Search Results for author:
Found 53 papers, 23 papers with code
Hierarchical Image Matching for UAV Absolute Visual Localization via Semantic and Structural Constraints
Absolute localization, aiming to determine an agent's location with respect to a global reference, is crucial for unmanned aerial vehicles (UAVs) in various applications, but it becomes challenging when global navigation satellite system (GNSS) signals are unavailable.
Super-fast rates of convergence for Neural Networks Classifiers under the Hard Margin Condition
We study the classical binary classification problem for hypothesis spaces of Deep Neural Networks (DNNs) with ReLU activation under Tsybakov's low-noise condition with exponent $q>0$, and its limit-case $q\to\infty$ which we refer to as the "hard-margin condition".
Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation.
TSDW: A Tri-Stream Dynamic Weight Network for Cloth-Changing Person Re-Identification
This dynamic weighting network consists of three parallel feature streams: facial features, head-limb features, and global features.
Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences.
A Risk Sensitive Contract-unified Reinforcement Learning Approach for Option Hedging
We propose a new risk sensitive reinforcement learning approach for the dynamic hedging of options.
StringNET: Neural Network based Variational Method for Transition Pathways
Rare transition events in meta-stable systems under noisy fluctuations are crucial for many non-equilibrium physical and chemical processes.
Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
With this goal in mind, this paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research.
Weak Generative Sampler to Efficiently Sample Invariant Distribution of Stochastic Differential Equation
Sampling invariant distributions from an It\^o diffusion process presents a significant challenge in stochastic simulation.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #1 on
Zero-Shot Video Question Answer
on Zero-shot Video Question Answering on LongVideoBench
(using extra training data)
From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction
In this paper, we introduce a novel From Graph to Word Bag (FWGB) approach, which introduces domain knowledge regarding constituent elements to guide the model in making judgments on confusing charges, much like a judge's reasoning process.
Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings
Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
Data Factors for Better Compositional Generalization
However, in contrast to this poor performance, state-of-the-art models trained on larger and more general datasets show better generalization ability.
MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images
We improve from NeRF and propose a novel framework that, by leveraging the parametric 3DMM models, can reconstruct a high-fidelity drivable face avatar and successfully handle the unseen expressions.
Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields.
Ranked #82 on
3D Human Pose Estimation
on 3DPW
RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
In addition, we propose RexUIE, which is a Recursive Method with Explicit Schema Instructor for UIE.
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them.
Scene Style Text Editing
Specifically, QuadNet consists of four parts, namely background inpainting, style encoder, content encoder, and fusion generator.
TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
For similar sized systems, it is ~4. 3x-4. 5x faster than the Graphcore IPU Bow and is 1. 2x-1. 7x faster and uses 1. 3x-1. 9x less power than the Nvidia A100.
Learning to Scale Temperature in Masked Self-Attention for Image Inpainting
Recent advances in deep generative adversarial networks (GAN) and self-attention mechanism have led to significant improvements in the challenging task of inpainting large missing regions in an image.
Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models.
Residual-Quantile Adjustment for Adaptive Training of Physics-informed Neural Network
Thus, we propose the Residual-Quantile Adjustment (RQA) method for a better weight choice for each training sample.
Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
MPoSM can model arbitrary tag dependency and perform POS induction through the objective of masked POS reconstruction.
Improving the Adversarial Robustness of NLP Models by Information Bottleneck
Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manipulated by adversaries to fool NLP models.
GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Providing natural language instructions in prompts is a useful new paradigm for improving task performance of large language models in a zero-shot setting.
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Combinatorial optimization is a well-established area in operations research and computer science.
Capture Agent Free Biosensing using Porous Silicon Arrays and Machine Learning
Biosensors are an essential tool for medical diagnostics, environmental monitoring and food safety.
Learn Quasi-stationary Distributions of Finite State Markov Chain
We propose a reinforcement learning (RL) approach to compute the expression of quasi-stationary distribution.
Active Learning for Saddle Point Calculation
To reduce the number of expensive computations of the true gradients, we propose an active learning framework consisting of a statistical surrogate model, Gaussian process regression (GPR) for the energy function, and a single-walker dynamics method, gentle accent dynamics (GAD), for the saddle-type transition states.
Sublinear Regret for Learning POMDPs
We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs).
Hidden Biases in Unreliable News Detection Datasets
Using the observations and experimental results, we provide practical suggestions on how to create more reliable datasets for the unreliable news detection task.
Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning
We introduce distributed NLI, a new NLU task with a goal to predict the distribution of human judgements for natural language inference.
What Can We Learn from Collective Human Opinions on Natural Language Inference Data?
Analysis reveals that: (1) high human disagreement exists in a noticeable amount of examples in these datasets; (2) the state-of-the-art models lack the ability to recover the distribution over human labels; (3) models achieve near-perfect accuracy on the subset of data with a high level of human agreement, whereas they can barely beat a random guess on the data with low levels of human agreement, which compose most of the common errors made by state-of-the-art models on the evaluation sets.
Deep Reinforcement Learning for On-line Dialogue State Tracking
To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems.
Composing Answer from Multi-spans for Reading Comprehension
This paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the given passages.
Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue
A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles.
Machine Learning and Control Theory
Conversely Machine Learning can be used to solve large control problems.
Towards Robustifying NLI Models Against Lexical Dataset Biases
While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of the language semantics.
The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions
For the first question, we conduct a thorough empirical study over analysis sets and find that in addition to the unstable final performance, the instability exists all along the training curve.
Stochastic Modified Equations for Continuous Limit of Stochastic ADMM
In this work, we put different variants of stochastic ADMM into a unified form, which includes standard, linearized and gradient-based ADMM with relaxation, and study their dynamics via a continuous-time model approach.
Regime Switching Bandits
We study a multi-armed bandit problem where the rewards exhibit regime switching.
Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution
Firstly, instead of producing a single score to discriminate images between real and fake, we propose a variant, called Fine-grained Attention Generative Adversarial Network for image super-resolution (FASRGAN), to discriminate each pixel between real and fake.
Semantics-aware BERT for Language Understanding
The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks.
Ranked #8 on
Natural Language Inference
on SNLI
DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension
Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question.
Dual Co-Matching Network for Multi-choice Reading Comprehension
Multi-choice reading comprehension is a challenging task that requires complex reasoning procedure.
Ranked #3 on
Question Answering
on RACE
Dependency or Span, End-to-End Uniform Semantic Role Labeling
Semantic role labeling (SRL) aims to discover the predicateargument structure of a sentence.
Ranked #9 on
Semantic Role Labeling
on CoNLL 2005
Scalable Algorithms for Learning High-Dimensional Linear Mixed Models
We provide theoretical guarantees for our learning algorithms, demonstrating the robustness of parameter estimation.
Affordable On-line Dialogue Policy Learning
The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical.
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy.
On-line Dialogue Policy Learning with Companion Teaching
On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios.
Bayesian Approximate Kernel Regression with Variable Selection
State-of-the-art methods for genomic selection and association mapping are based on kernel regression and linear models, respectively.
