However, automatically collecting such data (e.g. via large-scale web scraping) leads to low quality and poor image-text correlation, while human annotation is more accurate but requires significant manual effort and expense. We introduce $\textbf{ITIT}$ ($\textbf{I}$n$\textbf{T}$egrating $\textbf{I}$mage $\textbf{T}$ext): an innovative training paradigm grounded in the concept of cycle consistency which allows vision-language training on $\textit{unpaired}$ image and text data. ITIT is comprised of a joint image-text encoder with disjoint image and text decoders that enable bidirectional image-to-text and text-to-image generation in a single framework. During training, ITIT leverages a small set of paired image-text data to ensure its output matches the input reasonably well in both directions. Simultaneously, the model is also trained on much larger datasets containing only images or texts. This is achieved by enforcing cycle consistency between the original unpaired samples and the cycle-generated counterparts. For instance, it generates a caption for a given input image and then uses the caption to create an output image, and enforces similarity between the input and output images. Our experiments show that ITIT with unpaired datasets exhibits similar scaling behavior as using high-quality paired data. We demonstrate image generation and captioning performance on par with state-of-the-art text-to-image and image-to-text models with orders of magnitude fewer (only 3M) paired image-text data. Code will be released at https://github.com/LTH14/itit.

Details

NeurIPS Conference 2024 Conference Paper

Return of Unconditional Generation: A Self-supervised Representation Generation Method

  • Tianhong Li
  • Dina Katabi
  • Kaiming He

Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale unlabeled data. In the literature, the generation quality of an unconditional method has been much worse than that of its conditional counterpart. This gap can be attributed to the lack of semantic information provided by labels. In this work, we show that one can close this gap by generating semantic representations in the representation space produced by a self-supervised encoder. These representations can be used to condition the image generator. This framework, called Representation-Conditioned Generation (RCG), provides an effective solution to the unconditional generation problem without using labels. Through comprehensive experiments, we observe that RCG significantly improves unconditional generation quality: e. g. , it achieves a new state-of-the-art FID of 2. 15 on ImageNet 256x256, largely reducing the previous best of 5. 91 by a relative 64%. Our unconditional results are situated in the same tier as the leading class-conditional ones. We hope these encouraging observations will attract the community's attention to the fundamental problem of unconditional generation. Code is available at https: //github. com/LTH14/rcg.

PDF Details DOI

ICML Conference 2023 Conference Paper

Change is Hard: A Closer Look at Subpopulation Shift

  • Yuzhe Yang 0003
  • Haoran Zhang 0003
  • Dina Katabi
  • Marzyeh Ghassemi

Machine learning models often perform poorly on subgroups that are underrepresented in the training data. Yet, little is understood on the variation in mechanisms that cause subpopulation shifts, and how algorithms generalize across such diverse shifts at scale. In this work, we provide a fine-grained analysis of subpopulation shift. We first propose a unified framework that dissects and explains common shifts in subgroups. We then establish a comprehensive benchmark of 20 state-of-the-art algorithms evaluated on 12 real-world datasets in vision, language, and healthcare domains. With results obtained from training over 10, 000 models, we reveal intriguing observations for future progress in this space. First, existing algorithms only improve subgroup robustness over certain types of shifts but not others. Moreover, while current algorithms rely on group-annotated validation data for model selection, we find that a simple selection criterion based on worst-class accuracy is surprisingly effective even without any group information. Finally, unlike existing works that solely aim to improve worst-group accuracy (WGA), we demonstrate the fundamental tradeoff between WGA and other important metrics, highlighting the need to carefully choose testing metrics. Code and data are available at: https: //github. com/YyzHarry/SubpopBench.

Details

NeurIPS Conference 2023 Conference Paper

Improving CLIP Training with Language Rewrites

  • Lijie Fan
  • Dilip Krishnan
  • Phillip Isola
  • Dina Katabi
  • Yonglong Tian

Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which typically relies on data augmentations to prevent overfitting and shortcuts. However, in the CLIP training paradigm, data augmentations are exclusively applied to image inputs, while language inputs remain unchanged throughout the entire training process, limiting the exposure of diverse texts to the same image. In this paper, we introduce Language augmented CLIP (LaCLIP), a simple yet highly effective approach to enhance CLIP training through language rewrites. Leveraging the in-context learning capability of large language models, we rewrite the text descriptions associated with each image. These rewritten texts exhibit diversity in sentence structure and vocabulary while preserving the original key concepts and meanings. During training, LaCLIP randomly selects either the original texts or the rewritten versions as text augmentations for each image. Extensive experiments on CC3M, CC12M, RedCaps and LAION-400M datasets show that CLIP pre-training with language rewrites significantly improves the transfer performance without computation or memory overhead during training. Specifically for ImageNet zero-shot accuracy, LaCLIP outperforms CLIP by 8. 2% on CC12M and 2. 4% on LAION-400M.

PDF Details

ICLR Conference 2023 Conference Paper

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

  • Hao He 0011
  • Kaiwen Zha
  • Dina Katabi

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithms with a momentum encoder are more robust to indiscriminate poisoning, and propose a new countermeasure based on matrix completion. Code is available at: https://github.com/kaiwenzha/contrastive-poisoning.

Details

NeurIPS Conference 2023 Conference Paper

Rank-N-Contrast: Learning Continuous Representations for Regression

  • Kaiwen Zha
  • Peng Cao
  • Jeany Son
  • Yuzhe Yang
  • Dina Katabi

Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of sample orders, inducing suboptimal results across a wide range of regression tasks. To fill the gap, we propose Rank-N-Contrast (RNC), a framework that learns continuous representations for regression by contrasting samples against each other based on their rankings in the target space. We demonstrate, theoretically and empirically, that RNC guarantees the desired order of learned representations in accordance with the target orders, enjoying not only better performance but also significantly improved robustness, efficiency, and generalization. Extensive experiments using five real-world regression datasets that span computer vision, human-computer interaction, and healthcare verify that RNC achieves state-of-the-art performance, highlighting its intriguing properties including better data efficiency, robustness to spurious targets and data corruptions, and generalization to distribution shifts.

PDF Details

ICLR Conference 2023 Conference Paper

SimPer: Simple Self-Supervised Learning of Periodic Targets

  • Yuzhe Yang 0003
  • Xin Liu 0034
  • Jiang Wu
  • Silviu Borac
  • Dina Katabi
  • Ming-Zher Poh
  • Daniel McDuff

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks with limited or no supervision is of great benefit. Yet, existing self-supervised learning (SSL) methods overlook the intrinsic periodicity in data, and fail to learn representations that capture periodic or frequency attributes. In this paper, we present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized augmentations, feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations. Extensive experiments on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains verify the superior performance of SimPer compared to state-of-the-art SSL methods, highlighting its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts.

Details

ICML Conference 2021 Conference Paper

Delving into Deep Imbalanced Regression

  • Yuzhe Yang 0003
  • Kaiwen Zha
  • Ying-Cong Chen
  • Hao Wang 0014
  • Dina Katabi

Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i. e. , different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features, which explicitly acknowledges the effects of nearby targets, and calibrates both label and learned feature distributions. We curate and benchmark large-scale DIR datasets from common real-world tasks in computer vision, natural language processing, and healthcare domains. Extensive experiments verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems. Code and data are available at: https: //github. com/YyzHarry/imbalanced-regression.

Details

ICML Conference 2020 Conference Paper

Continuously Indexed Domain Adaptation

  • Hao Wang 0014
  • Hao He 0011
  • Dina Katabi

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e. g. , between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one often needs to transfer disease analysis and prediction across patients of different ages, where age acts as a continuous domain index. Such tasks are challenging for prior domain adaptation methods since they ignore the underlying relation among domains. In this paper, we propose the first method for continuously indexed domain adaptation. Our approach combines traditional adversarial adaptation with a novel discriminator that models the encoding-conditioned domain index distribution. Our theoretical analysis demonstrates the value of leveraging the domain index to generate invariant features across a continuous range of domains. Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

Details

ICLR Conference 2020 Conference Paper

Harnessing Structures for Value-Based Planning and Reinforcement Learning

  • Yuzhe Yang 0003
  • Guo Zhang 0006
  • Zhi Xu 0001
  • Dina Katabi

Value-based methods constitute a fundamental methodology in planning and deep reinforcement learning (RL). In this paper, we propose to exploit the underlying structures of the state-action value function, i.e., Q function, for both planning and deep RL. In particular, if the underlying system dynamics lead to some global structures of the Q function, one should be capable of inferring the function better by leveraging such structures. Specifically, we investigate the low-rank structure, which widely exists for big data matrices. We verify empirically the existence of low-rank Q functions in the context of control and deep RL tasks. As our key contribution, by leveraging Matrix Estimation (ME) techniques, we propose a general framework to exploit the underlying low-rank structure in Q functions. This leads to a more efficient planning procedure for classical control, and additionally, a simple scheme that can be applied to value-based RL techniques to consistently achieve better performance on "low-rank" tasks. Extensive experiments on control tasks and Atari games confirm the efficacy of our approach.

Details

ICLR Conference 2020 Conference Paper

Learning Compositional Koopman Operators for Model-Based Control

  • Yunzhu Li
  • Hao He 0011
  • Jiajun Wu 0001
  • Dina Katabi
  • Antonio Torralba 0001

Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis. The Koopman operator theory lays the foundation for identifying the nonlinear-to-linear coordinate transformations with data-driven methods. Recently, researchers have proposed to use deep neural networks as a more expressive class of basis functions for calculating the Koopman operators. These approaches, however, assume a fixed dimensional state space; they are therefore not applicable to scenarios with a variable number of objects. In this paper, we propose to learn compositional Koopman operators, using graph neural networks to encode the state into object-centric embeddings and using a block-wise linear transition matrix to regularize the shared structure across objects. The learned dynamics can quickly adapt to new environments of unknown physical parameters and produce control signals to achieve a specified goal. Our experiments on manipulating ropes and controlling soft robots show that the proposed method has better efficiency and generalization ability than existing baselines.

Details

ICLR Conference 2020 Conference Paper

Self-Supervised Learning of Appliance Usage

  • Chen-Yu Hsu 0001
  • Abbas Zeitoun
  • Guang-He Lee
  • Dina Katabi
  • Tommi S. Jaakkola

Learning home appliance usage is important for understanding people's activities and optimizing energy consumption. The problem is modeled as an event detection task, where the objective is to learn when a user turns an appliance on, and which appliance it is (microwave, hair dryer, etc.). Ideally, we would like to solve the problem in an unsupervised way so that the method can be applied to new homes and new appliances without any labels. To this end, we introduce a new deep learning model that takes input from two home sensors: 1) a smart electricity meter that outputs the total energy consumed by the home as a function of time, and 2) a motion sensor that outputs the locations of the residents over time. The model learns the distribution of the residents' locations conditioned on the home energy signal. We show that this cross-modal prediction task allows us to detect when a particular appliance is used, and the location of the appliance in the home, all in a self-supervised manner, without any labeled data.

Details

AAAI Conference 2019 Conference Paper

Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling

  • Hao Wang
  • Chengzhi Mao
  • Hao He
  • Mingmin Zhao
  • Tommi S. Jaakkola
  • Dina Katabi

We consider the problem of inferring the values of an arbitrary set of variables (e. g. , risk of diseases) given other observed variables (e. g. , symptoms and diagnosed diseases) and high-dimensional signals (e. g. , MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.

PDF Details

ICML Conference 2019 Conference Paper

Circuit-GNN: Graph Neural Networks for Distributed Circuit Design

  • Guo Zhang 0006
  • Hao He 0011
  • Dina Katabi

We present Circuit-GNN, a graph neural network (GNN) model for designing distributed circuits. Today, designing distributed circuits is a slow process that can take months from an expert engineer. Our model both automates and speeds up the process. The model learns to simulate the electromagnetic (EM) properties of distributed circuits. Hence, it can be used to replace traditional EM simulators, which typically take tens of minutes for each design iteration. Further, by leveraging neural networks’ differentiability, we can use our model to solve the inverse problem – i. e. , given desirable EM specifications, we propagate the gradient to optimize the circuit parameters and topology to satisfy the specifications. We exploit the flexibility of GNN to create one model that works for different circuit topologies. We compare our model with a commercial simulator showing that it reduces simulation time by four orders of magnitude. We also demonstrate the value of our model by using it to design a Terahertz channelizer, a difficult task that requires a specialized expert. The results show that our model produces a channelizer whose performance is as good as a manually optimized design, and can save the expert several weeks of topology and parameter optimization. Most interestingly, our model comes up with new designs that differ from the limited templates commonly used by engineers in the field, hence significantly expanding the design space.

Details

ICML Conference 2019 Conference Paper

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

  • Yuzhe Yang 0003
  • Guo Zhang 0006
  • Zhi Xu 0001
  • Dina Katabi

Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, images are preprocessed using two steps: first pixels are randomly dropped from the image; then, the image is reconstructed using ME. We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image. Since humans typically rely on such global structures in classifying images, the process makes the network mode compatible with human perception. We conduct comprehensive experiments on prevailing benchmarks such as MNIST, CIFAR-10, SVHN, and Tiny-ImageNet. Comparing ME-Net with state-of-the-art defense mechanisms shows that ME-Net consistently outperforms prior techniques, improving robustness against both black-box and white-box attacks.

Details

ICML Conference 2017 Conference Paper

Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture

  • Mingmin Zhao
  • Shichao Yue
  • Dina Katabi
  • Tommi S. Jaakkola
  • Matt T. Bianchi

We focus on predicting sleep stages from radio measurements without any attached sensors on subjects. We introduce a new predictive model that combines convolutional and recurrent neural networks to extract sleep-specific subject-invariant features from RF signals and capture the temporal progression of sleep. A key innovation underlying our approach is a modified adversarial training regime that discards extraneous information specific to individuals or measurement conditions, while retaining all information relevant to the predictive task. We analyze our game theoretic setup and empirically demonstrate that our model achieves significant improvements over state-of-the-art solutions.

Details

SODA Conference 2013 Conference Paper

Shift Finding in Sub-Linear Time

  • Alexandr Andoni
  • Piotr Indyk
  • Dina Katabi
  • Haitham Hassanieh

We study the following basic pattern matching problem. Consider a “code” sequence c consisting of n bits chosen uniformly at random, and a “signal” sequence x obtained by shifting c (modulo n ) and adding noise. The goal is to efficiently recover the shift with high probability. The problem models tasks of interest in several applications, including GPS synchronization and motion estimation. We present an algorithm that solves the problem in time Õ ( n ( f /(1+ f ) ), where Õ ( N f ) is the running time of the best algorithm for finding the closest pair among N “random” sequences of length O (log N ). A trivial bound of f = 2 leads to a simple algorithm with a running time of Õ ( n 2/3 ). The asymptotic running time can be further improved by plugging in recent more efficient algorithms for the closest pair problem. Our results also yield a sub-linear time algorithm for approximate pattern matching algorithm for a random signal (text), even for the case when the error between the signal and the code (pattern) is asymptotically as large as the code size. This is the first sublinear time algorithm for such error rates.

Details
v2026.09.13