Search Results for author:
Found 35 papers, 16 papers with code
Microsoft COCO Captions: Data Collection and Evaluation Server
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
RESA: Recurrent Feature-Shift Aggregator for Lane Detection
Lane detection is one of the most important tasks in self-driving.
Ranked #4 on
Lane Detection
on TuSimple
From Captions to Visual Concepts and Back
The language model learns from a set of over 400, 000 image descriptions to capture the statistics of word usage.
Ranked #1 on
Image Captioning
on COCO Captions test
Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
Model Inversion (MI) attacks aim to disclose private information about the training data by abusing access to the pre-trained models.
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in practice.
SCREWS: A Modular Framework for Reasoning with Revisions
To enable exploration in this space, we present SCREWS, a modular framework for reasoning with revisions.
Salient Object Ranking with Position-Preserved Attention
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
A Dynamic Speaker Model for Conversational Interactions
Characterizing these differences can be useful in human-computer interaction, as well as analysis of human-human conversations.
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Satisfying these constraints simultaneously is difficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation.
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering
Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular.
Bi-directional Attention with Agreement for Dependency Parsing
We develop a novel bi-directional attention model for dependency parsing, which learns to agree on headword predictions from the forward and backward parsing directions.
Ranked #4 on
Chinese Dependency Parsing
on Chinese Pennbank
Few-Shot Adaptation for Parsing Contextual Utterances with LLMs
We evaluate the ability of semantic parsers based on large language models (LLMs) to handle contextual utterances.
A Factored Neural Network Model for Characterizing Online Discussions in Vector Space
We develop a novel factored neural model that learns comment embeddings in an unsupervised way leveraging the structure of distributional context in online discussion forums.
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows.
Sounding Board: A User-Centric and Content-Driven Social Chatbot
We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement.
Language Models for Image Captioning: The Quirks and What Works
Two recent approaches have achieved state-of-the-art results in image captioning.
Talking to the crowd: What do people react to in online discussions?
This paper addresses the question of how language use affects community reaction to comments in online discussion forums, and the relative importance of the message vs. the messenger.
Planar Shape Detection at Structural Scales
Interpreting 3D data such as point clouds or surface meshes depends heavily on the scale of observation.
Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation
Data sharing for medical research has been difficult as open-sourcing clinical data may violate patient privacy.
Building A User-Centric and Content-Driven Socialbot
Additionally, we construct a new knowledge base to power the socialbot by collecting social chat content from a variety of sources.
Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects
Converting point clouds generated by Laser scanning, multiview stereo imagery or depth cameras into compact polygon meshes is a challenging problem in vision.
Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease
Speech disorders often occur at the early stage of Parkinson's disease (PD).
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers.
Unified Control Framework for Real-Time Interception and Obstacle Avoidance of Fast-Moving Objects with Diffusion Variational Autoencoder
Real-time interception of fast-moving objects by robotic arms in dynamic environments poses a formidable challenge due to the need for rapid reaction times, often within milliseconds, amidst dynamic obstacles.
Surveillance Face Anti-spoofing
In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks.
Surveillance Face Presentation Attack Detection Challenge
Based on this dataset and protocol-$3$ for evaluating the robustness of the algorithm under quality changes, we organized a face presentation attack detection challenge in surveillance scenarios.
Natural Language Decomposition and Interpretation of Complex Utterances
Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations.
Co-audit: tools to help humans double-check AI-generated content
Hence, we are seeing the emergence of tool-assisted experiences to help the user double-check a piece of AI-generated content.
Unified Physical-Digital Face Attack Detection
These three modules seamlessly form a robust unified attack detection framework.
Inverse Optimal Control for Linear Quadratic Tracking with Unknown Target States
A computationally efficient and numerically reliable parameter identification algorithm is proposed by equating optimal control strategies with a system of linear equations, and the associated relative error upper bound is derived in terms of data volume and signal-to-noise ratio.
