Search Results for author:
Found 104 papers, 53 papers with code
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
Studying how people interact with large language models (LLMs) in real-world scenarios is increasingly important due to their widespread use in various applications.
Efficient Memory Management for Large Language Model Serving with PagedAttention
On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage.
Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences.
Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation
We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing.
Decomposing Complex Queries for Tip-of-the-tongue Retrieval
When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content elements (e. g., book characters or events), information beyond the document text (e. g., descriptions of book covers), or personal context (e. g., when they read a book).
Gorilla: Large Language Model Connected with Massive APIs
Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis.
Simple Token-Level Confidence Improves Caption Correctness
The ability to judge whether a caption correctly describes an image is a critical part of vision-language understanding.
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144.
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device.
The Wisdom of Hindsight Makes Language Models Better Instruction Followers
In this paper, we consider an alternative approach: converting feedback to instruction by relabeling the original one and training the model for better alignment in a supervised manner.
Multitask Vision-Language Prompt Tuning
Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning.
TEMPERA: Test-Time Prompting via Reinforcement Learning
To achieve this, we design a novel action space that allows flexible editing of the initial prompts covering a wide set of commonly-used components like instructions, few-shot exemplars, and verbalizers.
On Optimizing the Communication of Model Parallelism
This pattern emerges when the two paradigms of model parallelism - intra-operator and inter-operator parallelism - are combined to support large models on large clusters.
Using Language to Extend to Unseen Domains
It is expensive to collect training data for every possible domain that a vision model may encounter when deployed.
Spectral Decomposition Representation for Reinforcement Learning
Representation learning often plays a critical role in reinforcement learning by managing the curse of dimensionality.
Autonomously Untangling Long Cables
Cables are ubiquitous in many settings and it is often useful to untangle them.
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
We demonstrate that it is possible to fine-tune both ResNet-18 and BERT within the memory constraints of a Cortex-M class embedded device while outperforming current edge training methods in energy efficiency.
Making Linear MDPs Practical via Contrastive Representation Learning
It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations.
Neurotoxin: Durable Backdoors in Federated Learning
In this type of attack, the goal of the attacker is to use poisoned updates to implant so-called backdoors into the learned model such that, at test time, the model's outputs can be fixed to a given target for certain inputs.
All You Need is LUV: Unsupervised Collection of Labeled Images using Invisible UV Fluorescent Indicators
Large-scale semantic image annotation is a significant challenge for learning-based perception systems in robotics.
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data
Our analyses consider (I) hundreds of Transformers trained in different settings, in which we systematically vary the amount of data, the model size and the optimization hyperparameters, (II) a total of 51 pretrained Transformers from eight families of Huggingface NLP models, including GPT2, BERT, etc., and (III) a total of 28 existing and novel generalization metrics.
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.
Representing Long-Range Context for Graph Neural Networks with Global Attention
Inspired by recent computer vision results that find position-invariant attention performant in learning long-range relationships, our method, which we call GraphTrans, applies a permutation-invariant Transformer module after a standard GNN module.
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation
Traditional computer vision models are trained to predict a fixed set of predefined categories.
The Effect of Model Size on Worst-Group Generalization
Overparameterization is shown to result in poor test accuracy on rare subgroups under a variety of settings where subgroup information is known.
Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward environments.
NovelD: A Simple yet Effective Exploration Criterion
We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary.
Grounded Graph Decoding Improves Compositional Generalization in Question Answering
Grounding enables the model to retain syntax information from the input in thereby significantly improving generalization over complex inputs.
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Goal-conditioned reinforcement learning (RL) can solve tasks in a wide range of domains, including navigation and manipulation, but learning to reach distant goals remains a central challenge to the field.
Taxonomizing local versus global structure in neural network loss landscapes
Viewing neural network models in terms of their loss landscapes has a long history in the statistical mechanics approach to learning, and in recent years it has received attention within machine learning proper.
Accelerating Quadratic Optimization with Reinforcement Learning
First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved.
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks
We then present a new algorithm, Latent Space Safe Sets (LS3), which uses this representation for long-horizon tasks with sparse rewards.
Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
We present two algorithms that enhance robust cable untangling, LOKI and SPiDERMan, which operate alongside HULK, a high-level planner from prior work.
Learning Space Partitions for Path Planning
Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function.
CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
Our results demonstrate that multiple purpose-built neural networks can function in sequence to accomplish the complex series of tasks required for automated analysis of real-world angiograms.
PAC Best Arm Identification Under a Deadline
In this work, the decision-maker is given a deadline of $T$ rounds, where, on each round, it can adaptively choose which arms to pull and how many times to pull them; this distinguishes the number of decisions made (i. e., time or number of rounds) from the number of samples acquired (cost).
Disentangling Dense Multi-Cable Knots
Disentangling two or more cables requires many steps to remove crossings between and within cables.
Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
In particular, we show that the "dot-product attention" that is the core of the Transformer's operation can be characterized as a kernel learning method on a pair of Banach spaces.
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
On all these tasks, ActNN compresses the activation to 2 bits on average, with negligible accuracy loss.
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Humans have a remarkable ability to make decisions by accurately reasoning about future events, including the future behaviors and states of mind of other agents.
Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
Our model transfers knowledge from pretrained image and sentence encoders and achieves strong performance with only 3M image text pairs, 133x smaller than CLIP.
Robust Object Detection via Instance-Level Temporal Cycle Confusion
Building reliable object detectors that are robust to domain shifts, such as various changes in context, viewpoint, and object appearances, is critical for real-world applications.
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
A recent trend in computer vision is to replace convolutions with transformers.
NBDT: Neural-Backed Decision Tree
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use.
BeBold: Exploration Beyond the Boundary of Explored Regions
In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR.
RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem
Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years.
Untangling Dense Knots by Learning Task-Relevant Keypoints
HULK successfully untangles a cable from a dense initial configuration containing up to two overhand and figure-eight knots in 97. 9% of 378 simulation experiments with an average of 12. 1 actions per trial.
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Second, we present an algorithm for a fixed deadline setting, where we are given a time deadline and need to maximize the probability of finding the best arm.
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration.
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
We show that the FQT gradient is an unbiased estimator of the QAT gradient, and we discuss the impact of gradient quantization on its variance.
Multi-Agent Collaboration via Reward Attribution Decomposition
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects
We explore learning pixelwise correspondences between images of deformable objects in different configurations.
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting.
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
Replacing BN with the recently-proposed Group Normalization (GN) can reduce gradient diversity and improve test accuracy.
Contrastive Code Representation Learning
Recent work learns contextual representations of source code by reconstructing tokens from their context.
Ranked #1 on
Method name prediction
on CodeSearchNet
Boundary thickness and robustness in learning models
Using these observations, we show that noise-augmentation on mixup training further increases boundary thickness, thereby combating vulnerability to various forms of adversarial attacks and OOD transforms.
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud
Bird's-eye-view (BEV) is a powerful and widely adopted representation for road scenes that captures surrounding objects and their spatial locations, along with overall context in the scene.
Bird's-Eye View Semantic Segmentation
Semantic Segmentation
+1
Ansor : Generating High-Performance Tensor Programs for Deep Learning
Ansor can find high-performance programs that are outside the search space of existing state-of-the-art approaches.
SegNBDT: Visual Decision Rules for Segmentation
To address this, prior work combines neural networks with decision trees.
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously.
Ranked #5 on
Neural Architecture Search
on ImageNet
Thompson Sampling for Linearly Constrained Bandits
We address multi-armed bandits (MAB) where the objective is to maximize the cumulative reward under a probabilistic linear constraint.
VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback
To that end, we first define three notions of regret for the welfare, the individual utilities of each agent and that of the mechanism.
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands.
Ranked #68 on
Neural Architecture Search
on ImageNet
NBDT: Neural-Backed Decision Trees
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use.
Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics
Robotic fabric manipulation is challenging due to the infinite dimensional configuration space, self-occlusion, and complex dynamics of fabrics.
Frustratingly Simple Few-Shot Object Detection
Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.
Ranked #15 on
Few-Shot Object Detection
on MS-COCO (30-shot)
ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions
Sample-based learning model predictive control (LMPC) strategies have recently attracted attention due to their desirable theoretical properties and their good empirical performance on robotic tasks.
Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data
We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation.
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference.
SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis
Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech.
Sound Audio and Speech Processing
ANODEV2: A Coupled Neural ODE Framework
It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE).
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing strategies.
Helen: Maliciously Secure Coopetitive Learning for Linear Models
Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e. g., better medical research, or fraud detection).
On-Policy Robot Imitation Learning from a Converging Supervisor
Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor.
Task-Aware Feature Generation for Zero-Shot Compositional Learning
In this work, we propose a task-aware feature generation (TFG) framework for compositional learning, which generates features of novel visual concepts by transferring knowledge from previously seen concepts.
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging.
Model-based Reinforcement Learning
reinforcement-learning
+1
ACE: Adapting to Changing Environments for Semantic Segmentation
However, neural classifiers are often extremely brittle when confronted with domain shift---changes in the input distribution that occur over time.
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
We show that TAFE-Net is highly effective in generalizing to new tasks or concepts and evaluate the TAFE-Net on a range of benchmarks in zero-shot and few-shot learning.
MLSys: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Constrained Thompson Sampling for Wireless Link Optimization
We model rate selection as a stochastic multi-armed bandit (MAB) problem, where a finite set of transmission rates are modeled as independent bandit arms.
Cloud Programming Simplified: A Berkeley View on Serverless Computing
Serverless cloud computing handles virtually all the system administration operations needed to make it easier for programmers to use the cloud.
Operating Systems
The OoO VLIW JIT Compiler for GPU Inference
Current trends in Machine Learning~(ML) inference on hardware accelerated devices (e. g., GPUs, TPUs) point to alarmingly low utilization.
Serverless Computing: One Step Forward, Two Steps Back
Serverless computing offers the potential to program the cloud in an autoscaling, pay-as-you go manner.
Distributed, Parallel, and Cluster Computing Databases
InferLine: ML Inference Pipeline Composition Framework
The dominant cost in production machine learning workloads is not training individual models but serving predictions from increasingly complex prediction pipelines spanning multiple models, machine learning frameworks, and parallel hardware accelerators.
Distributed, Parallel, and Cluster Computing
Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification
We develop a multi-task convolutional neural network (CNN) to classify multiple diagnoses from 12-lead electrocardiograms (ECGs) using a dataset comprised of over 40, 000 ECGs, with labels derived from cardiologist clinical interpretations.
Inter-BMV: Interpolation with Block Motion Vectors for Fast Semantic Segmentation on Video
Models optimized for accuracy on single images are often prohibitively slow to run on each frame in a video.
Scaling Video Analytics Systems to Large Camera Deployments
Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical premises.
Tune: A Research Platform for Distributed Model Selection and Training
We show that this interface meets the requirements for a broad range of hyperparameter search algorithms, allows straightforward scaling of search to large clusters, and simplifies algorithm implementation.
Deep Mixture of Experts via Shallow Embedding
Larger networks generally have greater representational power at the cost of increased computational complexity.
Fast Semantic Segmentation on Video Using Block Motion-Based Feature Interpolation
Convolutional networks optimized for accuracy on challenging, dense prediction tasks are prohibitively slow to run on each frame in a video.
Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
By enabling wider use of learned dynamics models within a model-free reinforcement learning algorithm, we improve value estimation, which, in turn, reduces the sample complexity of learning.
Neural Networks for irregularly observed continuous-time Stochastic Processes
Designing neural networks for continuous-time stochastic processes is challenging, especially when observations are made irregularly.
RLlib: Abstractions for Distributed Reinforcement Learning
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation.
A Berkeley View of Systems Challenges for AI
With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising and intelligent infrastructures, AI (Artificial Intelligence) has moved from research labs to production.
SkipNet: Learning Dynamic Routing in Convolutional Networks
While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient.
Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
We explore how Deep Neural Networks can represent meta-policies that switch among a set of previously learned policies, specifically in settings where the dynamics of a new scenario are composed of a mixture of previously learned dynamics and where the state observation is possibly corrupted by sensing noise.
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions.
Clipper: A Low-Latency Online Prediction Serving System
In this paper, we introduce Clipper, a general-purpose low-latency prediction serving system.
Scalable Linear Causal Inference for Irregularly Sampled Time Series with Long Range Dependencies
Linear causal analysis is central to a wide range of important application spanning finance, the physical sciences, and engineering.
Parallel Double Greedy Submodular Maximization
Many machine learning problems can be reduced to the maximization of submodular functions.
The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox
In this work, we present Velox, a new component of the Berkeley Data Analytics Stack.
Databases
GraphLab: A New Framework For Parallel Machine Learning
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging.
Optimistic Concurrency Control for Distributed Unsupervised Learning
Research on distributed machine learning algorithms has focused primarily on one of two extremes - algorithms that obey strict concurrency constraints or algorithms that obey few or no such constraints.
